Medium Risk

agent_capture

Store a thought with schema-enforced metadata. Handles dedup, conflict detection, and supersedes relations. Pass

How to control agent_capture ↓

What agent_capture does on Mybrain

AI agents use agent_capture to create or update resources in Mybrain — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mybrain environment.

Medium Risk

Why agent_capture needs a policy

The tool creates/stores new data (thoughts) in PostgreSQL. It handles deduplication and supersedes relations, indicating it writes and may update existing entries. While it can overwrite or supersede prior records, these actions appear reversible (records remain in DB with relations), placing it in Write rather than Destructive.

From the tool's definition 'Store a thought with schema-enforced metadata. Handles dedup, conflict detection, and supersedes relations.'

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

How to control agent_capture

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 agent_capture:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "agent_capture": {
      "limits": [
        {
          "counter": "agent_capture_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

agent_capture 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.

  1. Create a free account and register Mybrain — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about agent_capture

What does the agent_capture tool do? +

Store a thought with schema-enforced metadata. Handles dedup, conflict detection, and supersedes relations. Pass. 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 agent_capture? +

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

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

Can I rate-limit agent_capture? +

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

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

agent_capture 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.

Free to start. No card required.

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

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.