What can you do with this server?

This server coordinates AI-driven software development workflows, integrating Codex for planning, review, debugging, and verification with Antigravity CLI for code execution. * validate_workspace: Checks workspace authorization, Git repository status, and Antigravity CLI availability without modifying files or invoking a model. * summarize_repo_context: Reads repository instruction files (e.g., AGENTS.md, GEMINI.md) to gather project context before coding. * plan_with_codex: Asks Codex to generate and save a structured implementation plan before any code is written, with configurable reasoning depth. * review_with_codex: Asks Codex to review a diff, working tree, or specific files, returning severity-ordered findings in structured JSON. * debug_with_codex: Asks Codex to systematically analyze failures, stack traces, or command output without applying fixes. * verify_with_codex: Runs explicitly allowed verification commands and asks Codex to assess the evidence before declaring completion. * review_code_quality: Runs a local static analysis scan on TypeScript files (checking for as any casts, empty catch blocks, hardcoded secrets, console.log, TODOs, etc.) without consuming any LLM tokens. * run_antigravity_coding_task: Executes coding tasks via Antigravity CLI with strict execute/plan contracts, Git-verified commits, defined file scope, and acceptance criteria traceability. * run_gemini_coding_task: Deprecated alias for run_antigravity_coding_task, providing the same functionality with a deprecation notice. * run_development_workflow: Orchestrates the full plan → implement → review → fix → verify pipeline automatically, with configurable iteration limits, skip flags, and verification commands.

Which integrations are available for this server?

Integrates with OpenAI's Codex CLI for planning, review, debugging, and verification tasks in a software development workflow.

How do I use superpower-codex-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@superpower-codex-mcp Plan and code the user registration feature" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

superpower-codex-mcp

by Pushplayhero

Overview Schema Related Servers Score Discussions

TypeScript

Local

superpower-codex-mcp

A TypeScript MCP server that coordinates Codex and Antigravity CLI with a Superpowers-style software development workflow.

Codex handles planning, review, debugging, and verification. Antigravity CLI is the canonical coding executor. The server adds workspace authorization, Git-based change verification, acceptance criteria, compact task reports, and persisted diagnostics.

Requirements

Node.js 20.19 or newer, or Node.js 22.12 or newer
Codex CLI installed and authenticated
Antigravity CLI (agy) installed and authenticated
Git

Related MCP server: AgentBraid

Install

git clone https://github.com/Pushplayhero/superpower-codex-mcp.git
cd superpower-codex-mcp
npm.cmd install
npm.cmd run build
npm.cmd test

On macOS or Linux, use npm instead of npm.cmd.

Codex Desktop configuration

Add the server to your Codex MCP configuration. Replace the paths with your local clone and the workspaces the server may access.

[mcp_servers.superpower-codex]
command = "node"
args = ["C:\\path\\to\\superpower-codex-mcp\\dist\\src\\index.js"]

[mcp_servers.superpower-codex.env]
SUPERPOWER_CODEX_ALLOWED_ROOTS = "C:\\path\\to\\projects"

Restart Codex Desktop after changing MCP configuration.

On Windows, the server resolves Codex in this order:

SUPERPOWER_CODEX_COMMAND
codex.exe found on PATH
An existing global npm @openai/codex entrypoint

The packaged Codex Desktop binary under WindowsApps\OpenAI.Codex_* is skipped because Windows can reject external child-process launches with EPERM.

If no candidate exists, Codex-backed tools return structured diagnostics with codexCliAvailable: false and the paths that were searched.

Antigravity configuration

In a project that should use this MCP server, add .agents/mcp_config.json:

{
  "mcpServers": {
    "superpower-codex": {
      "command": "node",
      "args": [
        "C:\\path\\to\\superpower-codex-mcp\\dist\\src\\index.js"
      ],
      "env": {
        "SUPERPOWER_CODEX_ALLOWED_ROOTS": "C:\\path\\to\\projects"
      }
    }
  }
}

The default Antigravity executable is:

%LOCALAPPDATA%\agy\bin\agy.exe

Set SUPERPOWER_ANTIGRAVITY_COMMAND when it is installed elsewhere:

