What can you do with this server?

Think MCP is a structured reasoning server that enables LLMs to break down complex problems through sequential thinking, branching, and cross-session memory. Core Capabilities: Sequential Reasoning - Use think to add step-by-step thoughts with confidence scoring (1-10), sub-steps breakdown, and alternative approaches. Use think_batch to submit up to 30 thoughts in a single call for high-velocity reasoning with atomic validation. Branching & Revision - Explore alternative solution paths from any thought using branchId or revise previous thoughts with isRevision: true to correct mistakes without losing context. Deep Analysis Framework - Generate structured methodologies with think_logic through 4 phases: Chain Mapping → Crack Hunting → Standard Benchmark → Action Planning. Customize by depth (quick/standard/deep), focus (security, performance, reliability, UX, data-flow), and technology stack (NestJS, React, Redis, Next.js, etc.). Cross-Session Memory - Search current session thoughts or retrieve insights from previous sessions (24-hour retention) using think_recall with fuzzy matching across thoughts, extensions, and alternatives. Session Management - Finalize with think_done to validate logic gaps, unresolved blockers, and low-confidence thoughts, with optional export in Markdown or JSON format (including Mermaid diagrams). Use think_reset to clear context and start fresh. Intelligent Assistance - Built-in Nudge System provides proactive warnings for low confidence, tunnel vision, missing breakdowns, and unresolved blockers, plus complexity-based tool recommendations and stagnation detection. Performance Features - ~55% token reduction through imperative prompts, ASCII tree visualization, quick inline extensions (critique, elaborate, correct, innovate, polish), and progress tracking with next-action hints.

Which integrations are available for this server?

Supports exporting thought sessions in Markdown format for human-readable documentation of reasoning processes.

How do I use Think 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., "@Think MCP help me debug this authentication error in our NestJS API" 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.

Think MCP

by GofMan5

Overview Schema Related Servers Score Discussions

TypeScript

Think MCP

Structured reasoning tools for MCP-compatible LLM clients

npm version license mcp release gates

Reason step by step, branch when needed, block weak finals, and keep useful memory across sessions.

Install | Tools | think_cycle | Quality Gates | Changelog

Why this exists

Most LLM workflows fail in predictable ways:

They answer too early.
They stay linear when the task needs alternatives or critique.
They lose earlier insights between steps.
They finish with confidence that is not backed by verification.

Think MCP adds an external reasoning layer for those failures. It does not replace the model's intelligence. It constrains and structures the way that intelligence is used.

What is in 5.6.0

Added explicit coaching, completion blockers, and deterministic next-action routing for models.
Made finalized cycles terminal, restart-safe, and idempotent, including insight retries.
Rejected blank summaries and disconnected winning paths before state or insights are committed.
Kept omitted confidence optional instead of inventing false low-confidence failures.
Strengthened deep logic guidance with source evidence and an attempted refutation.
Replaced title-only regex evals with executable MCP and cycle behavioral tests.

Core model

Think MCP combines three layers:

Layer	Role	Outcome
`think` / `think_batch`	Capture incremental or prebuilt reasoning	Better decomposition, branching, revisions
`think_cycle`	Enforce adaptive depth and hard final gate	Blocks shallow or weak final answers
Recall + coaching + validation	Preserve useful context and warn on weak patterns	Better consistency and fewer dead-end sessions

Install

Run directly

npx -y @gofman3/think-mcp

MCP config

{
  "mcpServers": {
    "think": {
      "command": "npx",
      "args": ["-y", "@gofman3/think-mcp"]
    }
  }
}

Local development

npm install
npm run build
npm test

Toolset

Tool	Purpose	Best use
`think`	Add one structured reasoning step	Medium-complexity tasks that need guided progression
`think_batch`	Submit one already-built reasoning chain	Fast validation of a complete prebuilt chain
`think_cycle`	Adaptive reasoning state machine with a hard process gate	High-risk or high-complexity tasks
`think_logic`	Return a read-only analysis checklist	Choosing methodology before doing an audit
`think_recall`	Search the active scope or stored insights	Reuse patterns, avoid repeating dead ends
`think_done`	Finalize a `think` or `think_batch` scope	Controlled non-cycle completion
`think_reset`	Clear the active scope state	Hard context shift only

`think_cycle`

think_cycle is the main depth-control tool in the current release.

