Гибрид: компактные text-блоки + ResourceLink на каждое сообщение.
AI agents call get_history_with_links 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 is a Read operation—it queries and retrieves historical messages from Telegram chats. However, severity is elevated to 'medium' rather than 'low' because accessing message history on a personal Telegram account could expose sensitive communications, private conversations, or confidential information if misused by an AI agent without proper authorization checks.
From the tool's definition Tool name 'get_history_with_links' and description indicating it retrieves message history ('компактные text-блоки' = compact text blocks, 'каждое сообщение' = each message) with resource links.
Attacks that exploit this kind of access
Гибрид: компактные text-блоки + ResourceLink на каждое сообщение. 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_history_with_links: 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_history_with_links 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_history_with_links 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_history_with_links. 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_history_with_links 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 →