- Conduid
- Marketplace
- #retrieval
MCP servers tagged retrieval
144 live MCP servers tagged "retrieval", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with retrieval.
Mneme
Mneme gives an AI agent a local memory where each recalled item names its source and can be rechecked.
Indexa
The local context engine for AI. Summarizes every file, rolls folders up into whole-project context, and serves any AI tool (Claude Code, Cursor, local models) a ranked slice over…
Prbe Knowledge
Self-hosted knowledge engine: ingest your team's tools, hybrid (vector+keyword+graph) retrieval, cited LLM answers.
Ops Incident Core
Collector-first engineering evidence backend for deterministic ingestion, Qdrant retrieval, cited investigation, readiness reports, workflows, evals, and Core MCP. Azure deploymen…
XfeaturesAthenaeum
One authenticated knowledge and retrieval service for AI agents: D1 facts, R2 documents and AI Search behind a single REST, Workers RPC and MCP interface, with per-caller access c…
Tokenpak
Local proxy that puts the right project context in front of the model before it starts working — with a receipt for what was added
Madosho
a headless retrieval backend. Serves traditional RAG via a tool server or OpenAI shim, drive it from agents over MCP, CLI, or skills, run autonomous research subagents, and rate a…
Intently
Intent-first search that finds the right tool from a vague description. Hybrid retrieval over LLM-written cards, LLM rerank with recall safety, MCP server for AI agents, runs on a…
Constellate
Three knowledge planes (embedded, unified, composed) behind one retrieval contract, benchmarked head-to-head on MovieLens ml-25m. Relational, vector, and graph fusion, an MCP cont…
Grounded Context
Grounded, auditable context layer for enterprise agents: a deterministic path for exact facts + Elasticsearch hybrid retrieval for exploration, exposed over MCP. Every answer carr…
Awesome Agent Search
Research and best practices for bringing web search into Codex, Claude Code, OpenClaw, and AI coding agents.
Thalamus
A self-hosted, code-aware brain for coding agents — persistent memory linking why you did something to where it lives in the code, with the instruments to prove it helps.
Coremem
Git-diffable memory for AI agents — six-layer architecture, plain-text source of truth, Obsidian graph projection. MIT.
ANNPACK
Verifiable knowledge artifacts for AI agents — package, search, and prove exactly which source revision produced each retrieval.
Cairn
Repository documentation graph for AI agents
Saihm Adapters
Sovereign, client-side-encrypted memory for AI agents: drop-in adapters for LangChain, LangGraph, LlamaIndex, RAG, CrewAI and AutoGen, with erasure you can prove (GDPR Art. 17).
Pensyve
Universal memory runtime for AI agents. 8-signal retrieval, multimodal memory, spaced-repetition decay, and procedural learning. Rust core with Python, TypeScript, Go SDKs + MCP s…
TheStack-ai/waypath
aware recall via FTS5 and RRF, and governed memory with explicit promote and review gates. Ships Codex and Claude Code host shims and a native MCP server.
Ostk Recall
Local-first cross-corpus retrieval MCP server — model2vec embeddings + LanceDB (Tantivy BM25) + SQLite. One binary; hybrid (dense + BM25) search across markdown, code, and Claude…
Cf
Token-native agent memory retrieval for LLMs, without embedding APIs or vector databases.
renezander030/agentic-task-system
cli`
TheGoatPsy/mneme
native, accountable memory for Claude Code and any MCP client. Markdown is the source of truth, no LLM on the Stop path, redaction before every derived store.
PruneMem
MCP-compatible memory governance for AI agents — with structure, state, and lifecycle.
BrewMe
Reader-first source intelligence and MCP server for YouTube, Bilibili, RSSHub, and RSS, with grounded search, published reader docs, public CLI/TypeScript SDK surfaces, and plugin…
MemoryWiki
Local-first Memory Wiki for AI agents
Writing Context Rtfm
A MCP extension built on top of rtfm-ai that it acts as a gatekeeper by taking the agent's task, queries the underlying RTFM index, filters out background noise, and packs only th…
Kalairos
Durable, private, time-aware memory engine for long-running AI agents
Lira MCP
MCP server over the Liara cloud documentation: hybrid Persian/English retrieval, page reads, deployment config and build-log diagnosis. Corpus ships in the package, so no ingest,…
Vyral
Portable contracts and local-first runtimes for canonical data, retrieval, durable execution, and agent-facing AI.
Grounded Knowledge Engine
Local-first engine that grounds an AI agent's answers in your own Markdown and captures what it learns back into the KB — Node · TypeScript · MCP.
Prompt Refinery
Retrieval-grounded prompt refinement as a Python library, CLI, and MCP server
Vectorless MCP
MCP server for Vectorless — give AI agents access to structure-preserving document retrieval
Code KB
Retrieval & navigation service for a code monorepo + its docs: indexes source and docs into small, locatable "atoms" and answers with a strict cite-or-die policy. Agent-first, MCP…
Skinki
Local-first memory engine for AI agents — on-device, 0 network, embeddable anywhere via a stable C-ABI + MCP. Honest benchmarks, including the parts that failed.
PAL MEM
Context filter + AI SBOM + retrieval engine for agents working against corpora larger than any model's context window. Local-first, markdown-native, MCP-ready. Haiku 4.5 reac…
XfeaturesAthenaeumMCP
Model Context Protocol integration for Xfeatures Athenaeum: connection guide, auth configuration and client examples. The MCP server itself lives in the Athenaeum core repository.
Bruriah
An MCP server that lets an agent consult your knowledge without letting your knowledge instruct the agent. Evidence with provenance, never instructions.
Rag Eval MCP
Touchstone — know if you broke your RAG. An MCP server and CLI that score retrieval quality against a golden set: recall@k, MRR and hit rate, with no LLM calls.
Trie Memory
Experimental MCP memory server pairing a delta-encoded recognition trie with a concept store that binds surface forms across languages via temporal co-occurrence — "bush", "křoví"…
Arbol
Agent-readable memory for markdown notes: enforced schema, validator, BM25 + graph retrieval, MCP server, and an eval that tells you the truth
Kensho
Kensho — independent third-party profile of a public API surface, by API Evangelist. Kensho Technologies is the AI innovation hub of S&P Global, building machine learning and AI s…
Salva
Salva Runtime — self-hosted discovery intelligence runtime (API / MCP / CLI / SDK)
Memoryvault Kit
A personal memory layer for your AI tools. Intelligent authoring (gap detection, self-enriching graph, session-synthesis loop) + measurably good retrieval (94.9% blind Cov@10, sub…
Companybrain
The open-source memory layer for your company. Index everything, recall anything, own all of it.
Agentbuilder
NOVA by Fractics — secure, multi-tenant platform for grounded Hybrid RAG, ecommerce, Shopify, Lal Kitab, and support agents.
Dew Flow Benchmark
Measure any code repository, at any commit, through any retrieval engine — with the sample sizes attached.
Quickcontext
Provide fast local code search, indexing, and retrieval using Rust and Python tools with AI-assisted context and symbol analysis.
RAAAL
Quick demo for regime aware asset allocation based on: https://ora.ox.ac.uk/objects/uuid:1a421d83-a010-484e-83c1-504bc9f1cbbf/files/d7s75dd17x and https://rpc.cfainstitute.org/sit…
ThreadVault
Local-first Codex session archive, native desktop, smart backup, and read-only MCP tool.
Topk
Topk — independent third-party profile of a public API surface, by API Evangelist. TopK is a search engine for accuracy-critical AI applications, delivering hybrid search, multi-v…