Think ToolSAFE
An MCP server implementing the think tool for Claude
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server implementing the "think" tool for improving Claude's complex reasoning capabilities.
Overview
This MCP server implements the "think" tool as described in Anthropic's blog post, which provides Claude with a dedicated space for structured thinking during complex problem-solving tasks. The think tool has been shown to significantly improve performance in complex tasks requiring policy adherence and reasoning in long chains of tool calls.
Features
- Structured Thinking Space: Provides Claude with a dedicated place to break down complex problems
- Thought History: Maintains a log of all thoughts with timestamps for reference
- Statistics and Analysis: Offers metadata about thinking patterns
- Clean Slate Option: Allows clearing thought history when starting fresh
Installation
Install from PyPI:
pip install mcp-think-tool
Configuration
Windsurf
To use this tool with Claude in Windsurf, add the following configuration to your MCP config file:
"think": {
"command": "/home/xxx/.local/bin/mcp-think-tool",
"args": [],
"type": "stdio",
"pollingInterval": 30000,
"startupTimeout": 30000,
"restartOnFailure": true
}The command field should point to the directory where you installed the python package using pip.
Docker
You can install this MCP server with only the Dockerfile
First download the Dockerfile, navigate to its directory, and build the Docker image
docker build -t mcp-think-tool .
Then add the following configuration your MCP config file
"think": {
"command": "docker",
"args": ["run", "--rm", "-i", "mcp-think-tool"]
}This was tested and working with Claude Desktop and Cursor
b11099ea5ac6OBSERVED · 2026-10-07Exposed tools (4)
3 read · 0 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
clear_thoughts | destructive | Clear all recorded thoughts from the current session. |
get_thought_stats | read | Get statistics about the thoughts recorded in the current session. |
get_thoughts | read | Retrieve all thoughts recorded in the current session. |
think | read | Use this tool to think about something. It will not obtain new information or change anything, |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
clear_thoughts
Gates applied: no_behavioural_pass.
b11099ea5ac6full audit observations/trust-audit/mcp-server/dannymac180__think-tool-2.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | b11099ea5ac6 | SAFE | B | 89 | first audit |
Questions
What is the Think Tool MCP server?
An MCP server implementing the think tool for Claude
What tools does Think Tool expose?
4 in total: 3 read-only, 0 that write, and 1 that can delete or overwrite (clear_thoughts). Every one is listed on this page with its risk.
Is Think Tool safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Think Tool need?
No credential environment variables were found in its source, so it appears to need none.
How does Think Tool run?
It speaks stdio, so it runs as a local process your client starts.
How current is this page?
The grade is for one exact copy of the source (b11099ea5ac6), read on 2026-10-07. The repository is watched and re-audited when it changes.