AI agents call memory_lint to retrieve information from Exocortex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only analysis of the knowledge base, identifying issues and returning diagnostic information. It does not modify, delete, or execute anything — it 'returns' findings for review. The word 'Run' might suggest execution, but the description clarifies it only reads and reports. Severity is low since misuse would at worst expose internal memory structure.
From the tool's definition 'Run a comprehensive knowledge-base health check. Returns contradictions, stale claims, orphan entities, unlinked memories, and suggested wiki topics.'
Attacks that exploit this kind of access
Run a comprehensive knowledge-base health check. Returns contradictions, stale claims, orphan entities, unlinked memories, and suggested wiki topics. Use periodically to maintain knowledge quality. It is categorised as a Read tool in the Exocortex MCP Server, which means it retrieves data without modifying state.
Register the Exocortex MCP server in PolicyLayer and add a rule for memory_lint: 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 Exocortex. Nothing to install.
memory_lint 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 memory_lint 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 memory_lint. 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.
memory_lint is provided by the Exocortex MCP server (shawnhack/exocortex). 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 →