// MCP TOOL REFERENCE

BRAINMD TOOLS

17 tools from the brainMD MCP Server, categorised by risk level.

View the brainMD policy →
// ALL 17 BRAINMD TOOLS
READ 15 tools
Read compare_notes Compare two notes: cosine similarity of intros + naive unified diff + shared headings. Read context_for_query Pack top-relevant chunks into a markdown context block under a token budget. Returns text + sources + trunc... Read current_datetime Server Read find_orphans Notes with zero backlinks AND low semantic neighbours (isolation = 1 - max cosine). Read find_related Notes semantically close to a given note path (excludes self). Optional Read find_similar_tasks Semantic search across task lines (- [ ] / - [x]). Filter open/done/all. Read get_backlinks Backlinks for a given note path. Read get_tasks Aggregate tasks vault-wide. Read list_notes List all notes (and folders) in the vault. Read list_tags All tags in the vault with usage counts. Read read_note Read a single note. Returns content + mtime. Read search_notes Full-text search across the vault. Returns top 50 hits. Optional Read semantic_outline Cluster a note Read similar_notes Semantic (vector) search via RAG. Returns top-k chunks with paths and snippets. Optional Read weekly_digest Topic clusters across notes modified in a recent window (e.g.
WRITE 2 tools
Write append_note Append a paragraph to an existing note (ensures a blank-line separator). Write write_note Create or overwrite a note. Content is full body.

Route brainMD through PolicyLayer and every one of its 17 tools is checked against your policy before it runs.

CHECK YOUR STACK →

See every tool, the dangerous ones, and the token cost across your stack.

// FAQ
How many tools does the brainMD MCP server have? +

The brainMD MCP server exposes 17 tools across 2 categories: Read, Write.

How do I enforce policies on brainMD tools? +

Route the brainMD 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 brainMD tools fall into? +

brainMD tools are categorised as Read (15), Write (2). Each category has a recommended default policy.

Enforce policy on every brainMD tool call.

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

CHECK YOUR STACK →

Free to start. No card required.

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

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.