agent-bridge
This server acts as a bridge between Claude Code and Codex via MCP, enabling you to delegate coding tasks between the two agents.
Delegate tasks to Codex: Send a prompt to Codex, which runs through ACP using
codex-acp.Delegate tasks to Claude Code: Send a prompt to Claude Code, which runs using
claude -p(supports cc-switch proxy).Specify working directory: Optionally set
cwdfor the target agent.Set timeout: Optionally configure
timeoutMs(1,000–600,000 ms, default 120,000 ms) to control wait time.Bidirectional collaboration: Register the server with either agent (or any MCP client) to use the
delegatetool for cross-agent workflows.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@agent-bridgeDelegate to Codex to add unit tests for the authentication module"
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.
agent-delegate-bridge
An MCP server that lets Claude Code and Codex delegate tasks to each other.
Claude Code (or Codex, or any MCP-capable desktop tool) registers this server
and calls the delegate tool. Claude tasks run through claude -p (which
reads the provider proxy env from the cc-switch host-creds file, so it works
from any caller); Codex tasks run through the Agent Client Protocol (ACP).
[Claude Code] --MCP(stdio)--> [agent-delegate-bridge] --claude -p-----> [Claude Code CLI]
[Codex] --MCP(stdio)--> [agent-delegate-bridge] --ACP(stdio)-----> [codex-acp]Install
npm install -g agent-delegate-bridgeAfter installing, the agent-delegate-bridge binary is on your PATH.
Related MCP server: acli-helper
Register in Claude Code
claude mcp add bridge -- agent-delegate-bridgeRegister in Codex
codex mcp add bridge -- agent-delegate-bridge(For development from source, use node dist/index.js instead of agent-delegate-bridge.)
Usage
The delegate tool takes:
target:"codex"or"claude"— which agent to delegate totask: the prompt for the target agentcwd(optional): working directory for the target agenttimeoutMs(optional): max wait in milliseconds, 1000–600000 (default 120000) — raise it when the target is slow (e.g. a flaky network that retries before falling back)
Example prompt to Claude Code:
Use the
delegatetool with target "codex" to ask Codex to write a unit test forsrc/util.ts.
Requirements
Node.js 22+
Codex CLI (for delegating to Codex)
Claude Code (for delegating to Claude)
The ACP adapters are fetched automatically via
npx.
Troubleshooting
Codex delegation fails
Ensure you are logged into Codex (
codexCLI works and ~/.codex/auth.json exists).If
codex-acpfails with authentication errors, runcodex login(or re-authenticate) to refresh your session.The first
npxrun downloads the@agentclientprotocol/codex-acppackage — this may take 30-60 seconds.If delegation fails with a network error, run
codex doctor. If it reports provider endpoints as unreachable, your machine cannot access the ChatGPT API (you may need a proxy/VPN) — this is not a bridge issue.If delegation fails with "You've hit your usage limit", your ChatGPT/Codex account has run out of credits — wait for the quota reset or upgrade. This is an account-level limit, not a bridge issue.
Claude delegation fails
Ensure Claude Code is installed and
claudeis on your PATH.If your Claude is behind a cc-switch proxy, make sure cc-switch is running — the bridge reads the proxy env (ANTHROPIC_BASE_URL, token) from the cc-switch host-creds file so delegation works from any caller.
If the proxy env can't be found, delegation falls back to
claude's own claude.ai login (OAuth must be valid).
Delegation times out
The default timeout is 120 seconds. If the agent takes longer (e.g., complex tasks or slow network), the call will fail with a timeout error. For longer tasks, pass a larger timeoutMs to the delegate tool.
Note: the Codex side can hit a 120s timeout even for short prompts when the adapter keeps waiting — the most common cause is an account/usage error that the adapter never surfaces as a clean response. See "Codex delegation fails" above (usage limit, auth, network) before assuming a real hang.
Publishing to npm
The npm package name is agent-delegate-bridge. (An older package, bridge-mcp-server, is deprecated — don't install it.)
From a clean checkout, npm publish builds dist/ automatically via the prepack script, so the published tarball always matches the source. Typical flow:
npm version patch # bump version (0.1.10 -> 0.1.11)
npm run build && npm test # sanity check
npm publish # prepack runs `npm run build` automatically
git push --follow-tagsdist/is gitignored and not committed; theprepackhook rebuilds it on every publish, so you never ship a stale or empty build.When you change
src/, bump the version and republish — otherwise the installed global binary keeps the old build.Verify the published contents before announcing:
npm pack --dry-runlists the files that will go out.
License
MIT
Available Tools
1 tooldelegateA
Delegate a task to another coding agent (Claude Code or Codex) and return its final output. Use this to hand work to the other agent.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | Working directory for the target agent | |
| task | Yes | The task prompt for the target agent | |
| target | Yes | Which agent to delegate to | |
| timeoutMs | No | Max wait for the target agent in milliseconds (default 120000) |
TDQS
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 only states the high-level behavior of delegation and returning output, but omits important behavioral traits such as waiting behavior, timeouts, potential side effects, or failure modes. This is insufficient for a tool that delegates to an external agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, concise and front-loaded. It conveys the primary action and a usage hint without any unnecessary words, earning a high score for structure.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 4 parameters and no output schema, the description provides a basic understanding but lacks details on the return value structure, error behavior, or how cwd/timeout affect execution. It is adequate but leaves gaps for a tool of this complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents all parameters. The tool description adds no parameter-specific meaning beyond, which is acceptable as the baseline for full schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the action ('Delegate a task') and the resource ('another coding agent (Claude Code or Codex)'), and states the outcome ('return its final output'). It is specific and leaves no ambiguity about what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for use ('Use this to hand work to the other agent'), indicating when the tool should be invoked. However, it lacks explicit exclusions or comparisons to alternatives, so it does not fully earn a 5.
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.
1 tool update
v0.1.11- First observed
delegate
TDQS
Only a single tool exists, so there is no possibility of confusion with other tools. The delegate tool's purpose is clearly described as handing tasks to another agent.
With only one tool, naming consistency is trivially maintained. The name 'delegate' is a clear, imperative verb that matches its action.
The server has exactly one tool, which is borderline and feels thin for a 'bridge' concept. While it covers the core delegation operation, a single tool is at the low end of acceptable scoping.
The delegate tool covers the primary task of handing work to another agent, but there are no tools to discover available agents, check statuses, or manage the bridge. This leaves notable gaps for a full agent-bridge lifecycle.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
A paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage
Related MCP Servers
- FlicenseNot gradedqualityAmaintenanceMCP server that bridges coding agents (Claude Code, Codex, Gemini CLI) via ACP for pair programming, enabling agents to consult each other as tools.-
- AlicenseNot gradedqualityDmaintenanceA multi-agent MCP server that enables AI coding agents (Claude Code, Codex CLI, Gemini CLI) to communicate with each other.MIT
- AlicenseNot gradedqualityCmaintenanceA MCP server that enables Claude Code to delegate coding tasks to Codex via the MCP protocol, with task management, security checks, and result verification.30MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that enables Claude Code to communicate with other Claude Code agents over HTTP, allowing users to ask questions about remote codebases or delegate coding tasks.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/Ming0429/bridge-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server