Search MCP Servers

Query your product docs from AI tools. Source-cited answers from your indexed documentation.

Fast, intelligent web search and web crawling. New mcp tool: Exa-code is a context tool for coding

Web search for AI agents — one tool across 6 engines, routed to the cheapest + cached.

Live web search and clean-markdown page fetch over the Keenable web index.

Search the web and extract clean, readable text from webpages. Process multiple URLs at once to sp…

Discover available topics and explore up-to-date, topic-tagged web content. Search to surface the…

Pay-per-call agent superpowers: media/video gen, product demos, research, GTM, scraping, compute.

Australian tax knowledge base for agents: 34,500+ ATO documents, cited answers to any tax question.

Tag, rename, and enrich PDFs and images. Free tier: 1,500 tags/month, no credit card.

Apple Developer Documentation with Semantic Search, RAG, and AI reranking for MCP clients

Built-in MCP server for ArcadeDB multi-model database (graph, document, vector, time-series)

Paid remote MCP for agent code search routing MCP, structured receipts, audit logs, and reviewer-rea

A loc_id to its bounding box, centroid, and polygon, with its name and admin level.

Geospatial MCP server for earthquake, tsunami, volcano, disaster, and FX data queries.

Historical FX rates for 100+ currencies vs USD from IMF and World Bank data, 1940-present.

Open manufacturing and maker facility locations for country and facility-type queries.

Global earthquake events from the USGS, 2150 BC-present: magnitude, depth, location, counts.

Global flood events and extent 1985-present from the Dartmouth Flood Observatory and GFD.

Reverse geocode latitude/longitude to loc_id; resolve loc_ids to boundaries, centroids, hierarchy.

Global hurricane and tropical cyclone tracks from IBTrACS/NOAA, 1842-present. Wind and pressure.

Global population estimates from WorldPop, 2000-2030, at country and sub-national levels.

Convert latitude/longitude to the deepest administrative loc_id plus its full parent chain.

US tornado events 1950-present from the NOAA Storm Prediction Center: EF rating, tracks, damage.

Global tsunami events from NOAA NCEI, 2000 BC-present: wave height, runups, and counts.

UN Sustainable Development Goal indicators for all 17 goals, curated by country and year. Free.

Global volcanic eruptions from the Smithsonian Global Volcanism Program: VEI, location, dates.

Wildfire events and aggregates across global, U.S., and Canada sources. Paid via x402 USDC.

CIA World Factbook country indicators: infrastructure, energy, demographics, economy, 2002-2026.

World Bank World Development Indicators: curated country-year economy, health, education and more.

Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.

Semantic code search built for AI agents. Hybrid, AST-aware, context for 166 languages.

A personal RAG database you build from chat, so AI creates work that sounds like you.

Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.

Licensed, rights-cleared content for AI agents - verifiable license keys + EU AI Act attestation.

Your AI discovers and installs MCP servers across Official Registry, Glama, and Smithery.

Free, open MCP server for The Urantia Papers. 197 papers, 14,500+ paragraphs, 4,400+ entities.

Hypothesis-driven problem solving for AI agents: probe, falsify, escalate.

Persistent knowledge system with OWL-RL reasoning and 22 MCP tools. Local-first.

MCP server for Google search results via SERP API

Collaborative, cache-first web search for agents — cited answers from a shared live-web pool.

MCP server for searching Airweave collections with natural language queries.

95 typed Typesense operations for AI agents through an MCP server that is read-only by default.

Streamable-HTTP MCP gateway: web_fetch, web_search, metis_verify (SSRF-hardened).

Search and explore the Holy Qur'an with Arabic text, transliteration, and advanced search support.

Local-first, read-only MCP server for recall over your Gmail: search, contacts, threads, digests.

Web search that doesn't wreck your AI's memory.

Hybrid vector + reasoning retrieval, agent memory, multi-agent orchestration, MCP server, and RAG.

An MCP server that indexes and retrieves Plesk documentation.

Verify factual claims (verdict + citations) and resolve securities to FIGI identity over MCP.

