Get all conversations from a specific workspace
AI agents call get_workspace_conversations to retrieve information from Cursor DB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves conversation data from a workspace without modifying, deleting, or executing anything. It is a straightforward read operation. Severity is medium because conversation history may contain sensitive information (code, API keys, personal data discussed in IDE sessions), making unauthorized access a concern for data confidentiality, though the tool itself performs no destructive or executable action.
From the tool's definition Tool name is 'get_workspace_conversations' and description states 'Get all conversations from a specific workspace' — a retrieval operation with no modification.
Attacks that exploit this kind of access
Get all conversations from a specific workspace. It is categorised as a Read tool in the Cursor DB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Cursor DB MCP Server MCP server in PolicyLayer and add a rule for get_workspace_conversations: 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 DB MCP Server. Nothing to install.
get_workspace_conversations 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_workspace_conversations 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_workspace_conversations. 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_workspace_conversations is provided by the Cursor DB MCP Server MCP server (taylorchen/cursor-db-mcp). 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 →