Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build a website or app
-
WrapGuard MCP
MCP serversDetect unnatural Korean and English mid-word wrapping in responsive web pages.
wrapguard-mcp@0.1.1 -
agentfetch
MCP serversToken-budgeted web fetch for AI agents — auto-routes Jina, FireCrawl, Trafilatura, PDF.
agentfetch-mcp@1.0.1 -
zoogent
MCP serversAI agent orchestrator with Architect AI. Multi-team, web dashboard, 35+ MCP tools.
zoogent@0.4.2 -
mcp-server-browserbase
MCP serversMCP server for AI web browser automation using Browserbase and Stagehand
@browserbasehq/mcp-server-browserbase@2.1.1 -
claude-chat
MCP serversAnthropic Claude Messages API MCP server — chat, vision, web search, extended thinking
-
Defuddle Fetch
MCP serversFetch content from the web, cleaned up nicely for LLMs (using Defuddle).
defuddle-fetch-mcp-server@1.0.4 -
Infobroker
MCP serversMulti-provider research MCP server: unified web search, fact-checking, personal knowledge base.
infobroker@2026.11.16 -
visus-mcp
MCP serversSecurity-first web access for Claude. Sanitizes pages, blocks injection, redacts PII.
visus-mcp@0.6.1 -
Wick
MCP serversBrowser-grade web access for AI agents. Fetches any webpage, returns clean markdown.
wick-mcp@0.1.0 -
screenshotty
MCP serversCapture web pages as screenshots (returned inline) or PDFs via the Screenshotty API.
screenshotty-mcp@1.1.0 -
Exa
MCP serversExa MCP — neural/semantic web search + content retrieval (exa.ai)
@pipeworx/mcp-exa@0.2.1 -
Sarb Za
MCP serversSouth African Reserve Bank (SARB) Web API MCP. Keyless.
@pipeworx/mcp-sarb-za@0.2.1 -
Zyte
MCP serversZyte API MCP — unified web fetch + AI extraction (zyte.com)
@pipeworx/mcp-zyte@0.3.1 -
FetchV2
MCP serversFetch and extract web pages, discover links, and read llms.txt documentation indexes.
fetchv2-mcp-server@2.1.0 -
ClawPage
MCP serversExtract and structure any web page into clean JSON. Free tier: 10/day.
clawpage-mcp@0.2.1 -
Evocrawl MCP Server
MCP serversMCP server for Evocrawl — search, scrape, and interact with the web.
@evocrawl/evocrawl-mcp@4.0.1 -
yandex-metrika-mcp
MCP serversMCP server for Yandex Metrika — web analytics, counters, goals, traffic (Russia)
@theyahia/yandex-metrika-mcp@2.1.1 -
Wick
MCP serversBrowser-grade web access for AI agents. Fetches any webpage, returns clean markdown.
wick-mcp@0.5.0 -
DeepSeek Visionary
MCP serversDeepSeek web vision model as an MCP server with browser auto-login.
https://github.com/xlight/deepseek-visionary/releases/download/v0.2.2/visionary-server-aarch64-apple-darwin.mcpb -
Crawlora MCP
MCP serversHosted MCP: 4684 structured web-data tools across 534 platform groups.
-
lightpaper-mcp
MCP serversAPI-first publishing platform. Publish markdown as permanent web pages with quality scoring.
lightpaper-mcp@0.1.1 -
Yandex Metrika MCP
MCP serversMCP server for Yandex Metrika API — web analytics, traffic, audience data
@stufently/yandex-metrika-mcp@2.3.0 -
FATSEARCH
MCP serversWeb pages, PDFs and documents as small, clean, cached Markdown for AI agents
fatsearch@0.2.5 -
agentwebintel
MCP serversProxy-rotated web scraping and cross-platform intelligence for AI agents.
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.