codegraph_build · Context MCP: Risk & Policy

WHAT IT DOES

What codegraph_build does on Context

AI agents invoke codegraph_build to trigger actions in Context. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why codegraph_build needs a policy

While this tool doesn't directly delete data (Destructive) or move money (Financial), it executes a non-trivial operation that could have significant side effects depending on the directory path provided. An AI agent given an incorrect or malicious path could scan unintended directories, consume excessive resources, or create unexpected graph structures.

From the tool's definition The tool performs scanning and graph building operations on a project directory - 'Scan a project directory and build the knowledge graph from code files.' This involves executing a process that traverses the filesystem and parses code files to construct data…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

codegraph_build Rate-limited

codegraph_build stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "codegraph_build": {
      "limits": [
        {
          "counter": "codegraph_build_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Context, so you can run agents against it safely.

FAQ

Questions about codegraph_build

What does the codegraph_build tool do? +

Scan a project directory and build the knowledge graph from code files. It is categorised as a Execute tool in the Context MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on codegraph_build? +

Register the Context MCP server in PolicyLayer and add a rule for codegraph_build: 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 Context. Nothing to install.

What risk level is codegraph_build? +

codegraph_build is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit codegraph_build? +

Yes. Add a rate_limit block to the codegraph_build 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.

How do I block codegraph_build completely? +

Set action: deny in the PolicyLayer policy for codegraph_build. 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.

What MCP server provides codegraph_build? +

codegraph_build is provided by the Context MCP server (vibhasdutta/context-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.