It runs a session as a state machine:

start -> step -> status -> finalize

If the reasoning process is incomplete, finalize does not silently pass. It blocks completion and returns one concrete next action plus the required minimum of additional thoughts.

Key behavior

Adaptive required depth based on goal complexity and risk markers.
Hard gate for phase coverage: decompose, alternative, critique, synthesis, verification.
Structural quality score with penalties for repetition, weak verification, and unstable confidence. It does not pretend to judge semantic truth.
Confidence is optional; stability is reported only after two scored steps instead of inventing missing data.
Explicit constraintCheck before finalizing a session that started with constraints.
Terminal completion: a completed cycle keeps its approved answer, rejects new steps, and retries a failed deduplicated insight save safely.
Fallback interop with the regular think backend when backendMode=auto.
Loop budget control to avoid infinite cost and latency growth.

Input shape

{
  action: 'start' | 'step' | 'status' | 'finalize' | 'reset',
  sessionId?: string,
  scopeId?: string,
  goal?: string,
  context?: string,
  constraints?: string[],
  thought?: string,
  thoughtType?: 'decompose' | 'alternative' | 'critique' | 'synthesis' | 'verification' | 'revision',
  confidence?: number,
  finalAnswer?: string,
  constraintCheck?: string,
  backendMode?: 'auto' | 'independent' | 'think',
  maxLoops?: number,
  showTrace?: boolean,
  exportReport?: 'markdown' | 'json',
  includeMermaid?: boolean
}

Output shape

{
  status: 'in_progress' | 'blocked' | 'ready' | 'completed' | 'error',
  sessionId: string,
  scopeId?: string,
  loop: { current: number, max: number, required: number, remaining: number },
  quality: {
    overall: number,
    coverage: number,
    critique: number,
    verification: number,
    diversity: number,
    confidenceStability?: number
  },
  gate: { passed: boolean, reasonCodes: string[] },
  requiredMoreThoughts: number,
  nextPrompts: string[],
  shortTrace?: string[],
  finalApprovedAnswer?: string
}

Example flow

// 1. Start
{
  action: 'start',
  goal: 'Design a safe migration from Redis session cache to Postgres-backed sessions',
  constraints: ['zero logout spike', 'rollback in under 5 minutes'],
  backendMode: 'auto'
}

// 2. Add steps
{
  action: 'step',
  sessionId: 'cycle_xxx',
  thought: 'Break the migration into dual-write, read-fallback, rollout metrics, and rollback paths.'
}

// 3. Try to finalize
{
  action: 'finalize',
  sessionId: 'cycle_xxx',
  finalAnswer: 'We should migrate in phases and monitor it carefully...'
}

Typical blocked response:

{
  status: 'blocked',
  gate: { passed: false, reasonCodes: ['MISSING_PHASE_VERIFICATION'] },
  requiredMoreThoughts: 1,
  nextPrompts: [
    'Next: think_cycle step with thoughtType="verification" — define tests, metrics, and rollback triggers.'
  ]
}

Other tools

`think`

Use when you want incremental reasoning with revisions, branches, substeps, and quick extensions.

scopeId is optional and accepted only on thoughtNumber=1. If omitted on the first thought, a new active scope is created.

{
  thought: 'The bug likely comes from stale branch state after retry.',
  thoughtNumber: 1,
  totalThoughts: 3,
  nextThoughtNeeded: true,
  confidence: 6,
  quickExtension: {
    type: 'critique',
    content: 'Verify whether retry state is recreated or reused.'
  }
}

`think_batch`

Use only when the complete chain is already built and you want to validate it atomically in one call.

scopeId is optional. If omitted, batch submission creates a new active scope.

