// SCAN REPORT

Brain

34 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated: 11 Jun 2026

0 can modify or destroy data

34 read-only

34 tools total

Community server · catalogue entry verified 11/06/2026

How to control Brain ↓

TOOL MAP

What Brain exposes to your agents

Read (34) Write / Execute (0) Destructive / Financial (0)

Running more than one server? Check your whole stack →

THE RISK

What can go wrong

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

POLICY

How to control Brain

PolicyLayer is an MCP gateway — it sits between your AI agents and Brain, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "bob_dropped": {
    "limits": [
      {
        "counter": "bob_dropped_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Brain — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON BRAIN →

Free to start. No card required.

FULL CATALOGUE

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.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Brain

Is the Brain MCP server safe to use without restrictions? +

The Brain server is primarily read-only with 34 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Brain MCP server expose? +

34 tools across 3 categories: Execute, Read, Write. 34 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on Brain? +

Register the Brain MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Brain tool call.

Deterministic rules across all 34 Brain tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON BRAIN →

Free to start. No card required.

34 Brain tools catalogued and risk-classified — across an index of 43,000+ MCP servers.