atelier_browse

THE RISK

Low Risk

Why atelier_browse needs a policy

This tool retrieves and displays stored thoughts from a knowledge base using filters and pagination. It performs no write, delete, or execute operations; it only reads and presents data. The minimal blast radius of misuse would be exposure of personal knowledge, which is low severity in a personal knowledge base context where the user owns the data.

From the tool's definition Tool description states 'Browse thoughts with filtering by status, type, agent, and scope. Paginated.' — browse and filter operations are query/retrieval actions with no modification or side effects.

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

POLICY

How to control atelier_browse

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

policy.json

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

atelier_browse 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 Mybrain — 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 Mybrain tools

Write agent_capture Store a thought with schema-enforced metadata. Handles dedup, conflict detection, and supe Write atelier_hydrate Hydrate JSONL telemetry from a Claude Code project sessions directory into the brain. Non- Write atelier_relation Link two thoughts via a typed relation. Read agent_search Semantic search using three-axis scoring (recency + importance + relevance). Updates last_ Read atelier_hydrate_status Returns the completion state of a previous atelier_hydrate call for the given session_path Read atelier_stats Brain health check and statistics. Reports brain_enabled, counts by type/status/agent, con Read atelier_trace Traverse the relation graph from a thought. Backward = what led here. Forward = what follo

All 8 Mybrain 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 atelier_browse

What does the atelier_browse tool do? +

Browse thoughts with filtering by status, type, agent, and scope. Paginated. It is categorised as a Read tool in the Mybrain MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on atelier_browse? +

Register the Mybrain MCP server in PolicyLayer and add a rule for atelier_browse: 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 Mybrain. Nothing to install.

What risk level is atelier_browse? +

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

Can I rate-limit atelier_browse? +

Yes. Add a rate_limit block to the atelier_browse 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 atelier_browse completely? +

Set action: deny in the PolicyLayer policy for atelier_browse. 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 atelier_browse? +

atelier_browse is provided by the Mybrain MCP server (robertsfeir/mybrain). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mybrain tool call.

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

CHECK YOUR STACK →