run_cypher_query · Trip Planner MCP: Risk & Policy

WHAT IT DOES

What run_cypher_query does on Trip Planner MCP

AI agents invoke run_cypher_query to trigger actions in Trip Planner MCP. 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_cypher_query needs a policy

This tool allows execution of arbitrary Cypher queries against a Neo4j database containing employee information. While the description is empty (limiting confidence), the name and context make it clear this is an Execute-category tool. It is not Destructive by default (Cypher alone doesn't mandate irreversibility), but misconfiguration or permissive database access could allow destructive operations.

From the tool's definition Tool name is 'run_cypher_query' which executes Cypher queries against Neo4j. The server description mentions 'Neo4j employee graphs' as a data source.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_cypher_query Rate-limited

run_cypher_query 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_cypher_query": {
      "limits": [
        {
          "counter": "run_cypher_query_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 Trip Planner MCP, so you can run agents against it safely.

FAQ

Questions about run_cypher_query

What does the run_cypher_query tool do? +

run_cypher_query. It is categorised as a Execute tool in the Trip Planner MCP 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_cypher_query? +

Register the Trip Planner MCP server in PolicyLayer and add a rule for run_cypher_query: 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 Trip Planner MCP. Nothing to install.

What risk level is run_cypher_query? +

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

Can I rate-limit run_cypher_query? +

Yes. Add a rate_limit block to the run_cypher_query 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_cypher_query completely? +

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

run_cypher_query is provided by the Trip Planner MCP server (sushruth3002/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.