Активные истории конкретного юзера/канала.
AI agents call get_peer_stories to retrieve information from Claudegram without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves active stories from a user or channel, which is a read-only operation. It queries information without creating, modifying, deleting, or executing any state-changing actions. The minimal severity reflects that story data is typically intended to be public or semi-public information on Telegram, though confidence is high given the clear read semantics of the operation.
From the tool's definition Tool name 'get_peer_stories' and description 'Активные истории конкретного юзера/канала' (Active stories of a specific user/channel) indicate retrieval of existing data without modification or side effects.
Attacks that exploit this kind of access
Активные истории конкретного юзера/канала. It is categorised as a Read tool in the Claudegram MCP Server, which means it retrieves data without modifying state.
Register the Claudegram MCP server in PolicyLayer and add a rule for get_peer_stories: 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 Claudegram. Nothing to install.
get_peer_stories 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_peer_stories 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_peer_stories. 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_peer_stories is provided by the Claudegram MCP server (sanjar-x/claudegram). 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 →