graph_modify

THE RISK

Medium Risk

Why graph_modify needs a policy

The tool modifies (creates and updates) components and segments within P&ID/flowsheet diagrams, which are data structures. While 'remove' could suggest destructive intent, the context (insert/update/remove) indicates standard CRUD operations on graph nodes/edges rather than irreversible deletion of entire documents.

From the tool's definition Tool description explicitly states it "Apply[s] tactical graph modifications" including "insert/update/remove component" and "segment operations" — these are reversible data mutations on engineering diagrams.

Documented attack patterns abuse exactly the kind of access graph_modify gives an agent:

POLICY

How to control graph_modify

PolicyLayer is an MCP gateway — it sits between your AI agents and Engineering MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for graph_modify:

policy.json

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

graph_modify 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.

Create a free account and register Engineering MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Engineering MCP Server tools

Destructive layout_delete Delete a layout from the store Execute layout_compute Compute layout for a model using ELK. Produces orthogonal edge routing suitable for P&ID d Execute model_batch_apply Execute multiple operations in a single call for efficiency Execute rules_apply Apply validation rules and return structured issues for LLM processing. Optionally auto-fi Write area_deploy Deploy a template into a model (STRATEGIC operation - replaces 50+ atomic calls) Write model_tx_begin Start a transaction on a model for atomic multi-operation changes Write model_combine Merge multiple DEXPI models into one combined model. Combines all tagged plant items, inst Write model_load Import a model from various formats (JSON, Proteus XML, SFILES string) - Replaces dexpi_im

All 72 Engineering MCP Server tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about graph_modify

What does the graph_modify tool do? +

Apply tactical graph modifications (10 actions: insert/update/remove component, inline insertion, segment operations, etc.). It is categorised as a Write tool in the Engineering MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on graph_modify? +

Register the Engineering MCP Server MCP server in PolicyLayer and add a rule for graph_modify: 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 Engineering MCP Server. Nothing to install.

What risk level is graph_modify? +

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

Can I rate-limit graph_modify? +

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

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

graph_modify is provided by the Engineering MCP Server MCP server (puran-water/dexpi-sfiles-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Engineering MCP Server tool call.

Start from Engineering MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →