upsert_edge · TG_ MCP: Risk & Policy

WHAT IT DOES

What upsert_edge does on TG_MCP

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

WHY IT NEEDS A POLICY

Why upsert_edge needs a policy

Upsert operations are Write category because they create or modify data in a reversible manner. Severity is high because an AI agent with access to this tool could maliciously or erroneously modify edges in the TigerGraph database, potentially corrupting relationships between vertices and affecting downstream queries or analyses. However, it is not Destructive (no deletion) or Execute (no arbitrary code execution).

From the tool's definition Tool description states 'Insert or update an edge' — this is a write operation that modifies graph data. The verb 'upsert' (insert or update) indicates reversible data modification.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

upsert_edge Rate-limited

upsert_edge 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": {
    "upsert_edge": {
      "limits": [
        {
          "counter": "upsert_edge_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 TG_MCP, so you can run agents against it safely.

FAQ

Questions about upsert_edge

What does the upsert_edge tool do? +

MCP tool: Insert or update an edge. It is categorised as a Write tool in the TG_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 upsert_edge? +

Register the TG_ MCP server in PolicyLayer and add a rule for upsert_edge: 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 TG_MCP. Nothing to install.

What risk level is upsert_edge? +

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

Can I rate-limit upsert_edge? +

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

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

upsert_edge is provided by the TG_ MCP server (muzain187/tg_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.