MCP servers · by job
Web search MCP servers
121 MCP servers that search the web and scrape pages for an agent. 53 are SAFE, 22 CAUTION and 46 BLOCK. Ranked by trust score; each card opens the full audit.
Cite
Cite this page
ModelsAtlas. “Web search MCP servers”. Retrieved 29 Oct 2026. https://modelsatlas.com/mcp/topic/search/page/5
Verdicts · 121 servers
Transports
- stdio, runs locally94
- Streamable HTTP, remote49
- SSE, legacy remote10
- Not declared9
A server can list more than one transport.
Tool risk
19
servers expose at least one destructive tool: delete, overwrite or run. The median server with a readable tool list exposes 6 tools.
Servers with no destructive tools →121 web search servers
97–120 of 121 · ranked by trust score, then stars
Context Engine
kirachon/context-engine
Local-native Context Engine MCP server for codebase indexing, semantic retrieval, planning, and review workflows.
Deep Research
u14app/deep-research
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
fastCRW
fastcrw/crw
Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use ma
Docpull
raintree-technology/docpull
Local-first Python CLI and MCP server for versioned, cited context from web and document sources.
NeuronDB
neurondb/neurondb
NeuronDB PostgreSQL extension: vector similarity search (HNSW, IVFFlat), embeddings, kNN, ML in SQL, and hybrid full-text + vector retrieval.
Crw
us/crw
Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use ma
Pdf Reader Mcp
sylphlab/pdf-reader-mcp
Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.
Anymd
SylphxAI/anymd
Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.
PDF Reader
sylphxltd/pdf-reader-mcp
Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.
PDF Reader
sylphxai/pdf-reader-mcp
Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.
prax
lodsb/prax
A self-hosted library for the papers and web pages one person reads: hybrid search, a graph whose links cite their sentence, and an MCP interface for agents
harborclerk
r0shi/harborclerk
An MCP server that lets AI agents query your document archive instead of uploading it — with OCR, hybrid search, and cited local-AI answers in a private, Mac-native app.
Synorive
arturoaeriform174/Synorive
Search your files by meaning and fact-check the web, fully offline.
Npcpy
cagostino/npcpy
The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.
Npcpy
npc-worldwide/npcpy
The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.
npcpy
NPC-Worldwide/npcpy
The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.
Canonry <img src="https://raw.githubusercontent.com/Canonry/
Canonry/canonry
Agent-first AI SEO (AEO/GEO) operating platform
RE-call
GiulioDER/RE-call
Memory that abstains instead of guessing: agent memory on your own Postgres with a verdict, confidence and provenance on every hit, and a calibrated refusal when nothing clears the threshold.
engram
aiconnai/engram
MCP memory server for Claude Code, Cursor and AI agents - Rust local-first AI memory with hybrid search, SQLite, knowledge graph and Python/TypeScript SDKs
Fortemi
fortemi/fortemi
Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal ingestion (vision, audio transcription, speaker diarization), and knowledge graph. Rust + PostgreSQL.
crawlforge-mcp
mysleekdesigns/crawlforge-mcp
31 MCP tools that give Claude, Cursor and any MCP client the live web — scrape, crawl, search, real Google rank, change tracking, document parsing, plus an autonomous agent that researches from a plain-English prompt with no URLs. Clean Markdown and schema-validated JSON, not raw HTML. Local-Ollama
ApiTap
n1byn1kt/apitap
CLI, MCP server, and npm library that turns any website into an API — no docs, no SDK, no browser.
memory-cloud
kagura-ai/memory-cloud
Adaptive memory for AI agents & teams — beyond RAG. Self-hosted MCP server that gets smarter every time you search: hybrid search + a neural memory graph that learns. Works with Claude, ChatGPT & any MCP client.
video-research-mcp
Galbaz1/video-research-mcp
MCP tools and Claude Code workflows for video analysis, cited research, document extraction, knowledge storage, and optional explainer video production.
Other jobs
By risk
Questions
How do you decide which servers are web search servers?
Which web search MCP servers rank highest on trust?
How many web search servers only read?
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- How do you decide which servers are web search servers?
- Which web search MCP servers rank highest on trust?
- How many web search servers only read?