$env:SUPERPOWER_ANTIGRAVITY_COMMAND = "C:\custom\path\agy.exe"

Available tools

Tool	Purpose
`validate_workspace`	Validate workspace authorization and local capabilities without invoking a model.
`summarize_repo_context`	Read repository instructions such as `AGENTS.md` and `GEMINI.md`.
`plan_with_codex`	Ask Codex to create and save an implementation plan.
`review_with_codex`	Ask Codex to review a diff or selected files.
`debug_with_codex`	Ask Codex to investigate failures systematically.
`verify_with_codex`	Run explicitly allowed verification commands and ask Codex to assess the evidence.
`review_code_quality`	Run a local TypeScript structural scan without consuming model tokens.
`run_antigravity_coding_task`	Canonical coding execution tool backed by Antigravity CLI.
`run_gemini_coding_task`	Deprecated compatibility alias for `run_antigravity_coding_task`; it does not invoke Gemini CLI directly.
`run_development_workflow`	Coordinate plan, implement, review, fix, and verify stages.

Recommended workflow

Call validate_workspace.
Call summarize_repo_context.
Use plan_with_codex for broad or risky changes.
Execute the approved task with run_antigravity_coding_task.
Use review_code_quality as a token-free pre-filter.
Call review_with_codex.
Send review corrections back to Antigravity when required.
Call verify_with_codex before declaring completion.

For an automated version of this sequence, use run_development_workflow. Its verificationCommands input defaults to ["npm test", "npm run typecheck"] and can be replaced for pnpm, Bun, Python, Go, monorepo, or other project toolchains.

review_with_codex returns validated structured JSON with a status, summary, and severity-ordered findings array. Malformed model output is reported as an error instead of being interpreted as a clean review.

review_code_quality currently supports TypeScript. A Python-only workspace returns unsupportedLanguage: "python" instead of presenting zero scanned files as a clean review. Recursive Python detection ignores virtual environment and build directories (such as venv, .venv, __pycache__, .tox, build, dist, node_modules, and .git).

For explicit mixed selections (e.g. app.ts and app.py), the tool scans the TypeScript files and returns unsupportedFiles: ["app.py"] while omitting unsupportedLanguage.

Coding task example

{
  "workspacePath": "C:\\path\\to\\project",
  "prompt": "Implement the approved task using test-driven development.",
  "allowExecution": true,
  "timeoutSeconds": 1800,
  "model": "Gemini 3.5 Flash (Medium)",
  "mode": "execute",
  "planApproved": true,
  "requireCommit": true,
  "requireCleanWorkspace": true,
  "acceptanceCriteria": [
    {
      "id": "AC-1",
      "description": "The new behavior is covered by a regression test."
    }
  ],
  "allowedFiles": [
    "src/example.ts",
    "tests/example.test.ts"
  ],
  "responseDetail": "summary"
}

Supported model names:

gemini-3.5-flash
Gemini 3.5 Flash (Medium)
Gemini 3.1 Pro (High)

Unsupported legacy Gemini model names are rejected. The server does not automatically retry with a stronger model.

Status model and diagnostics

Coding task statuses

The coding tools (run_antigravity_coding_task and the legacy alias run_gemini_coding_task) return a JSON payload with a status field:

planned: A requested planning task was completed.
implemented_unverified: Files may be implemented, but required test or acceptance evidence is incomplete.
tests_passed: All supplied acceptance criteria map to named passing tests, but no commit was required or verified.
committed: Required commit and acceptance evidence were verified successfully.
mode_mismatch: Execute mode was requested, but the model asked for approval or returned a plan-only response.
contract_failed: Preconditions or postconditions failed (e.g., dirty workspace before execution, missing commit, output outside allowedFiles).
execution_failed: The tool or a required Git command failed to execute.
timed_out: Execution exceeded the configured timeout.

Workflow statuses

completed: Every recorded stage completed successfully.
completed_with_issues: Implementation ran, but one or more later stages did not complete successfully.
failed: The workflow could not pass an early prerequisite such as planning.