{
  goal: 'Audit deployment rollback flow',
  thoughts: [
    { thoughtNumber: 1, thought: 'Identify every entry point that can change rollout state and ownership.' },
    { thoughtNumber: 2, thought: 'Trace rollback triggers, timeout behavior, and observable recovery evidence.' }
  ]
}

`think_logic`

Use for strict methodology generation before an audit. It returns instructions, not findings; deep adds an evidence-and-disconfirmation gate.

{
  target: 'Review the payment retry pipeline for consistency and failure isolation',
  depth: 'deep',
  focus: ['reliability', 'performance', 'data-flow']
}

`think_recall`

Use before starting a familiar class of problem. Session recall searches the full active scope across the active think state and every attached think_cycle session. You can also pass an explicit scopeId.

{
  query: 'rollback strategy cache migration',
  scope: 'insights',
  limit: 5
}

`think_done`

By default, think_done finalizes the active think scope. Pass scopeId to finalize an inactive think scope explicitly. A cycle-only scope has no think history, so finalize it with think_cycle action finalize instead.

Quality and release gates

Release verification is built into the repo:

npm run validate:release

Main checks:

TypeScript typecheck
Unit and behavioral MCP tests (npm test; focused: npm run eval:local)
Repo structure validation
Security audit
Hard quality baseline in docs/quality/HARD_QUALITY_STANDARD.md

Runtime storage

Default data directory: ~/.think-mcp
Override with THINK_MCP_DATA_DIR
think_cycle sessions persist in runtime storage with TTL cleanup
Shared scope metadata persists in runtime_state.json

Package links

npm: @gofman3/think-mcp
repo: GofMan5/think-mcp

Changelog

v5.6.0

Added actionable model guidance and deterministic tool routing.
Hardened cycle completion, persistence, retries, confidence scoring, and state integrity.
Added real stdio and cycle behavioral evaluation while simplifying the build and package.

v5.5.1

Fixed broken mojibake output in runtime coaching strings.
Rebuilt and refreshed README for the current toolset and quality model.
Released documentation and packaging cleanup on top of 5.5.0.

v5.5.0

Added think_cycle for adaptive external reasoning with hard quality gates.
Added release-gated hard quality policy based on NEED_ADD.
Added eval scenarios for cycle gating, fallback behavior, autonomy quality, safety gates, and bounded retries.

v5.1.0

Switched prompt style toward imperative IF/THEN instructions.
Reduced token overhead significantly for common reasoning flows.

v5.0.0

Added think_logic methodology generation.

Available Tools

5 tools

thinkThinkA

Add one evolving reasoning step. Use for iterative work, revisions, or branches.

Whole chain ready -> think_batch. Enforced multi-pass gate -> think_cycle. Code-audit checklist -> think_logic.

Returns progress, surfaced guidance, and one next action.

ParametersJSON Schema

Name	Required	Description
`goal`	No	Session goal (set on first thought)
`scopeId`	No	Shared reasoning scope id (allowed only on thoughtNumber=1)
`thought`	Yes	Your thinking step
`branchId`	No	Branch identifier
`showTree`	No	Show ASCII tree
`subSteps`	No	Micro-actions (max 5)
`confidence`	No	Confidence 1-10
`isRevision`	No	Revising previous thought?
`alternatives`	No	Options to compare
`thoughtNumber`	Yes	Current number
`totalThoughts`	Yes	Estimated total
`quickExtension`	No	Inline extension (replaces separate extension tool)
`revisesThought`	No	Which thought to revise
`branchFromThought`	No	Branch point
`nextThoughtNeeded`	Yes	More thinking needed?

TDQS

A3.7/5.0

Behavior2/5

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

Annotations only include 'openWorldHint: false' with no readOnly or destructive hints. The description adds minimal behavioral context beyond stating it returns 'progress, surfaced guidance, and one next action'. It does not disclose effects on state, authorization needs, or parameter interaction behaviors.

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 highly concise, using only 4 sentences. The primary purpose is stated first, followed by sibling differentiations and a summary of returns. Every sentence earns its place with no redundancy.

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?

Despite 15 parameters and nested objects, the description is brief. It omits details on how parameters like 'subSteps', 'alternatives', or 'quickExtension' work together. The absence of an output schema increases the need for behavioral description, which is lacking.

