AI agents call get_tweets to retrieve information from Mcp Twitter without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and searches Twitter data based on user-provided queries. It performs no data modification, deletion, code execution, or financial operations. The only potential risk is information disclosure through search results, which is inherent to read operations and represents minimal risk in a social media context.
From the tool's definition Tool name 'get_tweets' and description 'Search twitter with a query' indicate data retrieval without modification. The query results are sorted by 'Top' or 'Latest', confirming read-only operation.
Documented attack patterns abuse exactly the kind of access get_tweets gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Twitter, and nothing reaches the server without passing your rules. This is the rule we recommend for get_tweets:
{
"version": "1",
"default": "deny",
"tools": {
"get_tweets": {}
}
}get_tweets is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search twitter with a query. Sort by 'Top' or 'Latest'. It is categorised as a Read tool in the Mcp Twitter MCP Server, which means it retrieves data without modifying state.
Register the Mcp Twitter MCP server in PolicyLayer and add a rule for get_tweets: 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 Twitter. Nothing to install.
get_tweets is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_tweets 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.
Set action: deny in the PolicyLayer policy for get_tweets. 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.
get_tweets is provided by the Mcp Twitter MCP server (luniakunal/mcp-twitter). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Twitter, 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.
7 Mcp Twitter tools catalogued and risk-classified — across an index of 43,000+ MCP servers.