Deprecation guidance

Structured JSON responses from the legacy alias run_gemini_coding_task include a top-level machine-readable deprecation object:

"deprecation": {
  "message": "run_gemini_coding_task is deprecated. Please use run_antigravity_coding_task instead.",
  "replacement": "run_antigravity_coding_task"
}

Workflow diagnostics

When run_development_workflow does not complete cleanly, it returns these additional diagnostic fields:

failedStage: The name of the first failing stage (e.g. "plan", "implement", "review", "verify").
nextAction: A descriptive recommendation on what to do next to resolve the issue.
failureSummary: The failed stage summary lifted to the top level.
failureDetails: The failed stage details lifted to the top level.

Workspace safety

By default, only the MCP process working directory and its descendants are allowed. Additional roots must be explicitly configured:

$env:SUPERPOWER_CODEX_ALLOWED_ROOTS = "C:\projects;D:\work"

Use ; as the delimiter on Windows and : on macOS or Linux.

Additional safeguards:

Coding execution requires allowExecution: true.
Verification commands require allowCommandExecution: true.
Verification commands run without a shell; pipes, redirects, and command separators are rejected.
Strict execution compares reported files and commits with Git metadata.
allowedFiles accepts only repository-relative paths.
Antigravity does not recursively call the coding-task MCP tool.

Development

npm.cmd install
npm.cmd run typecheck
npm.cmd test
npm.cmd run build

The verified baseline is 160 passing tests across 11 test files.

Updating an existing Windows installation

Download superpower-codex-mcp-v0.1.1-windows.zip from the GitHub release, extract it, and run:

powershell -NoProfile -ExecutionPolicy Bypass `
  -File .\scripts\update-installed.ps1 `
  -InstallPath "C:\path\to\superpower-codex-mcp"

The updater validates the installation, creates a backup under .update-backups, installs production dependencies, and verifies MCP tool discovery. Restart Codex Desktop after the update.

License

MIT

Available Tools

10 tools

debug_with_codexA

Ask Codex to analyze a failure using systematic debugging without applying fixes.

ParametersJSON Schema

Name	Required	Description
`workspacePath`	Yes	Repository or workspace path.
`symptom`	Yes	Observed failure or bug.
`commandOutput`	Yes	Relevant command output, stack trace, or logs.
`recentChanges`	No	Recent changes that may be related.

TDQS

A3.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description fully carries the burden of behavioral disclosure. It explicitly states that no fixes are applied, which is a critical behavioral trait. However, it lacks details on side effects, error handling, or permissions required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no wasted words. While it is very concise, it could benefit from a slight expansion to cover key aspects like the systematic approach or expected output.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that there is no output schema and no annotations, the description should explain what the tool returns or achieves. It only says 'analyze a failure', leaving the agent uncertain about the outcome or whether it gets a report, suggestions, or just a confirmation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description does not add extra meaning to the parameters beyond what the schema already provides. It mentions 'analyze a failure' but does not elaborate on parameter usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: to analyze a failure using systematic debugging without applying fixes. It uses a specific verb ('analyze') and resource ('failure'), and distinguishes from sibling tools like 'review_with_codex' and 'verify_with_codex' which have different focuses.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for debugging failures without fixing them, but it does not explicitly state when to use it or when to use alternatives. No guidance on exclusions or prerequisites is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

plan_with_codexA

Ask Codex to create a Superpowers-style implementation plan before Gemini CLI edits code. Returns and saves the plan.

ParametersJSON Schema

Name	Required	Description	Default
`workspacePath`	Yes	Repository or workspace path.
`goal`	Yes	Implementation goal.
`constraints`	No	Constraints Codex must respect.
`doneWhen`	No	Completion criteria.
`reasoningLevel`	No	Planning depth.	medium

