Low Risk

searchRecentTweets

Search recent tweets (last 7 days) on X/Twitter. Supports operators like from:user, #hashtag, $cashtag, -is:retweet, has:media, lang:en, etc. Useful for finding discussions about tokens, projects, trends, and people.

How to control searchRecentTweets ↓

What searchRecentTweets does on Agentek Eth

AI agents call searchRecentTweets to retrieve information from Agentek Eth without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why searchRecentTweets needs a policy

This tool queries public Twitter/X data without modifying, deleting, or executing any operations. It retrieves information about discussions, trends, and sentiment. The blast radius of misuse is minimal—an AI agent could only retrieve public tweets, which poses no direct risk to systems or financial assets. Classification as Read is appropriate.

From the tool's definition Tool description explicitly states 'Search recent tweets' which is a retrieval operation. The listed operators (from:user, #hashtag, $cashtag, etc.) are all query filters for finding and retrieving existing public data.

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

How to control searchRecentTweets

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

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

searchRecentTweets 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 Agentek Eth — 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 searchRecentTweets

What does the searchRecentTweets tool do? +

Search recent tweets (last 7 days) on X/Twitter. Supports operators like from:user, #hashtag, $cashtag, -is:retweet, has:media, lang:en, etc. Useful for finding discussions about tokens, projects, trends, and people. It is categorised as a Read tool in the Agentek Eth MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on searchRecentTweets? +

Register the Agentek Eth MCP server in PolicyLayer and add a rule for searchRecentTweets: 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 Agentek Eth. Nothing to install.

What risk level is searchRecentTweets? +

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

Can I rate-limit searchRecentTweets? +

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

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

searchRecentTweets is provided by the Agentek Eth MCP server (nanidao/agentek). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Agentek Eth tool call.

Start from Agentek Eth, 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.

165 Agentek Eth 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.