Low Risk

recent_additions

List agent-ready sites newly added to the Not Human Search index, sorted newest first. Use this to discover what's just landed on the agentic web — new MCP servers, fresh llms.txt adopters, new OpenAPI publishers. Good for weekly agent digests or tracking ecosystem momentum.

Part of the Not Human Search server.

recent_additions is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE NOT HUMAN SEARCH →

Free to start. No card required.

AI agents call recent_additions to retrieve information from Not Human Search without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though recent_additions only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

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

See the full Not Human Search policy for all 11 tools.

Get this rule live on your own Not Human Search server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY NOT HUMAN SEARCH →

View all 11 tools →

These attack patterns abuse exactly the kind of access recent_additions gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so recent_additions only ever does what you allow.

SECURE NOT HUMAN SEARCH →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the recent_additions tool do? +

List agent-ready sites newly added to the Not Human Search index, sorted newest first. Use this to discover what's just landed on the agentic web — new MCP servers, fresh llms.txt adopters, new OpenAPI publishers. Good for weekly agent digests or tracking ecosystem momentum.. It is categorised as a Read tool in the Not Human Search MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on recent_additions? +

Register the Not Human Search MCP server in PolicyLayer and add a rule for recent_additions: 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 Not Human Search. Nothing to install.

What risk level is recent_additions? +

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

Can I rate-limit recent_additions? +

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

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

recent_additions is provided by the Not Human Search MCP server (https://nothumansearch.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Not Human Search tool call.

Deterministic rules across all 11 Not Human Search tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.