TDQS

A3.5/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the tool 'returns and saves the plan', indicating persistence. However, it does not detail where the plan is saved, side effects on the workspace, permissions needed, or rate limits. The behavioral information is adequate but somewhat vague.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise at two sentences. It front-loads the core action ('Ask Codex to create an implementation plan') and adds a key behavioral detail ('returns and saves the plan'). No extraneous words or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of an output schema, the description could elaborate on what the plan contains (e.g., steps, structure) to help the agent anticipate results. While the tool is moderately complex with 5 parameters, the description provides only minimal context on the output format. It is sufficient but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the input schema already documents all five parameters with basic descriptions. The tool description does not add any extra meaning or usage guidance for the parameters beyond what the schema provides. Hence, baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool creates an implementation plan and returns/saves it. The verb 'Ask Codex to create' and noun 'implementation plan' provide a specific purpose. However, the phrase 'Superpowers-style' is somewhat jargon-like and may not be universally understood, slightly reducing clarity. It distinguishes from sibling tools focused on review or debugging.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions 'before Gemini CLI edits code', indicating when to use the tool (pre-editing). No explicit when-not-to-use guidance or alternatives are listed. The usage is implied but clear enough for an agent to infer it should be called before code modifications, not for reviews or verification.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

review_code_qualityA

Static analysis pre-filter for Codex. Scans TypeScript files for as any casts, empty catch blocks, hardcoded secrets, console.log, TODO comments, and other structural issues — all without calling an LLM. Run before Codex review to save token costs.

ParametersJSON Schema

Name	Required	Description
`workspacePath`	Yes	Repository or workspace path to scan.
`files`	No	Specific file paths (relative to workspace). Default: all src/*/.ts plus tests/*/.ts.
`checks`	No	Specific checks to run. Default: all.
`maxFindings`	No	Max findings to return.

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses it is a static analysis tool that does not call an LLM, implying read-only behavior. However, it does not mention error handling, return format, or potential side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loading the purpose and usage guidance. Every sentence adds value with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and simple parameters, the description covers the tool's function, usage context, and key behaviors. Minor gap: no explanation of return values or output format, but still adequate for selection.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds context by listing specific checks (e.g., 'as any', console.log) and default file paths, but does not elaborate on parameter syntax beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose as a static analysis pre-filter for Codex, scanning TypeScript files for specific structural issues. It distinguishes from siblings like review_with_codex by noting it runs without an LLM.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use the tool ('Run before Codex review to save token costs'), providing clear usage context. However, it does not explicitly mention when not to use it or compare with alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

review_with_codexA

Ask Codex to review the current diff or selected files. Returns findings first, ordered by severity.

ParametersJSON Schema

Name	Required	Description	Default
`workspacePath`	Yes	Repository or workspace path.
`reviewScope`	No	Review context scope.	diff
`files`	No	Relative files for specific-files review.
`focus`	No	Review focus.

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It discloses the return behavior: 'Returns findings first, ordered by severity.' This informs the agent about output order. However, it does not mention side effects (likely none for a review) or authentication needs. The description adds value beyond the schema's parameter descriptions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is only two sentences, with no extraneous words. It is front-loaded with the core action and immediately provides the key behavioral trait (ordered by severity). Perfectly concise for the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description could elaborate on the structure of 'findings' (e.g., types, metadata). It provides minimal contextual completeness. The tool has 4 parameters with good schema coverage, but the description does not cover edge cases or usage scenarios. Adequate but not comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so each parameter is already well-documented. The description adds no new semantic meaning beyond the schema; it only states the overall behavior. Baseline score of 3 is appropriate as the description does not significantly enhance parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool's purpose: 'Ask Codex to review the current diff or selected files.' This specific verb-object pairing ('review... diff or selected files') immediately distinguishes it from sibling tools like 'debug_with_codex' or 'plan_with_codex'. The mention of ordering by severity adds specificity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description implies when to use the tool (for code review) but does not explicitly state when not to use it or contrast with alternatives. Sibling tool names like 'review_code_quality' and 'validate_workspace' provide some context, but no direct exclusion is given. The guidance is clear but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

run_antigravity_coding_taskC

Canonical coding execution tool. Invokes Antigravity CLI while Codex retains planning, review, debugging, and verification responsibilities. Supports strict execute/plan contracts, Git-verified commits and file scope, acceptance-test traceability, and compact responses with persisted diagnostics.

