Analyze a repository and return its architecture map: file/module overview, internal import graph, HTTP routes (Express/Fastify/Koa), and frontend-to-backend call edges. Call this FIRST when entering an unfamiliar codebase instead of reading files one by one.
AI agents call analyze_repo to retrieve information from Codebase Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries structural metadata about a codebase (imports, routes, dependencies) with no side effects. It is purely informational—it maps the repository without altering it, executing code, or triggering external operations. The description explicitly positions it as an alternative to manual file reading, reinforcing its Read classification.
From the tool's definition The tool 'analyze_repo' performs static analysis and returns data structures: 'file/module overview, internal import graph, HTTP routes, and frontend-to-backend call edges.' It does not modify, execute against, or delete any code or data.
Attacks that exploit this kind of access
Analyze a repository and return its architecture map: file/module overview, internal import graph, HTTP routes (Express/Fastify/Koa), and frontend-to-backend call edges. Call this FIRST when entering an unfamiliar codebase instead of reading files one by one. It is categorised as a Read tool in the Codebase Context MCP Server, which means it retrieves data without modifying state.
Register the Codebase Context MCP server in PolicyLayer and add a rule for analyze_repo: 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 Codebase Context. Nothing to install.
analyze_repo 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 analyze_repo 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 analyze_repo. 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.
analyze_repo is provided by the Codebase Context MCP server (oh-namgyu/codebase-context-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 →