get_agent

THE RISK

Low Risk

Why get_agent needs a policy

The tool retrieves/fetches data (a Roo agent) from the network by event ID and stores it locally. This is a read-only operation from the perspective of data integrity — it does not create, modify, delete, or execute operations on the Nostr network. Saving to a local file is not a destructive or write operation on shared data.

From the tool's definition Tool name and description: 'Get a Roo agent by event ID and save it to .roomodes file' — the action is retrieval ('Get') of an existing agent by identifier. The 'save' operation is to a local file without modifying any remote data or state.

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

POLICY

How to control get_agent

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_agent": {}
  }
}

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

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

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP-NOSTR tools

Write publish Publish a tweet to Nostr Write publish-new-code-snippet Publish a new code snippet to Nostr Read fetch_snippet_by_id Fetch and display a snippet by its ID Read find_agents Find Roo agents with optional filtering by query Read find_instructions Find instructions with optional filtering by query Read find_snippets Find code snippets with optional filtering by author, language, and tags Read get_instructions Get an instruction by event ID Read list_snippets List code snippets metadata (without code content) with filtering by language and tags. Us

All 9 MCP-NOSTR tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get_agent

What does the get_agent tool do? +

Get a Roo agent by event ID and save it to .roomodes file. It is categorised as a Read tool in the MCP-NOSTR MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_agent? +

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

What risk level is get_agent? +

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

Can I rate-limit get_agent? +

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

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

get_agent is provided by the MCP-NOSTR MCP server (pablof7z/tenex-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP-NOSTR tool call.

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

CHECK YOUR STACK →