AI Sessions
AI Sessions MCP Server provides unified access to local AI assistant CLI session histories from Claude Code, Gemini CLI, and OpenAI Codex, with partial support for Cursor CLI. Built by yoavf using Go and the MCP SDK, it reads session files stored locally by these tools (~/.claude/projects/, ~/.gemini/tmp/, ~/.codex/sessions/) and exposes them through four tools: listing available tools, browsing recent sessions with filtering by tool and project, searching session content for specific queries, and retrieving full session transcripts with pagination. The implementation handles different storage formats (JSONL for Claude/Codex, JSON for Gemini, SQLite for Cursor) and provides a normalized interface for finding past solutions, reviewing recent work, learning from previous conversations, and resuming interrupted coding sessions across multiple AI CLI tools.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-01.
Scan details: Circle-IR · 2026-09-01 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/yoavf/ai-sessions-mcp
- Author type
- human
- Last scanned
- 2026-09-01
- Updated
- 2026-09-01
Use via MCP
Resolve AI Sessions 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.