ParametersJSON Schema

Name	Required	Description
`workspacePath`	Yes	Repository or workspace path.
`prompt`	Yes	Prompt for the coding task.
`allowExecution`	No	Must be true before invoking the tool.
`timeoutSeconds`	No
`mode`	No
`planApproved`	No
`requireCommit`	No
`requireCleanWorkspace`	No
`acceptanceCriteria`	No
`allowedFiles`	No
`model`	No	The model to use for the coding task.
`responseDetail`	No

TDQS

C2.8/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions 'compact responses with persisted diagnostics' and 'Git-verified commits' but does not disclose key traits such as potential destructiveness, required permissions, or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, but dense with technical jargon ('execute/plan contracts', 'acceptance-test traceability'). Could be more accessible without sacrificing meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 12 parameters and no output schema, the description leaves significant gaps: return values, error handling, and usage workflow are not explained. The tool is complex, but the description is too high-level.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is low (33% of parameters have descriptions). The description adds no parameter-specific meaning beyond the schema, failing to compensate for the gap. For example, the meaning of 'allowExecution' and 'planApproved' remain unclear from description alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it is a 'coding execution tool' that invokes Antigravity CLI, distinguishing from sibling planning and review tools. The purpose is specific and resource-oriented, though jargon-heavy.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Mentions support for 'execute/plan contracts' and 'Git-verified commits', implying use for execution tasks. However, no explicit when-to-use vs alternatives or when-not-to-use guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

run_development_workflowA

Orchestrate plan, implement, review, fix, and verify stages. Codex plans, reviews, and verifies; Antigravity executes coding and fix iterations.

ParametersJSON Schema

Name	Required	Description	Default
`workspacePath`	Yes	Repository or workspace path.
`goal`	Yes	Implementation goal.
`constraints`	No	Constraints the plan must respect.
`doneWhen`	No	Completion criteria.
`model`	No	Model for coding task.	gemini-3.5-flash
`skipPlan`	No	Skip planning phase if a plan already exists.
`skipReview`	No	Skip code review phase.
`skipVerify`	No	Skip final verification phase.
`verificationCommands`	No	Commands used for final verification.
`maxIterations`	No	Max code-review-fix iterations.

TDQS

A3.5/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided; description only assigns roles (Codex vs Antigravity) but does not disclose safety, destructiveness, or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise, front-loaded sentences with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Adequate for a composite tool but lacks details on workflow order, error handling, and iteration behavior; output schema absent but not required.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage with good descriptions for all 10 parameters; description adds no extra meaning beyond naming actors.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it orchestrates multiple stages (plan, implement, review, fix, verify) and differentiates from sibling tools which are individual steps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied usage for full development cycle but no explicit when-to-use or when-not-to-use compared to individual sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

run_gemini_coding_taskC

Deprecated compatibility alias for run_antigravity_coding_task. Invokes Antigravity CLI for coding. Supports strict execute/plan contracts, Git-verified commits and file scope, acceptance-test traceability, and compact responses with persisted diagnostics.

ParametersJSON Schema

Name	Required	Description
`workspacePath`	Yes	Repository or workspace path.
`prompt`	Yes	Prompt for the coding task.
`allowExecution`	No	Must be true before invoking the tool.
`timeoutSeconds`	No
`mode`	No
`planApproved`	No
`requireCommit`	No
`requireCleanWorkspace`	No
`acceptanceCriteria`	No
`allowedFiles`	No
`model`	No	The model to use for the coding task.
`responseDetail`	No

TDQS

C2.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description lists behavioral traits like strict contracts and Git verification, but omits potential side effects, authentication, or irreversible actions. Provides moderate transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with a bullet-like list of features, which is efficient and front-loaded. Could be slightly more structured but remains clear.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter tool with no output schema, the description is too brief. It lacks details on return values, error handling, and comprehensive usage context, leaving gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is low (33%), and the description does not compensate by adding meaning to individual parameters. It mentions features like acceptance-test traceability but does not connect to the schema's acceptanceCriteria parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly identifies the tool as a deprecated compatibility alias for run_antigravity_coding_task, stating its purpose. However, it does not differentiate itself from the sibling tool beyond being deprecated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies deprecation but does not explicitly state when to use this tool vs alternatives. No guidance on prerequisites or context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

summarize_repo_contextA

Read repository instruction files such as AGENTS.md and GEMINI.md. Returns startup context for Gemini CLI before coding.