Open-source LLM knowledge base: team chat into a typed knowledge graph and auto-generated wiki.

Zero-trust, air-gapped Enterprise GraphRAG MCP server with offline, citation-grounded answers.

Convert .eml email exports to Markdown with YAML front matter

Evidence-backed web research for AI agents with citations and confidence scores.

Calibre ebook library server: search, read content, curate metadata, semantic search, gated writes.

Calypso multimodal RAG for grounded answers from docs, images, charts, and knowledge.

Personal RAG over your GitHub history (commits, code, reviews), served to Claude Code over MCP.

Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth

Semantic code search and analysis from CodeAlive for AI assistants and agents.

Offline agentic memory: remember/recall/relate/forget/why over a fused vector+graph+columnar engine

Free Google Search with inline citations for any MCP-compatible AI tool.

Agent memory engine — 86 MCP tools, self-hosted, single Rust binary

Read-only semantic search MCP server for Obsidian vaults using local Ollama embeddings.

Self-correcting agent memory + MCP server: recall, supersede/revert/review corrections, erasure.

Session memory, knowledge search, Brave Search, Gemini AI, and code transforms for AI agents

Self-hosted knowledge backend for AI agents with hybrid search and MCP tools

Git-backed org memory for AI agents — hybrid search, tables, files & a URI graph over MCP.

Local-first MCP server: Claude searches, asks & drafts from your Obsidian vault. 21 tools, no keys.

IBM watsonx.ai MCP server for Claude integration

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

Search Obsidian vaults with hybrid full-text, fuzzy, semantic, and graph retrieval.

Local-first AI memory engine — 4-tier memory, people graph, Bayesian beliefs. Encrypted, 62µs.

MCP server for Telegram Archive — search messages, browse chats, and access history

bioRxiv/medRxiv/arXiv preprint full text as structured sections for AI agents + search.

Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling

Search 1,580 certification exam blueprints: domains, scoring, prerequisites, compare. No API key.

Lightning-fast RAG for AI agents. 4-layer fusion, ONNX Runtime, sub-200ms search.

Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.

Keyless multi-engine web search, fetch, and clean-Markdown read for AI agents. No API keys.

Verified Polish open data for AI agents: debt, budget, 460 MPs, votings, judiciary search, RAG.

Generate a ServiceBricks C# .NET microservice as a ZIP file.

Let AI agents watch videos: local transcripts, speakers, scenes, chapters and moment search

Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.

Local-first semantic code search across all your repos. Private context for AI coding assistants.

MCP server for SearXNG — privacy-respecting web search with pagination, URL reading

Semantic search over IMAGIN.studio API documentation — CDN, API, integration guides, and more.

Open-source bitemporal memory layer for LLM agents — knowledge graph with conflict resolution.

Self-hosted memory for AI agents with hybrid search, knowledge graphs, tasks, and document sync.

🔍 Read-only MCP server for secure filesystem exploration, searching, and analysis

Secure filesystem MCP server for reading, writing, searching, diffing, and patching files.

Memory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.

Google Gemini image generation, editing, and local processing via MCP

Google Jobs listings with direct apply links via the Apify Google Jobs Scraper, hosted MCP.

Yandex search results, images, and SERP data via the Apify Yandex Search Scraper, hosted MCP.

Read-only scripture-study engine: complete-or-fail concordance over Greek NT, Hebrew OT, LXX.

Deterministic, token-minimal agent memory: multi-hop [[wikilink]] recall with no LLM in the loop.

Local semantic code search with Git history. Works offline, no API key needed.

Web search, content extraction, PDF parsing, plus datetime and geolocation tools. No API keys.

Discover and recommend retriever MCP servers. Includes top picks and install config tools.

Multi-provider search broker for AI agents: 14 providers, 12-step extraction, retrieval workflows.

Capture the web, keep your copy as plain Markdown, and recall it by meaning. Local-first daemon.

Local semantic search over your Obsidian vault - always fresh, never reindex.

German federal & state legal texts (BGB, DSGVO, …) with canonical IDs and cite-grade provenance.

