HEURISTIC TOOLS

7 tools from the Heuristic MCP Server, categorised by risk level.

// ALL 7 HEURISTIC TOOLS

READ 3 tools

Read a_semantic_search Performs intelligent hybrid code search combining semantic understanding with exact text matching. Ideal fo... Read d_find_similar_code Find similar code patterns in the codebase. Given a code snippet, returns other code chunks that are semant... Read e_check_package_version Fetches the latest version of a package from its official registry. Supports npm, PyPI, crates.io, Maven, G...

WRITE 2 tools

Write d_ann_config Configure and monitor the ANN (Approximate Nearest Neighbor) search index. Actions: Write f_set_workspace Changes the current workspace path at runtime. This updates the search directory and cache, and optionally ...

DESTRUCTIVE 1 tools

Destructive c_clear_cache Clears the embeddings cache, forcing a complete reindex on next search or manual index operation. Useful wh...

EXECUTE 1 tools

Execute b_index_codebase Manually trigger a full reindex of the codebase. This will scan all files and update the embeddings cache. ...

// FAQ

How many tools does the Heuristic MCP server have? +

The Heuristic MCP server exposes 7 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Heuristic tools? +

Route the Heuristic server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Heuristic tools fall into? +

Heuristic tools are categorised as Read (3), Write (2), Destructive (1), Execute (1). Each category has a recommended default policy.

Enforce policy on every Heuristic tool call.

Start from Heuristic, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Instant setup, no code required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.