get_source_repo_map
AI agents call get_source_repo_map to retrieve information from Code Expert MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve or generate a semantic/dependency map of a source repository, which is a read-only operation that retrieves data without modifying it. The empty description reduces confidence slightly, but the pattern of sibling tools and the server's stated purpose (providing context to AI assistants) strongly suggest this is a Read categorization.
From the tool's definition The tool name 'get_source_repo_map' uses 'get', a read-only verb, and the server description emphasizes providing 'intelligent context' and 'semantic maps' to coding assistants.
Attacks that exploit this kind of access
get_source_repo_map. It is categorised as a Read tool in the Code Expert MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Code Expert MCP Server MCP server in PolicyLayer and add a rule for get_source_repo_map: 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 Code Expert MCP Server. Nothing to install.
get_source_repo_map 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 get_source_repo_map 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 get_source_repo_map. 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.
get_source_repo_map is provided by the Code Expert MCP Server MCP server (lfnovo/code-expert-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 →