get_chat
AI agents call get_chat to retrieve information from Cursor Chats Bridge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves chat data from Cursor's local database with no side effects, modification, or destructive capability. The server is explicitly documented as read-only. Although the tool description is empty, the name, server purpose, and sibling tools leave no ambiguity about its function.
From the tool's definition Tool name `get_chat` and context establish this as part of a "Read-only bridge" that "Exposes Cursor's local chat database". Sibling tools like `get_active_chat`, `list_chats`, and `search_chats` confirm this is a retrieval operation.
Attacks that exploit this kind of access
get_chat. It is categorised as a Read tool in the Cursor Chats Bridge MCP Server, which means it retrieves data without modifying state.
Register the Cursor Chats Bridge MCP server in PolicyLayer and add a rule for get_chat: 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 Cursor Chats Bridge. Nothing to install.
get_chat 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_chat 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_chat. 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_chat is provided by the Cursor Chats Bridge MCP server (jherard-fr/cursor-chats-bridge). 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 →