get_authorizations

Список активных сессий аккаунта (другие устройства/клиенты).

Server Claudegram sanjar-x/claudegram
Category Read
Risk class Low
Parameters 00 required

What get_authorizations does on Claudegram

AI agents call get_authorizations 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.

Why get_authorizations needs a policy

This tool retrieves information about active Telegram sessions/connected devices. While it reads sensitive session metadata that could inform an attacker about account activity and connected endpoints, it performs no destructive or write operations. It is categorized as Read rather than Execute because it simply queries session state without triggering any actions.

From the tool's definition Tool description translates to 'List of active account sessions (other devices/clients)'. The verb 'list' and noun 'sessions' indicate a read-only retrieval operation with no modification or deletion of data.

Questions about get_authorizations

What does the get_authorizations tool do? +

Список активных сессий аккаунта (другие устройства/клиенты). It is categorised as a Read tool in the Claudegram MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_authorizations? +

Register the Claudegram MCP server in PolicyLayer and add a rule for get_authorizations: 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.

What risk level is get_authorizations? +

get_authorizations is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_authorizations? +

Yes. Add a rate_limit block to the get_authorizations 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.

How do I block get_authorizations completely? +

Set action: deny in the PolicyLayer policy for get_authorizations. 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.

What MCP server provides get_authorizations? +

get_authorizations 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.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.