Local-first personal knowledge base. Cited answers from your vault via vector + graph retrieval.

Local-first web intelligence MCP server for AI coding agents

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

Clean raw HTML into LLM-ready text before agents spend tokens.

Persistent memory MCP server. 29 tools, BM25+MMR+OOD retrieval, CFR-21 audit, code graph.

Verifiable provenance for AI agents — ZK proofs over confidential documents, no plaintext exposure.

Traceable Chinese-history MCP: 4 cited tools over 9 classical texts (pre-Qin to Wei-Jin).

100% local MCP server for semantic code search: AST chunking, hybrid retrieval, code knowledge graph

Local code-memory graph for AI coding agents.

Fast local full-text search for Windows files (tantivy + jieba), exposed to AI agents over MCP.

Local-first MCP tools for searching and drafting from your X/Twitter archive.

Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.

Federated research discovery with S-Index metrics across a network of digital twins.

Local Work Model MCP server for agent work that learns from real outcomes.

Local-first multilingual memory for Codex, Claude Code, and MCP clients using Qdrant and Ollama.

Curated knowledge for AI agents — 19K chunks, 121 skills, semantic search via MCP

Curated knowledge API for AI agents - skill packs, semantic search, validated patterns.

melis x402 Tools — 22 pay-per-call APIs for AI agents. No accounts, no API keys. USDC on Base.

MCP server for jPOS and ISO 8583. Deterministic payment protocol tools for AI agents.

Fully local MCP server and CLI for web research

Extract YouTube transcripts for AI agents. Clean text or timestamped segments.

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

Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.

AI-powered code indexer with semantic search and knowledge graphs

MCP server for web search, content extraction, academic research, and library docs.

Read-only MCP server for GCP Cloud Storage: list objects in a bucket.

Read-only MCP server for OneDrive: list files/folders via Microsoft Graph API.

Read-only MCP server for PostgreSQL: list schemas/tables, run guarded queries.

MCP server for RabbitMQ: publish messages, poll one message from a queue.

Read-only MCP server for S3-compatible storage: list buckets and objects.

Read-only MCP server for SharePoint: list, browse, and inspect files/folders.

PDF-to-Markdown router. Per-page backend selection + confidence scoring for RAG ingestion.

MCP RAG: index PDFs, repos, YouTube, Discord, text; optional YouTube vision; query with citations.

Zero-config MCP server for searchable documentation. SQLite or PostgreSQL.

Check whether an AI answer is grounded in its context — deterministic, no LLM judge.

Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.

One API key, dozens of capabilities for your AI agent. Zero provider auth.

Markdown MCP — search, extract sections, list headings, find code blocks.

Local-first persistent memory for AI coding agents.

Long-term memory for AI agents — your Obsidian vault as searchable persistent memory.

Gmail Postmaster Tools v2 — domains, traffic metrics, and compliance via your own Google OAuth.

Security-hardened NotebookLM MCP with post-quantum encryption

Memory layer for AI coding assistants. Indexes git history + code, exposes via MCP.

Web search for AI agents — 5 tools: search, news, images, scrape, research. x402/USDC or API key.

Brave Search MCP — independent web index (no Google/Bing dependency)

Tavily MCP — wraps the Tavily API (tavily.com)

Verified, citable German & EU law for any LLM. Daily updates from official sources, hosted in DE.

Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.

Markdown vault MCP server with FTS5 + semantic search and frontmatter indexing

Read any web page as clean, ad-stripped Markdown past robots.txt and bot blocks, plus web search.

Sync public web sources into cited context packs for AI agents, RAG, and MCP clients.

Token-efficient MCP memory for Markdown vaults. Tiered search, GraphRAG, AI memories.

Persistent AI memory with entity resolution, temporal knowledge graph & 11 MCP tools.

MCP server giving AI agents persistent task memory across TickTick, Notion, GitHub, Linear & Beads

Causal graph memory engine for AI agents with scoring, activation, and forgetting

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

Self-curating agent memory kept honest by survival-based selection over measured outcomes.

