Глобальный поиск по юзерам/чатам/каналам по имени или @username.
AI agents call search_global 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 and queries information about users, chats, and channels without creating, modifying, deleting, or executing any actions. It is a straightforward read operation similar to a directory lookup or search function. The low severity reflects minimal blast radius—even if misused by an agent, searching for entities causes no harm or state change.
From the tool's definition Tool performs 'Глобальный поиск' (global search) by name or @username across users, chats, and channels. This is a query/search operation with no modification or side effects.
Attacks that exploit this kind of access
Глобальный поиск по юзерам/чатам/каналам по имени или @username. 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 search_global: 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.
search_global 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 search_global 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 search_global. 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.
search_global 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 →