Все доступные истории из ленты (по подпискам).
AI agents call get_all_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 or queries stories from a user's feed based on their subscriptions. It performs a read-only operation with no side effects, no code execution, no data modification, and no financial impact. The low severity reflects minimal blast radius if misused—an AI agent could retrieve personal stories, but this is passive observation only.
From the tool's definition Tool name 'get_all_stories' and description 'Все доступные истории из ленты (по подпискам)' (All available stories from feed by subscriptions) indicates retrieval of existing data without modification or deletion.
Attacks that exploit this kind of access
Все доступные истории из ленты (по подпискам). 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_all_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_all_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_all_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_all_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_all_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 →