Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
MCPSafari
MCP serversMCPSafari: Native Safari MCP Server for AI Agents
git clone https://github.com/Epistates/MCPSafari.git -
wet
MCP serversOpen-source MCP server for AI agents: web search, content extraction, and library docs -- 5-strategy scraping, runs without API keys.
git clone https://github.com/n24q02m/wet.git -
hyperresearch
MCP serversConvert Claude Code or Codex into the most intelligent Deep Research Agent. Collect, search, and synthesize web research into a persistent, searchable wiki that builds on itself. Hosted API + MCP: hyperresearch.ai
git clone https://github.com/jordan-gibbs/hyperresearch.git -
camofox-mcp
MCP serversAnti-detection browser MCP server for AI agents — navigate, interact, and automate the web without getting blocked
git clone https://github.com/redf0x1/camofox-mcp.git -
Agent Web Search
MCP serversProvider-neutral web_search for AI agents. Grounding + agent search APIs, keyless defaults.
agent-web-search-mcp@0.8.2 -
MegaMemory
MCP serversPersistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer.
git clone https://github.com/0xK3vin/MegaMemory.git -
open-browser-use
MCP servers🔮 Platform-neutral Browser Use for AI agents: real Chrome automation with a CLI + SDKs, no lock-in, dead simple.
git clone https://github.com/iFurySt/open-browser-use.git -
olostep-mcp-server
MCP serversMCP server for Olostep — the web scraping, crawling, and search infrastructure used by top AI companies. Gives any MCP-compatible AI agent the ability to scrape, crawl, batch-extract, and search the web in real time.
git clone https://github.com/olostep/olostep-mcp-server.git -
You.com Web Access & AI
MCP serversWeb search, AI agent, and content extraction via You.com APIs
@youdotcom-oss/mcp@4.0.7 -
agent-search-mcp
MCP serversFree-first Chinese and English web search MCP using zero-key sources and inspectable evidence.
agent-search-mcp@3.2.1 -
Molio
MCP serversA local-first personal knowledge layer for AI agents. Build evolving knowledge spaces with LLM Wiki, knowledge graphs, and agent workflows.
git clone https://github.com/zhuzhaoyun/Molio.git -
Awwwards-mcp
MCP serversFree, open-source MCP server that gives AI coding agents (Claude Code, Codex, Cursor, OpenCode, ZCode…) design inspiration from award-winning websites — search with real screenshots, pull design DNA, capture and record live sites. A Mobbin alternative. No API key.
git clone https://github.com/INSANE0777/Awwwards-mcp.git -
agent-web-actions
MCP serversStealth web automation for AI agents. Login, signup, navigate, screenshot.
-
agent-web-actions
MCP serversStealth web automation for AI agents. Login, signup, navigate, screenshot.
-
edgeever
MCP serversOpen-source, AI-native knowledge base & Evernote alternative with native MCP. Zero-cost on Cloudflare or Docker.
git clone https://github.com/tianma-if/edgeever.git -
speedrun
MCP serversFastest cross-platform E2E Automation for Mobile & Web
git clone https://github.com/hubastard/speedrun.git -
TinyFish AI Web Agent
MCP serversAI-powered web automation. Navigate websites using AI agents for one page or a thousand
-
web-recon-agent
MCP serversOwned-target web security assessment MCP server for authenticated, high-friction apps.
mcp-web-recon-agent@0.8.1 -
TinyFish AI Web Agent
MCP serversAI-powered web automation. Navigate websites using AI agents for one page or a thousand
-
axuse
MCP serversAccessibility-first browser & computer use for AI agents — one MCP server for every harness (Codex, Claude Code, OpenCode, Antigravity). Instruments the DOM/accessibility tree via CDP instead of screenshot loops: diffed snapshots, stable element refs, trusted input, typed errors. Zero dependencies
git clone https://github.com/ctoldigital/axuse.git -
MCP Research Agent: Web Scraping Tool for AI
MCP serversStructured web research tool for AI agents: search, fetch and shape web data into the JSON schema…
-
Path402 — Tokenised Web Content for AI Agents
MCP serversAI agents discover, acquire, and re-serve tokenised web content via the $402 protocol
path402@1.3.2 -
Iskat — Russian-language web search for agents
MCP serversRussian-language web search for agents: hybrid retrieval, product prices, full page text
-
Look up 133 agentic-web standards, live-probe any domain, validate manifests, generate boilerplate.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.