update_graph · Mnemosyne MCP: Risk & Policy

WHAT IT DOES

What update_graph does on Mnemosyne MCP

AI agents invoke update_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 update_graph needs a policy

The tool executes SPARQL UPDATE queries which can perform INSERT (write) and DELETE (destructive) operations. Since it spans both Write and Destructive categories, and the execution is driven by arbitrary query arguments, Execute is the most accurate primary category. The DELETE capability raises severity to high, as misuse could irreversibly remove knowledge graph data.

From the tool's definition 'Execute SPARQL update (INSERT/DELETE) on knowledge graph' — the tool runs arbitrary SPARQL update statements that can both insert and delete triples

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_graph Rate-limited

update_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": {
    "update_graph": {
      "limits": [
        {
          "counter": "update_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 update_graph

What does the update_graph tool do? +

Execute SPARQL update (INSERT/DELETE) on knowledge graph. 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 update_graph? +

Register the Mnemosyne MCP server in PolicyLayer and add a rule for update_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 update_graph? +

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

Can I rate-limit update_graph? +

Yes. Add a rate_limit block to the update_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 update_graph completely? +

Set action: deny in the PolicyLayer policy for update_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 update_graph? +

update_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.