AI agents call search_posts to retrieve information from Tgstat without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data from Telegram posts without modifying, deleting, or executing any operations. It is purely a read/search operation with no side effects. All sibling tools (get_channel, get_channel_posts, get_channel_stats, etc.) are similarly read-only analytics queries. Low severity due to minimal blast radius—worst case returns search results without irreversible consequences.
From the tool's definition Tool performs 'full-text search across Telegram posts' with optional filters (source-type, category, language, country, date). No mutation, deletion, or execution of code/commands.
Attacks that exploit this kind of access
Full-text search across Telegram posts, with optional source-type / category / language / country / date filters. It is categorised as a Read tool in the Tgstat MCP Server, which means it retrieves data without modifying state.
Register the Tgstat MCP server in PolicyLayer and add a rule for search_posts: 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 Tgstat. Nothing to install.
search_posts 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 search_posts 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 search_posts. 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.
search_posts is provided by the Tgstat MCP server (theyahia/tgstat-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →