A
licenseNot graded
qualityB
maintenanceEnables semantic search across conversation archives via MCP, allowing AI clients to retrieve relevant past conversations using vector embeddings and text fallback.
3 npm
4
ISC
io.github.AS-XS/ai-pensieve-mcp
by AS-XS
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@io.github.AS-XS/ai-pensieve-mcpSearch my archive for discussions about machine learning and show sources."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AI Pensieve MCP
Search your imported AI conversations locally, either through the illustrated desktop room or from an MCP client.
Privacy: the archive stays on your computer and MCP tools are read-only. Retrieved excerpts may be sent to the AI provider connected to your client. How your data is handled
Install
Open the desktop with uv:
uvx ai-pensieveFor a persistent command:
pipx install ai-pensieve
pensieveTo run only the read-only MCP server against an existing archive:
uvx ai-pensieve-mcp /absolute/path/to/archive.sqliteSee the package installation guide for client setup, platform requirements, persistent archive locations, and source installation.
Related MCP server: ThreadShelf MCP Server
Use the desktop
Open the wooden door and touch the Pensieve.
Choose Import a memory, then select a provider bottle, Unmarked for auto-detection, or Find & import local sessions.
Choose an exported file or folder, inspect the selection, and pour it into the basin. The original files stay unchanged.
Choose Search the waters, search by keyword, and open a smoke result to read the original thread.
The GUI imports ChatGPT, Claude, Gemini, DeepSeek, Grok, and supported coding sessions. NotebookLM currently provides notebook metadata only. See the full compatibility matrix and export guide.
Connect an AI client
Import an archive first, then follow AI client setup and check the client verification status. Try prompts such as:
Search my archive for discussions about machine learning. Show the source conversations and dates supporting your answer.
Find discussions of my project across different AI providers and compare the decisions recorded in them.
More example prompts and tool details.
The archive is a local snapshot: import or refresh again when new conversations should appear. For command-line imports, custom source folders, and revision and deduplication rules, see the user guide.
Licensed under Apache License 2.0.
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues
Related MCP Connectors
Search your AI chat history (ChatGPT, Claude, Codex) from any MCP client. Remote, private, read-only
Search your newsletter and YouTube archive, drafted actions and working context from any MCP client.
Read-only MCP access to authorized Vocci sessions, notes, files, and memory search.
- EngramOAuthapp.getengram
Persistent, verbatim, searchable memory for AI assistants — one memory across every MCP client.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceEnables semantic search and retrieval of archived AI conversations from multiple providers via the MCP protocol, allowing thread continuation and integration with MCP-capable tools.5MIT
- AlicenseNot gradedqualityCmaintenanceEnables LibreChat AI agents to search indexed message history and conversations via MCP tools, with user-scoped access and optional admin search, augmenting memory while reducing context loss.MIT
- FlicenseNot gradedqualityBmaintenanceEnables AI clients to read and search macOS Messages history through a read-only MCP interface.-