{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_mqc695rgv6n5","handle":"source-mcp","url":"https://wellknown.network/agents/source-mcp","links":{"self":"https://wellknown.network/agents/source-mcp/record.json","html":"https://wellknown.network/agents/source-mcp","markdown":"https://wellknown.network/agents/source-mcp/record.md","api":"https://wellknown.network/api/v1/agents/source-mcp","status":"https://wellknown.network/api/v1/agents/source-mcp/status","claim":"https://wellknown.network/agents/source-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/source-mcp/claim.json","badge":"https://wellknown.network/agents/source-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:source-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"source-mcp","summary":"A Model Context Protocol (MCP) server for semantic search and Retrieval-Augmented Generation (RAG) over local codebases and documents.","description":"<div align=\"center\">\n  <h1>🔍 Source-MCP</h1>\n  <p><strong>A Model Context Protocol (MCP) server for semantic search and Retrieval-Augmented Generation (RAG) over local codebases and documents.</strong></p>\n</div>\n\n---\n\n## 📖 Overview\n\n**Source-MCP** leverages the [Model Context Protocol](https://modelcontextprotocol.io) to provide AI assistants (like Claude, Gemini, and others) with direct access to local files through semantic search.\n\nInstead of manually copy-pasting code or documentation into your prompts, Source-MCP automatically indexes your local repository, generates vector embeddings, and enables the AI to semantically search and retrieve only the most relevant files.\n\n## ✨ Key Features\n\n- **Dual Embedding Support:**\n  - **OpenAI:** Uses robust `text-embedding-3-small` (1536 dimensions) for high-quality enterprise embeddings.\n  - **FastEmbed (Local):** Uses `sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2` (384 dims). Runs entirely locally, no API keys required, and supports multilingual inquiries.\n- **Smart Incremental Indexing:** Uses file fingerprints (modified time + size) to only index new or modified files, ensuring lightning-fast startup times.\n- **Auto-Migration:** Automatically detects embedding dimension changes (e.g., switching from OpenAI to FastEmbed) and safely recreates the vector index.\n- **Web Dashboard (Port 8000):**\n  - **Live Logs:** View real-time indexing and search activity with auto-scroll.\n  - **Reindex Base:** Force-wipe the vector DB and manifest for a completely fresh full scan.\n  - **Reindex Base:** Force-wipe the vector DB and manifest for a completely fresh full scan.\n  - **Search Debugging:** Special endpoint (`/api/search/debug?q=...`) to test raw semantic search scores.\n\n## 🤔 Why local embeddings and `zvec`?\n\nWe use [**zvec**](https://github.com/alibaba/zvec), a lightweight, high-performance vector database maintained by Alibaba. `zvec` is embedded directly into the Python process, eliminating the need to set …","publisher":null,"homepage":null,"repository":null,"version":"0.1.3b5","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:source-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.825,"provenance":"derived"},{"slug":"code.debugging","name":"Debugging","confidence":0.802,"provenance":"derived"},{"slug":"ai.prompting","name":"Prompt Management","confidence":0.791,"provenance":"derived"}],"categories":["ai","code","data","dev"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"source-mcp","registry":"pypi","observedAt":"2026-09-10T12:23:42.850Z","publishedAt":"2026-02-22T22:00:12.430538Z","latestVersion":"0.1.3b5"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"source-mcp","url":"https://pypi.org/project/source-mcp/","firstSeenAt":"2026-09-10T12:23:02.337Z","fetchedAt":"2026-09-10T12:23:02.337Z","normalizedAt":"2026-09-10T12:23:02.337Z"}]},"firstSeenAt":"2026-09-10T12:23:02.337Z","updatedAt":"2026-09-10T12:23:42.850Z"}