ParametersJSON Schema

Name	Required	Description
`workspacePath`	Yes	Repository or workspace path to summarize.
`includeFiles`	No	Additional relative files to include.
`maxChars`	No	Maximum characters to read.

TDQS

A3.6/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions reading instruction files and returning startup context, but lacks details on default files read, potential errors, or the nature of the returned context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences with no filler, front-loading the key action and purpose efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having 3 parameters and no output schema, the description does not explain the return value in detail or cover error scenarios, leaving gaps in completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with parameter descriptions. The tool description adds no extra meaning beyond the schema, earning the baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Read' and resource 'repository instruction files' with specific examples (AGENTS.md, GEMINI.md), and distinguishes from sibling tools that focus on debugging, planning, or code review.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for obtaining startup context before coding, but does not explicitly specify when to use this tool versus alternatives like plan_with_codex or validate_workspace.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

validate_workspaceA

Validate and canonicalize a workspace before loading context or starting Gemini. Returns structured authorization and capability diagnostics without modifying files or invoking a model.

ParametersJSON Schema

Name	Required	Description
`workspacePath`	Yes	Repository or workspace path to validate.
`checkGit`	No	Check for Git repository root.
`checkAntigravityCli`	No	Check for Antigravity CLI availability.

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description states it does not modify files or invoke a model, and returns structured authorization and capability diagnostics. With no annotations provided, this disclosure is valuable for the agent to understand it is a safe, read-only operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the purpose and includes behavioral info. No wasted words; every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 3 parameters with full schema descriptions and no output schema, the description adequately explains purpose and behavior. It could be slightly more complete by hinting at the diagnostic structure, but it is sufficient for agent understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description does not add additional meaning beyond the schema's parameter descriptions. It only broadly mentions validation and canonicalization.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it validates and canonicalizes a workspace before loading context or starting Gemini. It specifies the resource (workspace) and action (validate/canonicalize), and distinguishes from sibling tools that focus on coding tasks, reviews, and debugging.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description explicitly says 'before loading context or starting Gemini', indicating when to use. It does not provide when-not-to-use or alternatives, but the context is clear and distinct from sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

verify_with_codexB

Gate completion claims. Plans verification or runs explicitly allowed commands and asks Codex to assess the evidence.

ParametersJSON Schema

Name	Required	Description
`workspacePath`	Yes	Repository or workspace path.
`expectedBehavior`	Yes	Behavior that should now be true.
`verificationCommands`	No	Commands to run when command execution is allowed.
`allowCommandExecution`	No	Must be true before the MCP server runs commands.

TDQS

B3.3/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries full burden. It explains that the tool plans verification or runs allowed commands and asks Codex to assess evidence, but it does not disclose potential side effects, permission requirements, or whether the operation is destructive. The core behavior is described moderately.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise at two sentences, but the first sentence 'Gate completion claims' is somewhat cryptic and could be clearer. Overall, it is efficient with no redundant text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Without an output schema, the description fails to specify what the tool returns (e.g., assessment results, success/failure). Given the complexity of verification, the lack of return value details and missing behavioral context (e.g., how Codex's assessment is presented) makes the description incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds no parameter-specific details beyond what the schema already provides, such as the semantics of 'expectedBehavior' or 'verificationCommands'. It does not enhance understanding of parameter usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states it 'gates completion claims' by planning verification or running commands and using Codex for assessment. While 'gate' is somewhat unconventional, it clearly indicates a verification role, distinguishing it from sibling tools like plan_with_codex or review_code_quality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for verifying completion claims but does not explicitly state when to use this tool versus alternatives such as review_with_codex or debug_with_codex. No exclusions or context are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

2 tool updatesv0.1.1Jun 16, 2026

Changedreview_code_quality1 field changed

changedInput schema / properties / files / description

Previous value: -"Specific file paths (relative to workspace). Default: all src/**/*.ts."New value: +"Specific file paths (relative to workspace). Default: all src/**/*.ts plus tests/**/*.ts."

