capture_code_context · Brain MCP: Risk & Policy

WHAT IT DOES

What capture_code_context does on Brain

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

WHY IT NEEDS A POLICY

Why capture_code_context needs a policy

This tool writes new data to the persistent semantic memory store (PostgreSQL/pgvector), creating thought records and dimensions. It has reversible write semantics (data can be archived or overwritten), but no destructive, financial, or execution behavior. Misuse could pollute the knowledge base with incorrect code context, hence medium severity.

From the tool's definition 'Capture knowledge about code', 'Creates dimensions for repo, file, and symbol automatically'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

capture_code_context Rate-limited

capture_code_context 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.

View as policy code

policy.json

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

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Brain, so you can run agents against it safely.

FAQ

Questions about capture_code_context

What does the capture_code_context tool do? +

Capture knowledge about code — decisions, observations, or facts linked to specific files, symbols, or repositories. Creates dimensions for repo, file, and symbol automatically. It is categorised as a Write tool in the Brain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on capture_code_context? +

Register the Brain MCP server in PolicyLayer and add a rule for capture_code_context: 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 capture_code_context? +

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

Can I rate-limit capture_code_context? +

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

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

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