AI agents use capture_adr 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.
This tool creates and stores a new ADR entry in the persistent PostgreSQL-backed memory store. It is a write operation (creates new records) with no indication of irreversibility or destructive behavior. Misuse could pollute the knowledge base with incorrect architectural decisions, hence medium severity.
From the tool's definition 'Record an Architecture Decision Record. Captures the decision, its context, alternatives considered, and consequences. Automatically numbers the ADR within the current brain.'
Attacks that exploit this kind of access
Record an Architecture Decision Record. Captures the decision, its context, alternatives considered, and consequences. Automatically numbers the ADR within the current brain. 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.
Register the Brain MCP server in PolicyLayer and add a rule for capture_adr: 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.
capture_adr is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the capture_adr 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.
Set action: deny in the PolicyLayer policy for capture_adr. 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.
capture_adr 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →