AI Pensieve MCP

io.github.AS-XSPublished by GitHub account AS-XSv0.2.0Updated Oct 24, 2026

Search and cross-reference local AI chat history with read-only tools and source citations.

VerifiedSTDIODesktop onlyFiles & StorageKnowledge & Memory

Overview

AI-generated overview

Read-only MCP server that lets an assistant search and cross-reference your locally imported AI chat history, with source citations.

What you can do
  • Search a local archive of imported AI conversations by keyword and read the matching threads.
  • Cross-reference discussions of the same topic across different AI providers and compare what was decided.
  • Return source conversations and dates alongside answers so results can be cited.
  • Work only from a local snapshot, so new conversations appear after a re-import or refresh.
When to use it
Useful when you have exported chat histories from several AI providers and want an assistant to recall earlier discussions, trace where a decision was made, or compare answers across tools without uploading the archive to a service.
Requirements
A local Python environment with uv or uvx (or pipx for the desktop app); the MCP server is started with the absolute path to an existing archive.sqlite file. An archive must be imported first, typically through the separate desktop app, which reads exported files or folders. No accounts, API keys or environment variables are declared.
Before you install
Retrieved excerpts may be sent to the AI provider connected to your client, so private conversations can leave your machine that way. The archive is a snapshot and must be re-imported to stay current. Imported source files are left unchanged. The MCP tools are described as read-only, but the desktop import step writes to the local archive.

Installation

In SourceWeft

  1. Open AI Pensieve MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

AI Pensieve MCP

中文版：README · 客户端设置 · 用户指南

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:

sh
uvx ai-pensieve

For a persistent command:

sh
pipx install ai-pensievepensieve

To run only the read-only MCP server against an existing archive:

sh
uvx ai-pensieve-mcp /absolute/path/to/archive.sqlite

See the package installation guide for client setup, platform requirements, persistent archive locations, and source installation.

Use the desktop

  1. Open the wooden door and touch the Pensieve.
  2. Choose Import a memory, then select a provider bottle, Unmarked for auto-detection, or Find & import local sessions.
  3. Choose an exported file or folder, inspect the selection, and pour it into the basin. The original files stay unchanged.
  4. 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. Version 0.2.0 adds shelf → Connect to an AI for copyable setup and pensieve --demo to try invented memories in a temporary archive. 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.

Source: README.md at commit 6b0a3ed

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.2.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts