Scan project files for concept mentions and update code locations. Searches for concept names in source files.
AI agents call scan_codebase to retrieve information from Concept Tracker without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search and retrieval operation across project files to identify and locate references to concepts. While it updates metadata about code locations (which could be interpreted as a side effect), the primary function is scanning/searching—a read operation. It does not create, delete, or execute arbitrary code; it merely indexes and retrieves information about existing code.
From the tool's definition Tool description states it "Searches for concept names in source files" and "update code locations" - a lookup/scanning operation with no modification capability.
Attacks that exploit this kind of access
Scan project files for concept mentions and update code locations. Searches for concept names in source files. It is categorised as a Read tool in the Concept Tracker MCP Server, which means it retrieves data without modifying state.
Register the Concept Tracker MCP server in PolicyLayer and add a rule for scan_codebase: 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 Concept Tracker. Nothing to install.
scan_codebase 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 scan_codebase 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 scan_codebase. 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.
scan_codebase is provided by the Concept Tracker MCP server (liwengggou/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 →