AI agents call get_recent_actions 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 is a read-only operation that queries administrative action logs. It retrieves historical information about admin activities without creating, modifying, deleting, or executing any changes. The blast radius is minimal—misuse would result only in information disclosure of already-recorded admin actions to which the querying user likely has access permissions.
From the tool's definition Tool name 'get_recent_actions' and description 'Get recent admin actions (admin log)' indicate data retrieval with no side effects. This retrieves existing log data without modifying, deleting, or executing operations.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Get recent admin actions (admin log) in a group or channel. 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_recent_actions: 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_recent_actions 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_recent_actions 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_recent_actions. 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_recent_actions 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 →