AI agents call get_message_context to retrieve information from Tgmcp 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 message context with no side effects. It does not create, modify, delete, or execute operations. The verb 'retrieve' and the passive nature of the operation (reading contextual data) clearly place it in the Read category. Severity is low as misuse would only expose message content the agent can already access, with minimal blast radius.
From the tool's definition Tool name 'get_message_context' and description 'Retrieve context around a specific message' indicate a query operation that fetches existing data without modification.
Attacks that exploit this kind of access
Retrieve context around a specific message. It is categorised as a Read tool in the Tgmcp MCP Server, which means it retrieves data without modifying state.
Register the Tg MCP server in PolicyLayer and add a rule for get_message_context: 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 Tgmcp. Nothing to install.
get_message_context 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_message_context 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_message_context. 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_message_context is provided by the Tg MCP server (oevortex/tgmcp). 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 →