MCP servers · AI, RAG & memory
50 listings on this page, in order of arrival. Each one has its own page with README, repository facts and source links.
- contextweaver ★ 9
MCP gateway: bounded tool shortlists + artifact-backed result firewall. Deterministic, no model. - io.github.dhnpmp-tech/dcp-mcp
Saudi sovereign AI compute: OpenAI-compatible inference, rent GPU pods, manage storage. - io.github.digitamaz/clarvia
AI agent tool discovery and scoring. Search 15,400+ MCP servers, APIs, and CLIs. - kbdb
A searchable second brain for AI agents: ranked keyword and semantic search over your Markdown. - io.github.dioniipereyraa/memex ★ 6
One searchable memory of your Claude.ai chats and Claude Code sessions, served over MCP. - SearchForge ★ 2
Free open-source web search and page reading for LLMs, AI agents, and RAG. - io.github.dl-eigenart/agentshield-mcp
Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents. - io.github.dnotitia/akb ★ 160
Git-backed org memory for AI agents — hybrid search, tables, files & a URI graph over MCP. - io.github.docdyhr/macwhisper-mcp-server ★ 2
MacWhisper transcription for Claude Desktop. Fully local, no cloud, audio stays on your Mac. - io.github.dohertykariann-code/kariops-pulse
Track your brand's visibility in AI search across Claude, ChatGPT, Perplexity, and Gemini. - io.github.dominiclachance/neurakeep ★ 6
Local-first, source-cited memory for AI agents with proposal review, failure memory, and MCP tools. - io.github.donggyun112/keymem ★ 3
Associative key-graph memory for LLM agents — recall by association, not vector similarity. - Mitos ★ 4
Architectural decision memory for LLM-native workflows — markdown for humans, a graph for agents. - io.github.dr12hes/engrm
Shared memory across devices, sessions, and agents for OpenClaw, Claude Code, and Codex. - io.github.drQedwards/pmll-memory-mcp ★ 15
PMLL Memory MCP — persistent KV context memory and Q-promise deduplication. - io.github.droidrun/mobilerun ★ 9,363
Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows. - io.github.dth0108/bies-guardian
Deterministic sealed verdicts on public claims and startup ideas (0-LLM claim-safety guardian). - io.github.dubuqingfeng/gitlab-mcp-server ★ 9
GitLab MCP (Model Context Protocol) server for AI agents - io.github.dumbspacecookie/openeye ★ 2
Procedure verification for AR/XR with memory, visual sessions, and DPO trajectory export. - Lians Agent Memory ★ 10
Bitemporal memory for AI agents with point-in-time recall and tamper-evident audit history. - io.github.ebenezer-isaac/llmconveyors ★ 1
53 tools for LLM Conveyors: job hunting, B2B sales, ATS scoring, resume tools. - Decompose ★ 10
Decompose text into classified semantic units. Authority, risk, attention. No LLM. - agenthold ★ 2
Shared versioned state for multi-agent AI workflows - io.github.egoughnour/massive-context-mcp ★ 1
Handles 10M+ token contexts with chunking, sub-queries, and local Ollama inference. - io.github.eidetic-works/nucleus
Sovereign Agent OS — Persistent Memory, Governance & Compliance for AI Agents. - JProfiler ★ 2
Java profiling with AI agent integration. Profile CPU, memory, JDBC, HTTP and more. - io.github.ejentum/ejentum-mcp ★ 16
Reasoning, code, anti-deception, memory harness MCP tools. Stdio or HTTPS api.ejentum.com/mcp - Memory Fabric ★ 2
File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB. - io.github.elephia/elephia
Git for your AI's context: local-first, deterministic memory over MCP. An elephant never forgets. - ellmos Homebase ★ 1
Local-first LLM orchestration: memory, knowledge, state, routing, swarm, API discovery, plugins. - URL to Clean Markdown for LLMs & RAG
Fetch URLs and return clean Markdown for RAG — nav, ads and boilerplate stripped. - io.github.elyngved/failmodes
MCP server for the Fail Modes taxonomy — a knowledge base of AI system failure modes - nb-mcp-server ★ 1
MCP server wrapping the nb CLI for LLM-friendly note-taking - io.github.eralpozcan/vision-squeezer ★ 2
Cut vision-LLM token costs by snapping images to tile boundaries — Claude, GPT, Gemini, Llama, Qwen - SkillFM LLM Cost Optimizer
LLM cost optimizer for OpenAI, Anthropic, token usage, BYOK, and SkillFM Beacon audits. - io.github.es617/dbgprobe-mcp-server ★ 10
Let AI agents interact with debug probes — connect, flash, read/write memory, and reset. - io.github.evan-moon/memex ★ 3
Local-first second brain with semantic search. Markdown notes indexed by a local ML model. - Preflight
Check if your MCP server is ready to publish on the MCP Registry, Smithery, or npm. - Agentic Commerce Tools
7 free tools: MCP health scans, AI-readiness scores, llms.txt generator, glossary, indexes. - Nuzo Memory ★ 2
Local-first, auditable memory for MCP-compatible AI agents with explicit writes and SQLite storage. - Speech AI - Pronunciation, STT & TTS ★ 2
Pronunciation scoring, speech-to-text, and text-to-speech for language learning - io.github.faulkj/legion ★ 1
MCP-native LLM councils for debates, juries, blind panels, refinement, and custom deliberation. - io.github.felixAnhalt/Figma-Context-MCP ★ 5
LLM-optimized Figma MCP server. - io.github.felixAnhalt/figma-to-code-mcp ★ 5
LLM-optimized Figma MCP server. - Alchemy ★ 1
Serves the Alchemy writing ruleset to any agent, so its prose loses the usual LLM tells. - Agentverse Memory
Graph-native persistent memory for AI agents — 33 MCP tools, zero-LLM writes. - Voice Transcriber MCP Server
MCP server for transcribing Google Chat voice messages using Groq Whisper API - io.github.fieldcure/assiststudio-runner ★ 1
Windows-only headless LLM task automation engine with scheduling via Windows Task Scheduler. - io.github.fieldcure/essentials
Essential MCP server: HTTP, web search, downloads, Wolfram|Alpha, shell, JS, file I/O, memory. - io.github.fieldcure/rag
MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.