// MCP TOOL REFERENCE

BRAIN TOOLS

34 tools from the Brain MCP Server, categorised by risk level.

// ALL 34 BRAIN TOOLS

READ 34 tools

Read bob_dropped Inspect what L1 filtered out. Optional `reason` filter (e.g. 'cc:build-log-paste'). Read alignment_check Check if a decision aligns with your principles. Read bob_conversations_by_date List all conversations active on a given date (YYYY-MM-DD). For each Read bob_health Report the state of Bob's local memory. Use this first if you don't know Read bob_recent Most recent turns within the last `hours`. Filter by src and/or role. Read bob_search bob_search Read bob_thinking_trajectory Chronological pass on a topic — first mention to most recent. Shows how Read bob_tunnel_state Reconstruct work-in-progress on a domain/topic. Returns the most recent Read bob_what_do_i_think Surface the user's own positions on a topic. Filters to role='user' turns Read brain_stats brain_stats Read cognitive_patterns Analyze cognitive patterns and problem-solving approaches. Read context_recovery Full 'waking up' brief for re-entering a domain. Read conversations_by_date Get conversations from a specific date (YYYY-MM-DD format). Read dormant_contexts Find abandoned tunnels — domains with open questions you haven't resolved. Read get_conversation Get the full content of a specific conversation by ID. Read get_principle Get detailed info about a specific principle. Read github_search github_search Read list_principles List your configured principles. Read query_analytics query_analytics Read search_conversations search_conversations Read search_docs search_docs Read search_summaries search_summaries Read semantic_search Search conversations using semantic similarity (vector embeddings). Read switching_cost Estimate cognitive cost of switching between domains. Read thinking_trajectory thinking_trajectory Read trust_dashboard System-wide stats proving the prosthetic works. Read tunnel_history Meta-view of your engagement with a domain over time. Read unfinished_threads Find conversations worth revisiting: exploring/crystallizing stage with open questions. Read unified_search Search across ALL sources: conversations, GitHub, markdown. Read what_do_i_think what_do_i_think Read what_was_i_thinking Time-travel snapshot: What was on your mind during a specific month? Read bob_open_threads Surface unfinished work — user turns from the last 14 days ending in a Read open_threads Global inventory of ALL open questions across ALL domains. Read tunnel_state Reconstruct cognitive save-state for a domain — where you left off.

// FAQ

How many tools does the Brain MCP server have? +

The Brain MCP server exposes 34 tools across 1 categories: Read.

How do I enforce policies on Brain tools? +

Route the Brain 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 Brain tools fall into? +

Brain tools are categorised as Read (34). Each category has a recommended default policy.

Enforce policy on every Brain tool call.

Start from Brain, 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.