Low Risk

find_relations

Find how two concepts are connected. Args: - sourceUri: URI of the source concept - targetUri: URI of the target concept - max_hops: 1 | 2 | 3 (default: 1) Returns: - Direct connections (single predicate) - Multi-hop paths up to the configured depth

How to control find_relations ↓

What find_relations does on Schema Gov It MCP Server

AI agents call find_relations to retrieve information from Schema Gov It MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why find_relations needs a policy

This is a query/search operation over the Italian government data catalog ontologies and vocabularies. It retrieves relationship information between concepts without creating, modifying, deleting, or executing any operations. The blast radius of misuse is minimal—an agent could only learn about data relationships, not alter or act upon them.

From the tool's definition Tool name 'find_relations' and description indicate it 'Find[s] how two concepts are connected' by returning 'Direct connections' and 'Multi-hop paths'.

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

How to control find_relations

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "find_relations": {}
  }
}

find_relations is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Schema Gov It MCP Server — 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.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about find_relations

What does the find_relations tool do? +

Find how two concepts are connected. Args: - sourceUri: URI of the source concept - targetUri: URI of the target concept - max_hops: 1 | 2 | 3 (default: 1) Returns: - Direct connections (single predicate) - Multi-hop paths up to the configured depth. It is categorised as a Read tool in the Schema Gov It MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on find_relations? +

Register the Schema Gov It MCP Server MCP server in PolicyLayer and add a rule for find_relations: 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 Schema Gov It MCP Server. Nothing to install.

What risk level is find_relations? +

find_relations is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit find_relations? +

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

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

find_relations is provided by the Schema Gov It MCP Server MCP server (italia/dati-semantic-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Schema Gov It MCP Server tool call.

Start from Schema Gov It MCP Server, 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.

47 Schema Gov It MCP Server 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.