Agentic memory for cyber threat intelligence. STIX graphs, actor aliasing, offline RAG, Sigma/YARA.

The open retrieval layer for AI agents — index code, docs, data. Search via MCP.

Git-backed markdown memory for AI agents; search hides superseded and archived notes.

Local-first, persistent memory for AI coding agents — remember, recall, forget, and list, over MCP.

A semantic search engine for files and code.

Save tokens while coding — your AI agent gets structured code context, not file dumps.

Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.

Submit URLs for instant indexing via IndexNow and Google Indexing API.

Easy-to-setup local RAG server with minimal configuration

Local read-only semantic search for Markdown vaults through MCP.

MCP server for integrating Omnisearch with LLMs

Podcast transcripts as clean Markdown with real speaker names — via the Spoken API.

Temporal knowledge graph of your codebase (Graphiti + Neo4j), served to AI agents via MCP.

AI memory buyer routing with Forge docs, pricing, paid recommendations, and MCP discovery.

Local-first MCP code intelligence: 37 tools — hybrid search, blast-radius, diff review, memory.

Evidence-first PDF MCP. Agent Document Twin with citeable page+bbox evidence.

Long-term and multimodal memory for AI agents - character-aware, mem0-compatible, fully-local option

Free web search for AI agents — multi-engine parallel search, smart ranking, no sign-up, no limits

Deterministic ebook-to-markdown pipeline with MCP tools to browse, search, and read your books.

SQL Server MCP with RAG capabilities for Windows (native ODBC support)

SQL Server MCP with RAG capabilities for macOS (Docker SQL Server support)

Local research agent that verifies its own answers. Runs on Gemma 3 4B + Ollama, $0/query.

Vault-native, accountable memory for Claude Code and MCP clients. Markdown is ground truth.

Self-hosted, source-traceable memory layer and MCP server for AI agents, on your own Postgres.

Multi-engine search for AI agents. Trust scoring, local corpus, MCP-native. Self-hostable, BYOK.

MCP server for Thomson MO5 C development, 6809, CMOC, SDK, toolchain.

Serves coding agents one canonical doc per query instead of rereading the repo — ~60% fewer tokens.

95 typed Typesense operations for AI agents through an MCP server that is read-only by default.

Local-first AI memory with knowledge graphs and hybrid search. 17+ AI tools via MCP. Free.

Typed record store + hybrid search over MCP: deterministic lookups + semantic memory, per-customer.

MCP web search + tiered web fetch for AI agents (Exa, Firecrawl), SSRF-guarded, cross-platform.

Provenance-aware memory for AI agents: quarantine, abstention gate, supersession-with-history.

Graph-vector memory for AI assistants using FalkorDB and Qdrant

MCP Server for VictoriaMetrics. Provides integration with VictoriaMetrics API and documentation

MCP Server for VictoriaMetrics. Provides integration with VictoriaMetrics API and documentation

Local-first semantic memory for MCP agents. Recall, remember, forget, echo, drift, stats over stdio.

One shared, durable memory for your AI coding agents — local-first, zero-dependency.

Local-first, source-traceable agent memory — no LLM at ingest, fully offline

Semantic code retrieval engine with hybrid search, context expansion, and 40+ language support.

Code intelligence MCP server for 17+ programming languages.

Research workspace for Zotero + Obsidian + NotebookLM. Search, ingest, sync, verify briefs.

Web search that doesn't wreck your AI's memory.

Web search that doesn't wreck your AI's memory.

Federated local-first search across transcripts, files, KG, vectors, web and YouTube for AI agents.

Local-first memory engine for AI-agent teams: team/project ACL, recall, and federated sync.

Compressed Knowledge Graphs over MCP — 97 domains, 4× F1 vs RAG at 11× fewer tokens.

Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token.

Read-only MCP server for the OrchestKit docs: full-text search + Markdown fetch. No auth.

Your AI research assistant that cites real sources and stays honest

Local-first productivity: email, calendar, messaging, search, image gen. 49 tools. BYOK.

MemoryOracle - 10 agent memory tools: vector store, recall, summarization, redaction.