Medium Risk

add_facts

Add facts (relationships) to the graph. Nodes are auto-created if they don

How to control add_facts ↓

What add_facts does on Mcp Graph Engine

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

Medium Risk

Why add_facts needs a policy

The tool creates new relationships (facts) in the graph database, which is a reversible write operation. It modifies the graph state by adding edges/relationships and potentially creating nodes. While this can grow a graph significantly, it is reversible via tools like 'delete_graph' or selective deletion, so it does not qualify as Destructive.

From the tool's definition Tool name 'add_facts' and description 'Add facts (relationships) to the graph' clearly indicates creation/modification of data. The description is cut off ('Nodes are auto-created if they don') but the intent to add relationships is explicit.

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

How to control add_facts

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_facts": {
      "limits": [
        {
          "counter": "add_facts_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

add_facts 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.

  1. Create a free account and register Mcp Graph Engine — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about add_facts

What does the add_facts tool do? +

Add facts (relationships) to the graph. Nodes are auto-created if they don. It is categorised as a Write tool in the Mcp Graph Engine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_facts? +

Register the Mcp Graph Engine MCP server in PolicyLayer and add a rule for add_facts: 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 Mcp Graph Engine. Nothing to install.

What risk level is add_facts? +

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

Can I rate-limit add_facts? +

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

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

add_facts is provided by the Mcp Graph Engine MCP server (utilitydelta/mcp-graph-engine). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcp Graph Engine tool call.

Start from Mcp Graph Engine, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

24 Mcp Graph Engine tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.