// MCP TOOL REFERENCE

THOUGHTBOX TOOLS

4 tools from the Thoughtbox MCP Server, categorised by risk level.

READ TOOLS

mental_models Access 15 mental models for structured reasoning. Each model provides a complete prompt with process steps, examples, and pitfalls. Mental models ...

WRITE TOOLS

export_reasoning_chain Export a reasoning session to filesystem as linked JSON structure. Useful for persisting reasoning chains, sharing sessions, or archiving completed... 3/5

EXECUTE TOOLS

notebook Notebook toolhost for literate programming with JavaScript/TypeScript. Create, manage, and execute interactive notebooks with markdown documentati... 3/5 thoughtbox Step-by-step thinking tool for complex problem-solving. Supports flexible reasoning: forward thinking (1→N), backward thinking (N→1), branching, a... 3/5

// FAQ

How many tools does the Thoughtbox MCP server have? +

The Thoughtbox MCP server exposes 4 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on Thoughtbox tools? +

Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Thoughtbox server.

What risk categories do Thoughtbox tools fall into? +

Thoughtbox tools are categorised as Read (1), Write (1), Execute (2). Each category has a recommended default policy.

Enforce policies on Thoughtbox

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept

github.com/policylayer/intercept →