atelier_relation

THE RISK

Medium Risk

Why atelier_relation needs a policy

This tool creates a relationship/link between two existing thoughts in the knowledge base. It modifies the data by adding a new relation, but this is a reversible write operation (the relation can presumably be deleted). No code execution, deletion of data, or financial operations are involved.

From the tool's definition Link two thoughts via a typed relation

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

POLICY

How to control atelier_relation

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_relation:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "atelier_relation": {
      "limits": [
        {
          "counter": "atelier_relation_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

atelier_relation stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. 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.

LIMIT 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- Read agent_search Semantic search using three-axis scoring (recency + importance + relevance). Updates last_ Read atelier_browse Browse thoughts with filtering by status, type, agent, and scope. Paginated. 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 →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about atelier_relation

What does the atelier_relation tool do? +

Link two thoughts via a typed relation. It is categorised as a Write tool in the Mybrain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on atelier_relation? +

Register the Mybrain MCP server in PolicyLayer and add a rule for atelier_relation: 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_relation? +

atelier_relation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit atelier_relation? +

Yes. Add a rate_limit block to the atelier_relation 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_relation completely? +

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

atelier_relation 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 →