ThinkSAFE
A minimal MCP Server based on the Anthropic's "think" tool research
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/@marcopesani/think-mcp-server)
A minimal MCP Server based on the Anthropic's "think" tool research
Overview
This project implements a minimal Message Control Protocol (MCP) server that provides Claude AI models with the "think" tool capability. Based on Anthropic's research published on March 20, 2025, this implementation enables Claude to perform better on complex reasoning tasks involving multi-step tool usage.
What is the "think" tool?
The "think" tool gives Claude the ability to include an additional thinking step—with its own designated space—as part of reaching a final answer. Unlike extended thinking (which happens before response generation), the "think" tool allows Claude to pause during response generation to consider whether it has all necessary information to proceed.
Key benefits:
- Improves complex problem-solving performance
- Enhances policy adherence in tool usage
- Increases consistency in decision making
- Helps with multi-step problems requiring careful reasoning
Implementation
This server implements the "think" tool with the following specification:
{
"name": "think",
"description": "Use the tool to think about something. It will not obtain new information or change the database, but just append the thought to the log. Use it when complex reasoning or some cache memory is needed.",
"input_schema": {
"type": "object",
"properties": {
"thought": {
"type": "string",
"description": "A thought to think about."
}
},
"required": ["thought"]
}
}When to Use the "think" Tool
Based on Anthropic's research, this tool is most beneficial for:
- Tool Output Analysis: When Claude needs to process previous tool call outputs before acting
- Policy-Heavy Environments: When Claude must follow detailed guidelines
- Sequential Decision Making:
92582f5a90dcOBSERVED · 2026-10-09Connect
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-server -- npx -y [email protected]
{
"mcpServers": {
"think-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
think | read | Use the tool to think about something. It will not obtain new information or change the database, |
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 | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, zod, @types/node, typescript
Gates applied: no_behavioural_pass.
92582f5a90dcfull audit observations/trust-audit/mcp-server/marcopesani__think.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 |
|---|---|---|---|---|---|
| 2026-10-09 | 92582f5a90dc | SAFE | B | 89 | first audit |
Questions
What is the Think MCP server?
A minimal MCP Server based on the Anthropic's "think" tool research
What tools does Think expose?
1 in total: 1 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 npm as think-mcp-server at 0.1.1.
How current is this page?
The grade is for one exact copy of the source (92582f5a90dc), read on 2026-10-09. The repository is watched and re-audited when it changes.