run_langgraph · MCP Demo Project MCP: Risk & Policy

WHAT IT DOES

What run_langgraph does on MCP Demo Project

AI agents invoke run_langgraph to trigger actions in MCP Demo Project. 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 run_langgraph needs a policy

This tool executes a computational workflow (LangGraph) with user-supplied inputs rather than simply retrieving static data. While the operation itself appears benign (generating jokes, stories, or poems), it represents code execution that processes arbitrary input through a workflow engine.

From the tool's definition Tool name explicitly contains 'run' and description states 'Run the langgraph workflow' — this triggers external workflow execution whose effects depend on the input argument (what type of content is generated).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_langgraph Rate-limited

run_langgraph 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": {
    "run_langgraph": {
      "limits": [
        {
          "counter": "run_langgraph_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 MCP Demo Project, so you can run agents against it safely.

FAQ

Questions about run_langgraph

What does the run_langgraph tool do? +

Run the langgraph workflow with the given input to get a joke , story , poem or none. It is categorised as a Execute tool in the MCP Demo Project MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_langgraph? +

Register the MCP Demo Project MCP server in PolicyLayer and add a rule for run_langgraph: 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 MCP Demo Project. Nothing to install.

What risk level is run_langgraph? +

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

Can I rate-limit run_langgraph? +

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

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

run_langgraph is provided by the MCP Demo Project MCP server (vaibhavgala262/mcp_servers). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.