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.
Showing 1771 to 1800 of 1933
-
refigure
io.github.HelgDemidov/refigure
Convert DOCX/XLSX to Markdown — native chart-data extraction, optional VLM for figures
-
rejstrik-mcp
io.github.janF19/rejstrik-mcp
Czech company registry MCP that reads filed PDF financial statements — keyless, agent-native.
-
relayted API
de.relayted/api
Screenshots in real browsers, web page to Markdown or PDF, Nostr relay tests. Prepaid per request.
-
rendercheck
io.github.ParthibanRajasekaran/rendercheck
Check from a screenshot that text is really visible to users. Local, offline OCR.
-
repage
app.repage/repage
Publish HTML & Markdown to shareable links with versions, comments, and project organization.
-
resume
io.github.theluckystrike/resume
Tailor a resume and write a cover letter as real Word .docx files from facts you stored once.
-
resumejson
com.tiraisoft/resumejson
Parse a resume or CV (PDF, DOCX, text, scan or photo) into typed JSON.
-
review-assist-mcp
io.github.uditk2/review-assist-mcp
Turns an AI coding agent session into a reviewable Intent Document, validated against the diff.
-
ris
io.github.Honeyfield-Org/ris
Access Austrian laws, court decisions & legal documents via the RIS API.
-
roTEAMnet Career Workspace
com.roteamnet/career-workspace
Search jobs, review confirmed CV facts and prepare documents with scoped OAuth access.
-
rq-scan
io.github.RECERQA/rq-scan
MCP Server for RQ-SCAN - AI-powered document OCR and data extraction platform
-
rtfx.pro
pro.rtfx/rtfx
Publish what Claude makes (HTML, PDF, small site) to a private link only chosen people can open.
-
rutter
io.github.shinytoyrobots/rutter
Recall past decisions and the notes your AI sessions cited, from a local markdown folder.
-
scholar
io.github.mlintangmz2765/scholar
Hardened Scholar MCP for deep academic research (Scopus, OpenAlex, Unpaywall) with PDF vision.
-
scrapa.app
app.scrapa/scrapa
Read web pages as markdown, search the web, list a site's URLs and run a real Chrome.
-
scraper
io.github.ofershap/scraper
Web scraping MCP — extract clean markdown, links, and metadata from any URL.
-
scrapi
io.github.bamchi/scrapi
Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.
-
scree
io.github.jrapakko/scree
Local semantic and keyword search over the markdown in a repo or notes folder.
-
screenshot-api
io.github.therealMrFunGuy/screenshot-api
Website screenshots as PNG, JPEG, or PDF with custom viewports and full-page capture.
-
screenshot.com.ar
ar.com.screenshot/screenshot
Screenshots and clean markdown of any public web page, rendered in a real Chrome browser.
-
scribe
com.writulos/scribe
Generate clean markdown documentation for your code — one file, or up to 20 in one batch.
-
scribo
io.github.causa-prima-ai/scribo
EN 16931-compliant e-invoices: XRechnung, ZUGFeRD, Factur-X, Peppol BIS, Facturae or US PDF. Free.
-
sealtier
io.github.CloudCorpRecords/sealtier
Local OKF tier check for Markdown folders: scan tiers, trust verdicts and git change reports.
-
search
com.neurobird/search
Web search for AI agents. Ranked results with page passages already extracted, plus URL to markdown.
-
searchts
io.github.capad-xyz/searchts
Keyless web access for AI agents: read bot-walled pages as Markdown, search, grab assets
-
searxNcrawl
io.github.DasDigitaleMomentum/searxncrawl
Web search via SearXNG and/or You.com, plus clean Markdown crawling via Crawl4AI. Self-hosted.
-
searxng-deepdive
io.github.burakaydinofficial/searxng-deepdive
MCP server for SearXNG with engine targeting, multi-page fanout, and HTML→Markdown URL reading.
-
second-brain-bridge
io.github.IsaiahDupree/second-brain-bridge
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
-
sendpage
com.sendpageapp/sendpage
Publish an HTML document as a link anyone can open in one tap, plus PDF, image and Word export.
-
sensefold
app.sensefold/sensefold
Personal context for every AI: search, read, and write back to your private Markdown library.
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.