Get conversation and commit context for a specific file. Returns conversations and commits that touched this file, with relevance indicators. Use keywords parameter to filter conversations by topic and get matching excerpts. NOTE: This returns metadata only - use file-reading tools to get actual ...
AI agents call get_file_context to retrieve information from Cursor Conversations MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a query/search tool that retrieves historical metadata about conversations and commits related to a file. It performs read-only access to conversation history and commit metadata. The explicit note that it returns metadata only and does not provide actual file contents confirms it is a retrieval operation with no side effects, no code execution, and no data modification capability.
From the tool's definition Tool description explicitly states 'This returns metadata only' and 'Use file-reading tools to get actual file contents'.
Documented attack patterns abuse exactly the kind of access get_file_context gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cursor Conversations MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_file_context:
{
"version": "1",
"default": "deny",
"tools": {
"get_file_context": {}
}
}get_file_context is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get conversation and commit context for a specific file. Returns conversations and commits that touched this file, with relevance indicators. Use keywords parameter to filter conversations by topic and get matching excerpts. NOTE: This returns metadata only - use file-reading tools to get actual file contents, and get_conversation to see full conversation details. It is categorised as a Read tool in the Cursor Conversations MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Cursor Conversations MCP Server MCP server in PolicyLayer and add a rule for get_file_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 Cursor Conversations MCP Server. Nothing to install.
get_file_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_file_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_file_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_file_context is provided by the Cursor Conversations MCP Server MCP server (vltansky/cursor-chat-history-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Cursor Conversations MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 Cursor Conversations MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.