MCP server directory

59888 public MCP servers from the official MCP Registry (26001 from verified domains, 33887 community). Search, filter, copy a setup snippet. Nothing here is installed by cosmic-mcp.

Community listing. Not installed or verified by cosmic-mcp. Check the source before you run anything.

Search servers

Search

Showing 331 to 360 of 376

• pensieve

  io.github.praveen-ilangovan/pensieve

  Manually-triggered, self-organising personal memory for AI agents; SQLite, no vector DB.

  Community pypistdio databasesmemoryvector-search

• pgvector

  io.github.mittalpk/pgvector

  Similarity search, hybrid search, and index management for pgvector-backed PostgreSQL tables

  Community pypistdio searchdatabasesvector-search

• polymnemo

  io.github.PCBZ/polymnemo

  Shared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).

  Community remotestreamable-http memoryvector-search

• prompt-injection-scanner

  io.github.4hmetuyar/prompt-injection-scanner

  Scans RAG content/scraped pages for indirect prompt injection

  Community npmstdio ai-modelsvector-search

• prompt-injection-scanner

  io.github.GuardBee/prompt-injection-scanner

  Scans RAG content/scraped pages for indirect prompt injection

  Community npmstdio ai-modelsvector-search

• psyXe MCP Server

  io.github.bjenkinsgit/psyxe-mcp

  Apple Notes, Reminders, and Contacts for AI assistants. BERT semantic search. macOS.

  Community vector-searchmemorysearch

• qai-consultant-mcp

  io.github.gvasile29/qai-consultant-mcp

  Keyless local MCP server for QA: standards retrieval, effort estimation, doc review, test analysis.

  Community pypistdio testingvector-search

• quillrag

  io.github.Ayush-yadav11/quillrag

  Single-binary local RAG MCP server in Rust. MiniLM compiled in, hybrid search, zero deps.

  Community searchvector-search

• rag

  io.github.fieldcure/rag

  MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.

  Community vector-searchcustomer-supportsearch

• rag-knowledge-graph-mcp

  io.github.CSOAI-ORG/rag-knowledge-graph-mcp

  Rag Knowledge Graph MCP Server by MEOK AI Labs

  Community pypistdio memoryvector-search

• rag-knowledge-mcp

  io.github.CSOAI-ORG/rag-knowledge-mcp

  Rag Knowledge MCP Server by MEOK AI Labs

  Community pypistdio vector-search

• rag-mcp

  io.github.jaimenbell/rag-mcp

  Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.

  Community pypistdio vector-searchsearch

• rag-vault

  io.github.RobThePCGuy/rag-vault

  Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup

  Community npmstdio customer-supportsearchvector-search

• ragalgo

  io.github.kokogo100/ragalgo

  Dynamic RAG Engine preventing AI hallucinations in Korean Finance and Crypto markets.

  Community npmstdio cryptofinancevector-search

• ragdrift-mcp

  io.github.MukundaKatta/ragdrift-mcp

  Diagnose RAG drift: interpret scores, recommend thresholds, explain dimensions.

  Community npmstdio vector-search

• ragmetric-mcp

  io.github.MukundaKatta/ragmetric-mcp

  RAG retrieval IR metrics: recall@k, hit@k, MRR, NDCG@k, evaluate_batch.

  Community npmstdio vector-searchdata-analyticsmemory

• ragnarok

  io.github.freyr/ragnarok

  Local RAG search over Obsidian vaults: SQLite hybrid search with local Ollama embeddings.

  Community pypistdio searchvector-searchai-models

• redm-mcp

  io.github.Cmoen11/redm-mcp

  RedM / RDR3 docs MCP server: native lookups, semantic search, VORP, RSGCore, oxmysql.

  Community remotestreamable-http vector-searchsearch

• reftrixmcp

  io.github.TKMD/reftrixmcp

  Web design analysis with 26 MCP tools: layout, motion, quality, semantic search via pgvector

  Community npmstdio vector-searchdesignsearch

• repofind

  io.github.CloudCorpRecords/repofind

  Local codebase search for agents: hybrid keyword/semantic search, locate, expand, related code.

  Community npmstdio searchvector-search

• retriEVAL

  io.github.hcarrillo001/retrieval-mcp

  LLM evals as MCP tools: score outputs for faithfulness, relevancy, and hallucination.

  Community ocistdio ai-modelsvector-search

• scicompute

  io.github.CloudCorpRecords/scicompute

  Scientific computation: named tensors, matrix algebra and vector operations, fully local.

  Community npmstdio communicationsciencevector-search

• seam-runtime

  io.github.BlackhatShiftey/seam-runtime

  SEAM: local-first memory runtime for AI agents, with retrieval and glassbox provenance over MCP.

  Community pypistdio memoryvector-search

• searchpin

  io.github.telly6/searchpin

  Self-hosted web search for AI agents — zero API keys, embedding rerank, multi engine parallel search

  Community pypistdio searchapi-integrationvector-search

• shodh-memory

  io.github.varun29ankuS/shodh-memory

  Cognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs.

  Community npmstdio memoryvector-searcheducation

• skeletongraph

  io.github.yashdoke7/skeletongraph

  Zero-LLM structural code retrieval for AI coding agents, served over MCP.

  Community pypistdio vector-search

• slimdex-mcp

  io.github.Siddhukaushik/slimdex-mcp

  Narrow code retrieval for agents: outlines, symbol context, dep graph, persistent memory.

  Community npmstdio memoryvector-search

• smart-connections

  io.github.gogogadgetbytes/smart-connections

  MCP server for Obsidian Smart Connections. Semantic search using your vault's embeddings.

  Community npmstdio vector-searchproductivitysearch

• smart-connections-mcp

  io.github.msdanyg/smart-connections-mcp

  Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private.

  Community npmstdio vector-searchproductivitysearch

• socraticode

  io.github.giancarloerra/socraticode

  MCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.

  Community npmstdio vector-searchsearch

Source: the official MCP Registry (registry.modelcontextprotocol.io), refreshed daily, plus public GitHub data. "Verified domain" means the publisher proved the namespace's domain to the registry; it is not a review. Machine-readable: /v1/directory/servers.