{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_tpyg46vhcqdx","handle":"pgvector-azure-openai-mcp-server","url":"https://wellknown.network/agents/pgvector-azure-openai-mcp-server","links":{"self":"https://wellknown.network/agents/pgvector-azure-openai-mcp-server/record.json","html":"https://wellknown.network/agents/pgvector-azure-openai-mcp-server","markdown":"https://wellknown.network/agents/pgvector-azure-openai-mcp-server/record.md","api":"https://wellknown.network/api/v1/agents/pgvector-azure-openai-mcp-server","status":"https://wellknown.network/api/v1/agents/pgvector-azure-openai-mcp-server/status","claim":"https://wellknown.network/agents/pgvector-azure-openai-mcp-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/pgvector-azure-openai-mcp-server/claim.json","badge":"https://wellknown.network/agents/pgvector-azure-openai-mcp-server/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:pgvector-azure-openai-mcp-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"pgvector-azure-openai-mcp-server","summary":"An MCP server with RAG capabilities using Azure OpenAI embeddings and pgvector for PostgreSQL.","description":"# pgvector Azure OpenAI MCP server\n\nAn MCP server with RAG capabilities using Azure OpenAI embeddings and pgvector for PostgreSQL.\n\nFocuses on Azure OpenAI embeddings.\n\n## Features\n\n- **MCP Compatible**: Fully based on the Model Context Protocol, seamlessly integrating with AI assistants.\n- **Collection Management**: Create, list, rename, and delete vector collections.\n- **Vector Operations**: Add vectors, search for similar content, and process documents in batches.\n- **Embedding Service**: Integrates Azure OpenAI embeddings.\n- **Modern Package Management**: Based on the uv package manager for fast installation and dependency management.\n- **Atomic Operations**: Database transactions ensure atomicity for operations like collection renaming.\n- **Cross-Platform Support**: Compatible with Windows, macOS, and Linux.\n\n## Quick Start\n\n### 1. Installation Methods\n\n**Method 1: Run directly with uvx (Most Recommended)**\n\n```bash\n# No installation required, run directly with uvx in MCP configuration\n# uvx will automatically download and manage packages\n```\n\n**Method 2: Install with uv**\n\n```bash\n# Global tool installation\nuv tool install pgvector-azure-openai-mcp-server\n\n# Or project dependency installation\nuv add pgvector-azure-openai-mcp-server\n```\n\n**Method 3: Install with pip**\n\n```bash\npip install pgvector-azure-openai-mcp-server\n```\n\n### 2. Set up the Database using Docker\n\nUse `docker-compose.yaml` to set up a database with `pgvector` support.\n\nTo install `pgvector` into the database, an `init-db.sql` script must be ran when the PostgreSQL container is first ran. Download this `init-db.sql` script first:\n\n```bash\nwget https://raw.githubusercontent.com/darktohka/pgvector-azure-openai-mcp-server/refs/heads/master/init-db.sql\n```\n\nThen, create the `docker-compose.yaml`:\n\n```yaml\nservices:\n  db:\n    image: pgvector/pgvector:pg18\n    restart: always\n    environment:\n      POSTGRES_DB: mcp_vectors\n      POSTGRES_USER: username\n      POSTGRES_PASSWORD: password\n    ports:\n …","publisher":null,"homepage":null,"repository":null,"version":"1.0.4","license":"MIT","protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:pgvector-azure-openai-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.database","name":"Databases","confidence":1,"provenance":"derived"},{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"derived"},{"slug":"infra.cloud","name":"Cloud Platforms","confidence":1,"provenance":"derived"}],"categories":["data","infra"],"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":"pgvector-azure-openai-mcp-server","registry":"pypi","observedAt":"2026-09-10T09:27:03.584Z","publishedAt":"2025-10-23T13:25:03.068636Z","latestVersion":"1.0.4"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"pgvector-azure-openai-mcp-server","url":"https://pypi.org/project/pgvector-azure-openai-mcp-server/","firstSeenAt":"2026-09-10T09:26:13.991Z","fetchedAt":"2026-09-10T09:26:13.991Z","normalizedAt":"2026-09-10T09:26:13.991Z"}]},"firstSeenAt":"2026-09-10T09:26:13.991Z","updatedAt":"2026-09-10T09:27:03.584Z"}