query_graph · Mnemosyne MCP: Risk & Policy

WHAT IT DOES

What query_graph does on Mnemosyne MCP

AI agents invoke query_graph to trigger actions in Mnemosyne 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 query_graph needs a policy

SPARQL supports not just SELECT (read) but also UPDATE, INSERT, DELETE, and DROP operations. The description says 'execute SPARQL query' without restricting to read-only queries, so this must be treated as Execute. If the agent supplies a destructive SPARQL update, it could irreversibly modify the graph.

From the tool's definition "Execute SPARQL query on knowledge graph" — the tool runs arbitrary SPARQL queries against the graph store

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query_graph Rate-limited

query_graph 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": {
    "query_graph": {
      "limits": [
        {
          "counter": "query_graph_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 Mnemosyne MCP, so you can run agents against it safely.

FAQ

Questions about query_graph

What does the query_graph tool do? +

Execute SPARQL query on knowledge graph, return filtered results (max 100 rows). It is categorised as a Execute tool in the Mnemosyne 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 query_graph? +

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

What risk level is query_graph? +

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

Can I rate-limit query_graph? +

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

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

query_graph is provided by the Mnemosyne MCP server (sophia-labs/mnemosyne-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.