"Understanding RAG (Retrieval-Augmented Generation or related topics)" matching MCP servers:

An MCP server providing web search, image search, and page scraping tools to LLMs without requiring API keys.

Provides persistent, searchable memory across AI coding agent and chat history (Claude Code, Codex, Gemini CLI, ChatGPT, and more) via retrieval-augmented generation, enabling semantic and hybrid search to retain context across sessions.

AI modifies a function but misses 5 callers that also need updating. crag fixes this — it builds precise call graphs via static analysis, so AI knows exactly what's affected before making changes.

A lightweight RAG (Retrieval-Augmented Generation) system for Claude Code that enables semantic search over local markdown documents via MCP tools, saving tokens and time.

Enables read-only search and retrieval of your email across multiple IMAP accounts through a local notmuch index, served over authenticated HTTP for MCP clients like Claude or Codex.

An MCP server for codebase context that gives AI coding agents structural understanding through symbol graph, semantic search, blast radius, and convention detection tools.

Enables coding agents to coordinate in spaces through direct messages, topics, blackboards, and durable inboxes, exposing bus tools over MCP and RPC while pushing inbox updates over SSE.

Provides AI assistants with persistent graph database memory using Neo4j, enabling task management, relationship understanding, semantic search with embeddings, file indexing, and multi-agent coordination through the Model Context Protocol.

https://gopls-mcp.org/ MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.

A memory, docs, and repo context layer for engineering agents, providing typed persistent memory, RAG document retrieval, and repository-aware tools to recall decisions, runbooks, and operational knowledge across sessions.

Runs a language server and provides tools for communicating with it. Language servers excel at tasks that LLMs often struggle with, such as precisely understanding types, understanding relationships, and providing accurate symbol references.

An MCP server for prompt and RAG evaluation workflows, enabling users to register, create API keys, and run evaluations via Claude Desktop, Cursor, or other MCP clients, with a hosted backend for heavy evaluation work.

Transforms a codebase into a queryable knowledge base for code understanding, impact analysis, ownership lookup, and more via CLI, HTTP API, or MCP.

Fetches documents by URL, DOI, ISBN, PMID or PMCID, and reports a block as a block, never as an empty success.

MCP server for a self-hostable personal planner — exposes memo, todo, calendar event, and cross-resource full-text search tools so Claude, Cursor, or any MCP client can manage your schedule and notes in natural language.

Zabbix MCP server and CLI in one Go binary. 15 task-shaped tools: current problems, host investigation, why an alert did or did not arrive, metrics, maintenance. Zabbix 6.4+.

Baryon connects MCP-compatible AI assistants to Proton Mail through a local bridge, enabling email search, reading, attachment handling, and draft creation while enforcing deliberate permission limits. It runs locally and cannot send, delete, or modify mail.

Local-first Git hosting for AI coding agents. lgh serve turns any directory into an HTTP Git remote (127.0.0.1:9418) with push events, commit-status reporting, smart .gitignore generation, secret/large-file detection, and optional LAN sharing with auth. The MCP server exposes 10 tools covering repo registration, one-command backup (lgh up), server control, and event access.

Turn PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, SQLite or Snowflake into MCP tools and a REST API, with API keys and per-table role-based access.

A wallet for AI agents: test funds, payments, paid APIs and escrow on Aether. Give an AI agent its own wallet on Aether, a proof-of-work chain with post-quantum (ML-DSA-44) signatures. The agent gets an address and testnet funds in one step, then sends and receives AETH or USDC under per-payment and daily limits you set. It can pay for APIs that answer HTTP 402, sell its own, rate the services it

Lets a model use hundreds or thousands of MCP tools without loading them: it puts five tools in front of a large MCP server or gateway, so the model searches for the tool it needs and calls it. Search combines BM25 with a multilingual embedding model that runs inside the proxy.

Agent memory for facts that change. When a user corrects something, Recall replaces the old fact, tells the agent what it replaced, and keeps the old value in a history. Ask what was believed on any date, see every change to a fact, or diff two dates. Runs locally on polign_db, Postgres with pgvector, MongoDB, or Qdrant. Apache 2.0.

Unified MCP server for Gemini media generation --Nano Banana (images), Veo 3.1 (video), TTS, and Lyria 3 (music). Single Go binary, 12 tools, supports Gemini API key and Vertex AI.

Enables AI image generation and editing using Google's Gemini Multimodal Image APIs.

Safe write access for AI agents. Stellar Jay is an append-only business fact store: every change is kept, attributed to the agent that made it, and can be undone. Agents record, correct and retract facts, read entities, and reverse a bad run with undo_changes. Self-host with stellarjay-mcp (Go, AGPL) or connect to the hosted AvianSuite server at https://mcp.aviansuite.com/mcp.

A deterministic symbol oracle over a locally built index of the repository: whether a symbol exists, what a file declares, and what changed structurally since the last snapshot. It also ships a PreToolUse guard that stops an Edit/Write referencing a function, constant or type the repo does not declare, before the write lands rather than after the build fails. No LLM, no API keys, no network, no l

Enables AI agents to store and retrieve self-hosted memories over MCP (stdio or Streamable HTTP) using local embeddings that work fully offline. Writes are redacted before they hit storage and every read is recorded in an exportable, append-only audit log.

Self-hosted webhook relay and tunnel with Noise NK encryption. Inspect requests, replay webhooks, trace AI pipelines, connect/disconnect tunnels — 13 MCP tools. No tokens or passwords needed.

Lets AI agents read what Kubernetes containers were doing right before they were OOMKilled or crashed: Java heap histograms and Go heap profiles taken before the kill, logs of the dead instance, and core dumps matched to the pod. Read-only tools to list captures, read summaries and raw evidence, and see which containers are near their memory limit now.

AI 3D model generation and post-processing MCP server — text/image/multiview-to-3D via Tripo, retopology, format conversion (GLB/FBX/OBJ/STL/USDZ), and stylization. Single Go binary, 10 tools.