MCP server for searching Claude Code conversation history via Agent Genesis
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"agent-genesis-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Agent Genesis MCP Server > MCP server for searching Claude Code conversation history This package provides an MCP (Model Context Protocol) server that enables Claude Code to search through your conversation history using the Agent Genesis API. Current package version: `1.6.0` ## Prerequisites - Python 3.10+ - Agent Genesis API running (via Docker) ## Installation ### From PyPI ```bash pip install agent-genesis-mcp ``` ### From Source ```bash git clone https://github.com/agentgenesis/agent-genesis.git cd agent-genesis/mcp-server pip install -e . ``` ## Configuration Add to your Claude Code configuration: **Linux/macOS:** `~/.claude.json` **Windows:** `%USERPROFILE%\.claude.json` ```json { "mcpServers": { "agent-genesis": { "command": "agent-genesis-mcp", "args": [] } } } ``` Or if installed in a virtual environment: ```json { "mcpServers": { "agent-genesis": { "command": "/path/to/venv/bin/agent-genesis-mcp", "args": [] } } } ``` ## Available Tools ### `search_conversations` Search through your Claude Code conversation history. **Parameters:** - `query` (str): Search query string - `limit` (int, optional): Max results (default: 5, max: 50) - `project` (str, optional): Filter by project name **Example:** ```python search_conversations(query="authentication flow", limit=10, project="my-app") ``` **Returns:** ```json { "success": true, "results": [ { "score": 0.856, "project": "my-app", "timestamp": "2025-01-15T10:30:00Z", "conversation_id": "conv_abc123", "content_snippet": "Implementing authentication...", "full_content_length": 1245 } ], "total_found": 3, "query": "authentication flow" } ``` ### `get_api_stats` Get statistics about the indexed conversation corpus. **Returns:** - Total conversations indexed - Number of unique projects - Index health status ### `check_api_health` Verify that the Agent Genesis API is running and healthy. ### …
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.