{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_xn9bvxaxcd29","handle":"kb-mcp-server","url":"https://wellknown.network/agents/kb-mcp-server","links":{"self":"https://wellknown.network/agents/kb-mcp-server/record.json","html":"https://wellknown.network/agents/kb-mcp-server","markdown":"https://wellknown.network/agents/kb-mcp-server/record.md","api":"https://wellknown.network/api/v1/agents/kb-mcp-server","status":"https://wellknown.network/api/v1/agents/kb-mcp-server/status","claim":"https://wellknown.network/agents/kb-mcp-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/kb-mcp-server/claim.json","badge":"https://wellknown.network/agents/kb-mcp-server/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/kb-mcp-server/history","tools":"https://wellknown.network/api/v1/agents/kb-mcp-server/tools"},"ard":{"identifier":"urn:air::server:kb-mcp-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"kb-mcp-server","summary":"A Model Context Protocol (MCP) server implementation for txtai","description":"# Embedding MCP Server\n\nA Model Context Protocol (MCP) server implementation powered by txtai, providing semantic search, knowledge graph capabilities, and AI-driven text processing through a standardized interface.\n\n## The Power of txtai: All-in-one Embeddings Database\n\nThis project leverages [txtai](https://github.com/neuml/txtai), an all-in-one embeddings database for RAG leveraging semantic search, knowledge graph construction, and language model workflows. txtai offers several key advantages:\n\n- **Unified Vector Database**: Combines vector indexes, graph networks, and relational databases in a single platform\n- **Semantic Search**: Find information based on meaning, not just keywords\n- **Knowledge Graph Integration**: Automatically build and query knowledge graphs from your data\n- **Portable Knowledge Bases**: Save entire knowledge bases as compressed archives (.tar.gz) that can be easily shared and loaded\n- **Extensible Pipeline System**: Process text, documents, audio, images, and video through a unified API\n- **Local-first Architecture**: Run everything locally without sending data to external services\n\n## How It Works\n\nThe project contains a knowledge base builder tool and a MCP server. The knowledge base builder tool is a command-line interface for creating and managing knowledge bases. The MCP server provides a standardized interface to access the knowledge base. \n\nIt is not required to use the knowledge base builder tool to build a knowledge base. You can always build a knowledge base using txtai's programming interface by writing a Python script or even using a jupyter notebook. As long as the knowledge base is built using txtai, it can be loaded by the MCP server. Better yet, the knowledge base can be a folder on the file system or an exported .tar.gz file. Just give it to the MCP server and it will load it.\n\n### 1. Build a Knowledge Base with kb_builder\n\nThe `kb_builder` module provides a command-line interface for creating and managing knowledge bas…","publisher":null,"homepage":null,"repository":null,"version":"0.3.1","license":"MIT","protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:kb-mcp-server","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"derived"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":0.836,"provenance":"derived"},{"slug":"data.database","name":"Databases","confidence":0.791,"provenance":"derived"}],"categories":["data","knowledge"],"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":"kb-mcp-server","registry":"pypi","observedAt":"2026-10-28T08:28:02.037Z","publishedAt":"2025-04-25T14:40:51.069649Z","latestVersion":"0.3.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"kb-mcp-server","url":"https://pypi.org/project/kb-mcp-server/","firstSeenAt":"2026-09-09T22:23:09.937Z","fetchedAt":"2026-10-28T08:26:20.026Z","normalizedAt":"2026-10-28T08:26:20.026Z"}]},"firstSeenAt":"2026-09-09T22:23:09.937Z","updatedAt":"2026-10-28T08:28:02.038Z"}