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 adds no significant meaning beyond the schema, only reiterating the tool's purpose and return value. It does not explain parameter relationships or usage patterns.

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 adds one evolving reasoning step for iterative work, revisions, or branches. It distinguishes from sibling tools by naming alternatives like 'think_batch' and 'think_cycle'.

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 (iterative work, revisions, branches) and provides clear alternatives (think_batch, think_cycle, think_logic). However, it does not include explicit 'when not to use' guidance.

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

think_cycleThink CycleA

Run an enforced multi-pass reasoning loop for high-risk or ambiguous work.

Start once, then follow the single returned next step until the gate passes; finish with action=finalize. If start had constraints, include constraintCheck. For ordinary iterative work use think. Do not use think_done for a cycle.

Interop:

backendMode=auto: mirror to think backend with fallback
backendMode=think: strict think backend mode (no fallback)
backendMode=independent: standalone cycle only

ParametersJSON Schema

Name	Required	Description
`goal`	No	Goal for start action
`action`	Yes	Cycle action
`context`	No	Additional context
`scopeId`	No	Shared reasoning scope id (start only)
`thought`	No	Thought content for step action
`maxLoops`	No	Loop budget
`sessionId`	No	Cycle session id (required except start)
`showTrace`	No	Show expanded trace
`confidence`	No	Confidence for step thought (stability is reported after two scored steps)
`backendMode`	No	Interop backend mode
`constraints`	No	Constraints list
`finalAnswer`	No	Final answer candidate for finalize
`thoughtType`	No	Optional thought type override
`exportReport`	No	Export format for finalize
`includeMermaid`	No	Include Mermaid diagram in finalize export
`constraintCheck`	No	For finalize with constraints: map each constraint to evidence or a verification step

TDQS

A4.6/5.0

Behavior4/5

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

The description reveals the multi-pass cycle behavior (start, step, gate, finalize) and the interplay with backends through backendMode. It adds constraint handling guidance. Annotations provide openWorldHint=false, which describes bounding of effects; the description complements this with workflow details. No contradictions with annotations.

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 concisely structured with a clear first sentence, a step-by-step flow paragraph, a sibling comparison sentence, and a bullet list for interop modes. Every sentence adds value; no wasted text.

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 the tool's complexity (16 parameters, no output schema, minimal annotations), the description provides a good overview of the lifecycle and usage. It covers when to use, the start-step-finalize flow, and interop. However, it does not explain the gate mechanism or stability concept mentioned in parameter descriptions, which would be helpful for full understanding.

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

Parameters4/5

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

Input schema has 100% coverage with descriptions for all 16 parameters. The description does not document parameters individually but integrates some into the workflow (e.g., constraints, constraintCheck, backendMode). This adds marginal value beyond schema, so score is above baseline 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 tool's purpose as an enforced multi-pass reasoning loop for high-risk or ambiguous work. It distinguishes from siblings by explicitly directing users to use 'think' for ordinary iterative work and warning against using 'think_done' for a cycle. The verb 'run' and resource 'reasoning loop' are specific.

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

Usage Guidelines5/5

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

The description provides explicit guidance on when to use this tool ('for high-risk or ambiguous work') and when not to ('for ordinary iterative work use think'). It also warns against using 'think_done' for a cycle, giving clear alternatives. The interop section further clarifies backend mode selection.

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

think_doneThink DoneA

Verify and close a think/think_batch scope before a complex final answer.

For think_cycle use action=finalize. Rejects path gaps or unresolved blockers and returns the next correction.

ParametersJSON Schema

Name	Required	Description
`scopeId`	No	Explicit think scope id (defaults to active scope)
`summary`	Yes	Final logic summary
`verdict`	Yes	Ready for answer?
`winningPath`	Yes	Thought numbers leading to solution
`exportReport`	No	Export format (optional)
`includeMermaid`	No	Include diagram in export

TDQS

A3.7/5.0

Behavior4/5

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

The description adds behavioral details beyond the sparse annotation (openWorldHint: false): it reveals that the tool performs verification, closure, and can reject with next corrections. It also mentions a specific action for think_cycle. This provides useful context about what the tool does internally.