Changedrun_development_workflow1 field changed

addedInput schema / properties / verificationCommands

Added value: +{
+  "default": [
+    "npm test",
+    "npm run typecheck"
+  ],
+  "description": "Commands used for final verification.",
+  "items": {
+    "type": "string"
+  },
+  "minItems": 1,
+  "type": "array"
+}

10 tool updatesv0.1.0Jun 13, 2026
- First observeddebug_with_codex
- First observedplan_with_codex
- First observedreview_code_quality
- First observedreview_with_codex
- First observedrun_antigravity_coding_task
- First observedrun_development_workflow
- First observedrun_gemini_coding_task
- First observedsummarize_repo_context
- First observedvalidate_workspace
- First observedverify_with_codex

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: Codex-based analysis (debug, plan, review, verify), CLI-based implementation (antigravity, gemini), static quality check, context summarization, workspace validation, and a workflow orchestrator. No two tools have overlapping responsibilities.

Naming Consistency4/5

All names use snake_case and follow a verb_noun pattern. However, there are two subpatterns: 'verb_with_codex' (debug, plan, review, verify) and 'run_*' tasks plus standalone verbs (review_code_quality, summarize_repo_context, validate_workspace). This minor inconsistency prevents a perfect score.

Tool Count5/5

With 10 tools, the set is well-scoped for a development assistant. Each tool addresses a specific phase or support function without unnecessary duplication or missing critical steps.

Completeness4/5

The tools cover the full development loop: context loading, workspace validation, planning, implementation (two CLIs), static quality review, deep review, debugging, verification, and an orchestrated workflow. A slight gap is the lack of an explicit undo/rollback mechanism, but the workflow tool can manage iterations.

Maintenance

ActivityStale

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

AgentDrive A
sh.agentdrive
Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.
Agent Orchestration Developer Tools
202
AI Worlds CLI Knowledge A
com.claude-world
Source-checked CLI guides and model-aware planning for Claude Code, Codex, and Grok Build.
Command Line Developer Tools Documentation Access
121
TokenmaxxingOAuth
io.github.Brock-Denton
Coordinate coding agents through MCP using existing AI plans, saved work, and independent checks.
Agent Orchestration Coding Agents Autonomous Agents
1
Roamer MCPOAuth
com.mathismeadows
Project registry, behavioral specs, and engineering threads for AI coding agent workflows.
Agent Orchestration Developer Tools Project Management
1

Related MCP Servers

codex-agy-bridge
Agent Orchestration Autonomous Agents
varadfromeast
A
license
B
quality
A
maintenance
An MCP bridge that lets Codex delegate long-running agent work to the Antigravity CLI, providing observable and resumable tool-based execution with project scoping.
Updated 2 months ago (2026-07-20 17:58 UTC)
13
7
MIT
AgentBraid
Agent Orchestration Version Control Developer Tools
xuu33030
A
license
Not graded
quality
B
maintenance
A local-first MCP orchestration server that uses Codex as lead planner and Antigravity as host to delegate and review bounded tasks with Git integration and persistent SQLite state.
Updated a month ago (2026-07-30 00:44 UTC)
Apache 2.0
nokto-agent-orchestrator MCPofficial
Agent Orchestration Coding Agents Version Control
noktohq
A
license
Not graded
quality
B
maintenance
Orchestrates Claude Code and OpenAI Codex to plan, implement, review, and verify code changes via pull requests with security controls.
Updated 6 days ago (2026-08-31 20:33 UTC)
1
MIT
agent-delegation-mcp
Coding Agents Autonomous Agents Code Execution
artcar12
A
license
Not graded
quality
B
maintenance
Enables Claude Code to delegate implementation tasks to Antigravity CLI and OpenCode, run them fully autonomously, and then review and gate the results.
Updated 23 days ago (2026-08-14 17:33 UTC)
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Pushplayhero/superpower-codex-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

superpower-codex-mcp

Requirements

Install

Codex Desktop configuration

Antigravity configuration

Available tools

Recommended workflow

Coding task example

Status model and diagnostics

Coding task statuses

Workflow statuses

Deprecation guidance

Workflow diagnostics

Workspace safety

Development

Updating an existing Windows installation

License

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

nokto-agent-orchestrator MCPofficial

Latest Blog Posts

MCP directory API