bob_search

THE RISK

Low Risk

Why bob_search needs a policy

The tool appears designed to search indexed conversation history and embeddings. No description is provided, which lowers confidence slightly, but the naming convention ('bob_search'), server purpose (indexing for search), and context of sibling read-only tools all point to a retrieval function with no side effects.

From the tool's definition Tool name 'bob_search' combined with server description stating it 'indexes conversation history...into searchable embeddings' and list of sibling tools that are all read-only queries (tunnel_state, switching_cost, thinking_trajectory,…

Documented attack patterns abuse exactly the kind of access bob_search gives an agent:

POLICY

How to control bob_search

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "bob_search": {}
  }
}

bob_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Brain — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Brain 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_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

All 34 Brain tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about bob_search

What does the bob_search tool do? +

bob_search. It is categorised as a Read tool in the Brain MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on bob_search? +

Register the Brain MCP server in PolicyLayer and add a rule for bob_search: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Brain. Nothing to install.

What risk level is bob_search? +

bob_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit bob_search? +

Yes. Add a rate_limit block to the bob_search rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block bob_search completely? +

Set action: deny in the PolicyLayer policy for bob_search. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides bob_search? +

bob_search is provided by the Brain MCP server (mordechaipotash/brain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

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 →