AI agents call get_gif_search to retrieve information from Tgmcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data (GIF search results) without creating, modifying, deleting, executing code, or committing financial obligations. The 'search' verb and 'returns a list' pattern are characteristic of Read category operations. Severity is low because querying GIFs poses minimal risk even if misused by an agent.
From the tool's definition Tool description states 'Search for GIFs by query. Returns a list of Telegram document IDs' — a pure search/retrieval operation with no modifications or side effects.
Attacks that exploit this kind of access
Search for GIFs by query. Returns a list of Telegram document IDs (not file paths). It is categorised as a Read tool in the Tgmcp MCP Server, which means it retrieves data without modifying state.
Register the Tg MCP server in PolicyLayer and add a rule for get_gif_search: 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 Tgmcp. Nothing to install.
get_gif_search 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_gif_search 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_gif_search. 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_gif_search is provided by the Tg MCP server (oevortex/tgmcp). 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 →