checkpoint_run · MEMGRAPH- MCP: Risk & Policy

WHAT IT DOES

What checkpoint_run does on MEMGRAPH-MCP

AI agents use checkpoint_run to create or update resources in MEMGRAPH-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MEMGRAPH-MCP environment.

WHY IT NEEDS A POLICY

Why checkpoint_run needs a policy

The tool modifies run state by applying a patch and persisting a checkpoint. This is a reversible write operation (creating a checkpoint record), not destructive since checkpoints are additive and support resume capabilities. Misuse could corrupt run state but is unlikely to cause irreversible harm.

From the tool's definition Apply a small state patch and create an explicit checkpoint

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

checkpoint_run Rate-limited

checkpoint_run stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "checkpoint_run": {
      "limits": [
        {
          "counter": "checkpoint_run_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MEMGRAPH-MCP, so you can run agents against it safely.

FAQ

Questions about checkpoint_run

What does the checkpoint_run tool do? +

Apply a small state patch and create an explicit checkpoint. It is categorised as a Write tool in the MEMGRAPH-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on checkpoint_run? +

Register the MEMGRAPH- MCP server in PolicyLayer and add a rule for checkpoint_run: 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 MEMGRAPH-MCP. Nothing to install.

What risk level is checkpoint_run? +

checkpoint_run is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit checkpoint_run? +

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

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

checkpoint_run is provided by the MEMGRAPH- MCP server (mikeb317/memgraph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

checkpoint_run is one line of MEMGRAPH-'s registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →