ai-history
Click on "Install 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., "@ai-historysearch my past AI chat sessions for the Docker setup discussion"
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 History Ingester Daemon & MCP Server
A cross-platform service and Model Context Protocol (MCP) server that watches, ingests, indexes, and searches past chat sessions, agent actions, implementation plans, and artifacts from local AI coding tools (Antigravity IDE, Antigravity CLI, Claude Code, Windsurf, OpenCode, Codex, ChatGPT/Claude exports).
Architecture & Features
Local Disk Recovery (
antigravity-localtool):Zero-dependency on external databases. Directly scans and inspects local Antigravity brain sessions (
~/.gemini/antigravity-ide/brainand~/.gemini/antigravity/brain).Supports
list,search,get,recover, andartifactsactions.Summarizes file names, sizes, creation, and modification timestamps for artifacts before returning specific file content.
Vector Database Integration (Qdrant):
Indexes session transcripts, prompt steps, and agent tool executions into a Qdrant vector database (
ai_history).Provides full-text and semantic search across past sessions and tool executions.
Continuous Background Watcher Daemon:
Incremental ingestion watching
brain/directories, keeping track of file read offsets in~/.ai-history-ingest-offsets.json.
Lightweight Web Viewer:
Optional browser UI on port
3333to inspect conversations and tool history.
Related MCP server: callimachus
MCP Configuration
Add the server to your MCP configuration (e.g. ~/.gemini/antigravity-ide/mcp_config.json, ~/.gemini/config/mcp_config.json, or Claude Desktop config):
{
"mcpServers": {
"ai-history": {
"command": "node",
"args": [
"/path/to/ai-history-mcp/dist/mcp/server.js"
],
"env": {
"QDRANT_URL": "http://192.168.2.11:6333",
"COLLECTION_NAME": "ai_history"
}
}
}
}Available MCP Tools
Tool | Purpose | Key Parameters |
| Direct local filesystem access to Antigravity sessions, transcripts, and artifacts (bypasses Qdrant). |
|
| Search chats stored in Qdrant vector database. |
|
| Search past agent tool invocations (bash, file edits, etc.) in Qdrant. |
|
| View Qdrant points count, indexed vectors, health status, and local storage stats. | (none) |
Running the Ingestion Daemon
Build
npm install
npm run buildManual / Development
npm run daemon
# or live-reloading:
npm run dev:daemonLinux (Systemd User Service)
mkdir -p ~/.config/systemd/user/
cp ai-history-daemon.service ~/.config/systemd/user/
systemctl --user daemon-reload
systemctl --user enable --now ai-history-daemon.serviceLicense
Released into the public domain under the Unlicense.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Persistent memory for AI agents. Search, store, and recall across sessions.
Shared memory for coding agents. Stop re-explaining your codebase every session.
Securely search and manage workspace context files for AI agents and teams.
Universal persistent memory and knowledge retrieval layer for AI agents and LLMs.
11
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceIndexes and searches agent conversation logs from Antigravity and Cursor workspaces, enabling semantic search, token analysis, and benchmarking over local SQLite storage.19MIT
- AlicenseAqualityAmaintenanceLocal index and hybrid search (SQLite FTS5 + on-device vector KNN) over your AI coding-agent conversation history across 11 tools (Claude Code, Codex, Cursor, and more). Exposes search_threads, search_current_project, recent_threads, get_thread, list_tags, and list_open_todos so any agent can recall its own past work.2237AGPL 3.0
- AlicenseAqualityAmaintenanceProvides persistent, searchable memory across AI coding agent and chat history (Claude Code, Codex, Gemini CLI, ChatGPT, and more) via retrieval-augmented generation, enabling semantic and hybrid search to retain context across sessions.55MIT
- AlicenseNot gradedqualityCmaintenanceEnables semantic search over local AI-agent session logs (e.g., Claude Code, Hermes) using local embeddings, returning relevant chunks without exposing full transcripts.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Bluscream/ai-history-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server