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: two sentences, no fluff. The first sentence front-loads the main purpose, and the second adds key behavioral details. Every sentence is necessary and directly informative.

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?

For a tool with 6 parameters and no output schema, the description provides adequate context (verification, closure, rejection). It mentions returning 'next correction', hinting at output. However, it lacks explanation of how parameters interact or the overall workflow (e.g., after you have a winning path). The think_cycle reference adds some cross-tool context but also potential confusion.

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?

The input schema has 100% parameter coverage with descriptions, so the baseline is 3. The description does not add any additional meaning about parameters beyond the schema. It does not explain how parameters like winningPath or verdict relate to the tool's behavior.

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 'Verify and close a think/think_batch scope', which is a specific verb+resource. It distinguishes from siblings by mentioning 'For think_cycle use action=finalize', indicating a different use case. However, the reference to think_cycle within the description is slightly confusing and could be clearer about the differentiation.

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 using this tool 'before a complex final answer', which gives a usage context. It also describes rejection conditions. However, it does not explicitly compare with sibling tools or provide when-not-to-use guidance. The reference to think_cycle is an alternative but not fully explanatory.

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

think_logicThink LogicA

Read-only

Return a read-only code-analysis checklist. It does not inspect code, store progress, or produce findings.

Use only when a model needs a methodology; use think or think_cycle to perform the analysis.

ParametersJSON Schema

Name	Required	Description	Default
`depth`	No	Methodology depth	standard
`focus`	No	Focus areas to prioritize
`stack`	No	Tech stacks for stack-specific checks
`target`	Yes	What to analyze (feature, flow, component, system description)
`context`	No	Additional context (tech stack, constraints, requirements)

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already indicate readOnlyHint=true, and description reinforces read-only behavior and adds boundaries (no code inspection, no storage, no findings). No contradictions, and description adds context beyond annotations.

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 sentences plus one usage directive; front-loaded with purpose, no wasted words. Every sentence adds value.

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

Completeness5/5

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

Given the tool's simplicity (read-only checklist with well-described schema), the description covers purpose, usage, and behavioral boundaries adequately. No gaps for an AI agent to select and invoke correctly.

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. Description does not add additional meaning beyond schema; parameters are already well-described in the input 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?

Description clearly states it returns a read-only code-analysis checklist, explicitly stating what it does not do (inspect code, store progress, produce findings). It also distinguishes from siblings by directing to use think or think_cycle for analysis.

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

Usage Guidelines5/5

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

Explicit usage guidance: 'Use only when a model needs a methodology' and specifies alternatives (think, think_cycle) for performing analysis. This provides clear when-to-use and when-not-to-use conditions.

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

think_recallThink RecallA

Read-only

Read-only search of an active/explicit scope or saved insights.

Use before repeating work or relying on prior reasoning.

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No	Max results
`query`	Yes	Search query (fuzzy matching)
`scope`	No	Where to search	session
`scopeId`	No	Explicit scope id (session recall only)
`searchIn`	No	What to search (session only)	all
`threshold`	No	Match strictness (lower = stricter)

TDQS

A4.2/5.0

Behavior4/5

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

The description confirms the read-only nature ('Read-only search') as indicated by annotations (readOnlyHint=true) and adds context about scope types. No contradictions.

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?

Extremely concise with two sentences, front-loading the purpose. Every word adds value.

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 the schema fully describes parameters, annotations present, and no output schema, the description adequately covers the tool's functionality for a read-only search.

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 minimal parameter insight beyond 'saved insights' mapping to scope; no extra detail on limit, threshold, etc.

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 specifies a clear verb ('search') and resource ('active/explicit scope or saved insights'), distinguishing it from sibling tools like think and think_done.

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: 'before repeating work or relying on prior reasoning.' It does not provide negative examples or alternatives, but the context is clear.

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.

