Cursor Conversations
MCP server by Vlad Tansky that provides AI assistants with direct access to Cursor's local conversation database for analyzing coding patterns and generating personalized development insights. The implementation reads SQLite conversation data directly from Cursor's storage, offering tools for conversation retrieval, search, analytics, and relationship discovery across chat history, with support for both legacy and modern Cursor database formats. Built with TypeScript using better-sqlite3 for database access, it includes conversation parsing, code block extraction, file relationship mapping, and export capabilities in multiple formats, serving developers who want to analyze their actual coding conversations to extract personalized coding rules, identify recurring development patterns, and generate context-aware assistance based on their real project history and problem-solving sessions.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Cursor Conversations from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.