ThinkSAFE
MCP Server for reasoning
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Think MCP is an implementation of an MCP (Model Context Protocol) server that provides a "think" tool for structured reasoning in agentic AI workflows. This project is inspired by the Anthropic engineering article: The "think" tool: Enabling Claude to stop and think in complex tool use situations.
According to the referenced article, adding the think tool can lead to improved evaluation metrics by enabling reasoning capabilities even in models that do not natively possess advanced reasoning skills.
What is the "think" tool?
The "think" tool allows an AI agent to pause and record an explicit thought during complex reasoning or multi-step tool use. It does not change the environment or database, but appends the thought to the log, helping the agent process information, backtrack, or comply with detailed policies.
This approach is especially useful for:
- Tool output analysis (processing results of previous tool calls)
- Policy-heavy environments (verifying compliance with guidelines)
- Sequential decision making (where each step builds on previous ones)
Features
- Implements the "think" tool as described in Anthropic's research
- Minimal, standards-based MCP server using [mcp[cli]](https://pypi.org/project/mcp/)
- Ready for integration with Claude or other agentic LLMs
Usage
MCP server configuration
Add this MCP server to your facorite agent.
"mcpServers": {
"think-mcp": {
"command": "uvx",
"args": ["think-mcp"],
"enabled": true
}
}Tool definition
The "think" tool is defined as:
- Input:
thought(string) — A thought to think about. - Behavior: Appends the thought to the log for structured reasoning.
Advanc
1ad278de67c9OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add think_mcp -- uvx think_mcp
{
"mcpServers": {
"think_mcp": {
"command": "uvx",
"args": [
"think_mcp"
]
}
}
}Exposed tools (4)
4 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
criticize | read | Use the tool to critic your steps. |
plan | read | Use the tool to plan your steps. |
search | read | Search the web for a given query. |
think | read | Use the tool to think about something. |
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 | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
async def criticize(criticism: str = Field(..., description="Сonstructive criticism")) -> str:
Gates applied: no_behavioural_pass.
1ad278de67c9full audit observations/trust-audit/mcp-server/rai220__think-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 | 1ad278de67c9 | SAFE | B | 89 | first audit |
Questions
What is the Think MCP server?
MCP Server for reasoning
What tools does Think expose?
4 in total: 4 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Think 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.
What credentials does Think need?
No credential environment variables were found in its source, so it appears to need none.
How does Think run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as think_mcp.
How current is this page?
The grade is for one exact copy of the source (1ad278de67c9), read on 2026-10-07. The repository is watched and re-audited when it changes.