"Information about backend development or backend systems" matching MCP servers:

A Docker-based local RAG backend that provides advanced document search capabilities using vector, graph, and full-text retrieval via the Model Context Protocol. It supports over 28 file formats and tracks evolving relationships between concepts using a Neo4j-backed graphiti implementation.

A local-first AI backend that combines Model Context Protocol, Retrieval-Augmented Generation, and an agent runtime to answer questions from a private knowledge base.

An MCP server that implements Retrieval-Augmented Generation to efficiently retrieve and process important information from various sources, providing accurate and contextually relevant responses.

MCP server that connects Cursor IDE to Inky backend, enabling users to list and filter personalized coding rules stored in Pinecone.

A self-hosted memory backend for MCP clients, providing tools for storing, searching, updating, and deleting memories with per-user scoping and OIDC support.

Provides MCP tools to upsert and search vector-embedded note chunks, enabling semantic retrieval from a PostgreSQL/pgvector backend.

Provides AI agents with database-like operations over LanceDB with automatic BGE-M3 multilingual embedding generation, enabling semantic search, CRUD operations, and safe schema migrations across structured data.

An MCP-compatible RAG backend using LangGraph and FastAPI, enabling chaining of AI model logic with document context search.

A clean architecture backend API that registers and semantically searches data using vector embeddings, acting as an MCP context provider to connect AI models to external data.

A multi-model platform that integrates RAG (Retrieval-Augmented Generation) with LLMs, supporting OCR via Tesseract and offering both backend API and frontend web interface.

Provides AI assistants with long-term semantic memory capabilities through local vector-based storage. Enables storing, recalling, and managing information across sessions with complete privacy using ChromaDB, with no data ever leaving your machine.

Multi-modal RAG engine for AI assistants. Stores conversation history, conclusions, diffs, error traces, and other development artifacts in LanceDB with vector search, multi-factor scoring, and an LLM-driven consolidation pipeline.

Self-hosted knowledge backend for AI agents. Provides 11 MCP tools for hybrid vector + keyword search, container-isolated knowledge bases, and 4 storage connectors (S3, Azure Blob, MinIO, filesystem). Built with .NET, runs via Docker.

An MCP server that provides AI assistants with access to Multi Theft Auto: San Andreas function documentation through vector similarity search and smart keyword expansion. It enables efficient information retrieval with features like deprecation warnings and SQLite caching for technical documentation.

Provides AI agents with persistent, searchable memory using semantic search, auto-linking, and categorization, with zero-config local setup or production-ready external providers.

An MCP server that retrieves resume/experience evidence relevant to a job description via vector RAG, and tracks fit-analysis results in a configurable tracking store (Notion or SQLite), with tools like match_job, push_to_tracker, and list_applications.

Enables agents to run semantic search across one or more local project directories by automatically maintaining a LAN-local Qdrant index with Ollama embeddings. Indexing, staleness checks, and incremental updates happen transparently, so users can query code by meaning without managing collections, chunks, or hashes.

An MCP server for semantic search and retrieval of indexed Slack messages stored in Qdrant using Cohere reranking via AWS Bedrock. It enables users to search through Slack history, retrieve full message threads, and access channel or user statistics through natural language.

Turns a tools.yaml contract into typed, tenant-guarded vector database tools that agents can use via Python imports or MCP.

Enables asking natural language questions about local videos, using Whisper transcription, ChromaDB vector storage, and Groq for timestamped answers via MCP.