AI agents call refresh_stale_knowledge to retrieve information from Brain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs semantic search and comparison operations to identify potentially outdated knowledge entries. It does not modify, delete, or execute any operations—it merely queries the PostgreSQL-backed vector database and presents results with diffs for human review. The phrase 'decide whether to supersede them' indicates the decision and action belong to the user, not the tool itself.
From the tool's definition The tool 'refresh_stale_knowledge' is described as finding and showing knowledge with diffs—it retrieves stale thoughts and returns them with context. The verb 'show' and 'returns' indicate data retrieval with no modification or deletion.
Attacks that exploit this kind of access
Find knowledge that may be stale due to code changes and show diffs. Returns stale thoughts with enough context to decide whether to supersede them. It is categorised as a Read tool in the Brain MCP Server, which means it retrieves data without modifying state.
Register the Brain MCP server in PolicyLayer and add a rule for refresh_stale_knowledge: 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.
refresh_stale_knowledge is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the refresh_stale_knowledge 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 refresh_stale_knowledge. 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.
refresh_stale_knowledge 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 →