graph_ingest · CodeGraph MCP Server MCP: Risk & Policy

WHAT IT DOES

What graph_ingest does on CodeGraph MCP Server

AI agents invoke graph_ingest to trigger actions in CodeGraph MCP Server. 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 graph_ingest needs a policy

While the tool does not delete data (Destructive), modify existing code artifacts (Write in the sense of code changes), or move money (Financial), it does execute a process that ingests code from a filesystem and registers results. This is an Execute category action because it triggers an operation whose effects (graph construction, resource consumption, state changes) depend on the arguments (target directory).

From the tool's definition The tool 'graph_ingest' is described as triggering code ingestion for a target directory and registering the graph. The verb 'trigger' combined with 'ingest' indicates activation of an external process that scans and processes files in the specified directory.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

graph_ingest Rate-limited

graph_ingest 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": {
    "graph_ingest": {
      "limits": [
        {
          "counter": "graph_ingest_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 CodeGraph MCP Server, so you can run agents against it safely.

FAQ

Questions about graph_ingest

What does the graph_ingest tool do? +

Trigger code ingestion for a target directory and register the graph. It is categorised as a Execute tool in the CodeGraph MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on graph_ingest? +

Register the CodeGraph MCP Server MCP server in PolicyLayer and add a rule for graph_ingest: 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 CodeGraph MCP Server. Nothing to install.

What risk level is graph_ingest? +

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

Can I rate-limit graph_ingest? +

Yes. Add a rate_limit block to the graph_ingest 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 graph_ingest completely? +

Set action: deny in the PolicyLayer policy for graph_ingest. 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 graph_ingest? +

graph_ingest is provided by the CodeGraph MCP Server MCP server (nabiatech/codegraph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.