7 tool updatesv5.6.0Jul 26, 2026

Changedthink2 fields changed

changedInput schema / properties / quickExtension / description

Previous value: -"Inline extension (replaces extend_thought)"New value: +"Inline extension (replaces separate extension tool)"

addedInput schema / properties / scopeId

Added value: +{
+  "description": "Shared reasoning scope id (allowed only on thoughtNumber=1)",
+  "type": "string"
+}

Removedthink_batch
Addedthink_cycle

Changedthink_done5 fields changed

removedInput schema / properties / constraintCheck

Removed value: -{
-  "description": "How constraints were addressed",
-  "type": "string"
-}

removedInput schema / properties / potentialFlaws

Removed value: -{
-  "description": "What could go wrong",
-  "type": "string"
-}

addedInput schema / properties / scopeId

Added value: +{
+  "description": "Explicit think scope id (defaults to active scope)",
+  "type": "string"
+}

addedInput schema / properties / summary / minLength
```
Added value: +1
```
addedInput schema / properties / winningPath / minItems
```
Added value: +1
```

Addedthink_logic

Changedthink_recall1 field changed

addedInput schema / properties / scopeId

Added value: +{
+  "description": "Explicit scope id (session recall only)",
+  "type": "string"
+}

Removedthink_reset

5 tool updatesv1.0.0Jan 3, 2026
- First observedthink
- First observedthink_batch
- First observedthink_done
- First observedthink_recall
- First observedthink_reset

Install Server

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

TDQS

A3.8/5.0

Disambiguation4/5

Tools have distinct purposes (add step, close, recall, cycle, logic checklist), but think_done references 'think_batch' which is not a tool, potentially causing confusion.

Naming Consistency2/5

Four tools follow 'think_' prefix pattern, but one is simply 'think' without the underscore, breaking consistency.

Tool Count5/5

5 tools is well-scoped for a reasoning assistant, each serving a clear role without being overwhelming.

Completeness3/5

Covers core reasoning operations but lacks the referenced 'think_batch' tool and potentially missing features like reset or status.

Maintenance

ActivitySlowing

ResponsivenessSyncing

Resources

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

agentstack-mcp A
io.github.inity13
Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.
Autonomous Agents Agent Orchestration
241
LiminalityOAuth
ai.physea
Breaks a hard question or decision into checkable sub-questions, grounds each to a real tool.
1
MindlifyOAuth
co.mindlify
Turn AI conversations into visual knowledge maps. Create, connect, search, and organize thoughts.
Knowledge & Memory Note Taking
1
Fify B
io.github.renfei-design
Turn grounded AI answers into trusted comparisons, plans, timelines, and decision views.
AI & Machine Learning Data Visualization
211

Related MCP Servers

Visum Thinker MCP Server
Autonomous Agents Travel & Transportation Developer Tools
multiluca2020
A
license
B
quality
Not graded
maintenance
Provides structured sequential thinking capabilities for AI assistants to break down complex problems into manageable steps, revise thoughts, and explore alternative reasoning paths.
Updated 6 months ago (2026-03-17 12:49 UTC)
29
-
CRASH - Cascaded Reasoning
Autonomous Agents Code Analysis Developer Tools
nikkoxgonzales
A
license
A
quality
A
maintenance
Enables structured, iterative reasoning for complex problem-solving with features like confidence tracking, revision mechanisms, and branching support. Provides flexible validation and multiple output formats for systematic analysis and decision-making tasks.
Updated 9 months ago (2025-12-17 15:53 UTC)
1
22
72
MIT
Sequential Thinking MCP Server
Autonomous Agents Developer Tools
cmarin
A
license
A
quality
D
maintenance
Enables structured, step-by-step problem-solving with dynamic revision and branching capabilities. Supports breaking down complex problems into manageable steps while allowing course corrections and alternative reasoning paths.
Updated a year ago (2025-08-26 04:30 UTC)
1
102,549
1
-
Sequential Thinking MVP Server
Autonomous Agents Developer Tools Knowledge & Memory
fmangot
A
license
B
quality
Not graded
maintenance
Enables AI assistants to perform structured, step-by-step reasoning by breaking down complex problems into numbered thoughts, with support for revising previous steps and exploring alternative reasoning paths.
Updated 10 months ago (2025-11-16 19:58 UTC)
5
-

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/GofMan5/think-mcp'

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