Low Risk

search_twitter

search_twitter

How to control search_twitter ↓

What search_twitter does on SocialData MCP Server

AI agents call search_twitter to retrieve information from SocialData 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 search_twitter needs a policy

Twitter search is a standard read operation that queries and retrieves publicly available or account-accessible tweet data without creating, modifying, or deleting any information. While the description is uninformative, the naming convention and sibling tools (all getters/readers) provide sufficient context to classify this as a Read operation with low blast radius.

From the tool's definition Tool name 'search_twitter' combined with context of sibling read-only tools (analyze_tweet_engagement, get_account_balance, get_community_members, get_community_tweets) indicates data retrieval.

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

How to control search_twitter

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

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

search_twitter 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 SocialData 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 search_twitter

What does the search_twitter tool do? +

search_twitter. It is categorised as a Read tool in the SocialData MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_twitter? +

Register the SocialData MCP Server MCP server in PolicyLayer and add a rule for search_twitter: 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 SocialData MCP Server. Nothing to install.

What risk level is search_twitter? +

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

Can I rate-limit search_twitter? +

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

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

search_twitter is provided by the SocialData MCP Server MCP server (thesethrose/socialdata-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every SocialData MCP Server tool call.

Start from SocialData 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.

41 SocialData 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.