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.

Search servers

Search

Showing 481 to 510 of 1099

• Rounder tools

  io.github.adam-sari/roundertools

  Local PDF, Office, image, archive and video tools for AI agents. Files never leave your computer.

  Community npmstdio documentsfilesimage

• Rowlite MCP Server

  io.github.pipik-roman/rowlite

  Go-based MCP server providing Markdown table file inspection and row-level operations.

  Community documents

• S3eidat Tools

  io.github.s3eidat/s3eidat-tools-mcp

  Free, private PDF, image, text, developer, calculator and QR tools. Runs locally; no uploads.

  Community npmstdio developer-toolsdocumentsimage

• SSRS2

  io.github.AntoineGou/ssrs2

  Markdown to editable PowerPoint, Word, PDF; checks, edits and previews RDLC/RDL reports.

  Community remotestreamable-http documents

• Safe Docx

  io.github.UseJunior/safe-docx

  AI-native surgical editing of Word .docx and OpenDocument .odt files with formatting preservation

  Community npmstdio documentsfiles

• Safe Web Reader for AI

  io.github.marcepalacios12/safe-web-reader

  Web pages, JavaScript sites and PDFs to clean Markdown for AI agents, prompt injection removed.

  Community ai-modelsdocuments

• Saliga data tools (Apify)

  io.github.msalihk/saliga-apify-tools

  Pay-per-result data tools: bulk APIs, docs to Markdown, OCR, files, datasets, papers, tech stack.

  Community documentsfilesscience

• SammaPix — Image & PDF tools for AI agents

  io.github.samma1997/sammapix

  Image & PDF tools for AI agents: compress, convert, resize, PDF, AI vision, pipeline.

  Community remotestreamable-http documentsimage

• Samong

  io.github.waanvar/samong

  Search your own Markdown notes, including languages written without spaces between words.

  Community documentsmemorysearch

• SchemaSure — structured extraction

  io.github.noamjose/schemasure

  Extract schema-valid JSON from text/HTML or document images. Pay with x402 on Base or MPP on Tempo.

  Community npmstdio documentsimagescraping

• Scholar MCP

  io.github.Liyux3/scholar-mcp

  Federated academic search, citation traversal, persistent PDF download, and temporary reading.

  Community pypistdio sciencedocumentssearch

• Scholar MCP

  io.github.pvliesdonk/scholar-mcp

  Scholarly papers, patents, books, standards and PDF conversion

  Community pypistdio sciencedocuments

• Scholar RAG MCP

  io.github.notwhiteblank/scholar-rag-mcp

  Academic paper knowledge-base MCP server: PDF ingest, vector search with reranking, KB management.

  Community pypistdio sciencevector-searchdocuments

• Screen Control

  io.github.Xeakaes/computer-use-for-all-agents

  Safety-gated computer use for AI agents: screen OCR and vision, mouse, keyboard, window control.

  Community documents

• Screenshot & PDF Capture API

  io.github.Br0ski777/screenshot-pdf

  Capture screenshots (PNG/JPEG/WebP) and generate PDFs from any URL. x402 payments.

  Community remotesse api-integrationdocumentsimage

• ScreenshotAPI

  io.github.Screenshot-API/screenshot-mcp

  Website screenshots, URL/HTML to PDF, scrolling videos, and web scraping via ScreenshotAPI.

  Community npmstdio documentsscrapingvideo

• Screenshotline

  io.github.MAMubeenKhan/screenshotline

  Screenshot any web page, or read it as clean Markdown, with consent banners, ads and popups removed.

  Community remotestreamable-http documentsimagemarketing

• Second Brain

  io.github.ara-5/second-brain

  Shared Graph-RAG memory for AI agents: markdown vault, wikilink recall, tasks, messaging.

  Community npmstdio memorycommunicationdocuments

• Section Anything

  io.github.Omniwot/section-anything

  A PDF's real sections for agents: heading tree, pages and section text. Free mode is local.

  Community pypistdio documents

• SeekLink

  io.github.simonsysun/seeklink

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

  Community pypistdio vector-searchdocumentssearch

• Semlith

  io.github.semlith/semlith

  Local search over your code and documents for AI agents.

  Community documentssearch

• Sentor

  io.github.NIKX-Tech/sentor-mcp

  Score sentiment toward specific entities in text. Cluster documents and name topics.

  Community pypistdio documents

• Sezzlee OpenAPI

  io.github.sezzlee/openapi

  Expose an OpenAPI document to agents as a search-first tool catalog over your existing API.

  Community npmstdio api-integrationdocuments

• Sezzlee PDF

  io.github.sezzlee/pdf

  Extract text from local PDF documents with optional pluggable OCR. Read-only, no network.

  Community npmstdio documentsscraping

• Sezzlee XML

  io.github.sezzlee/xml

  Query local XML documents with XPath, paged and sandboxed to one folder. Read-only.

  Community npmstdio documents

• SharePoint MCP Server

  io.github.ravikant1918/sharepoint-mcp

  MCP server for Microsoft SharePoint — manage folders, documents, and metadata.

  Community pypistdio documents

• Shelfmark

  io.github.Dankaro-projects/shelfmark

  Local, privacy-first document catalogue for AI agents: metadata-only discovery, no cloud, no RAG.

  Community pypistdio documentsvector-search

• ShipPage

  io.github.jieshu666/shippage

  Publish HTML or Markdown to a public URL in one call. Zero config, auto-registers on first use.

  Community npmstdio documents

• SilverBullet

  io.github.wicahma/silverbullet-mcp

  List, read, write, append, delete and search markdown pages in a SilverBullet space.

  Community npmstdio documentssearch

• Skavio PDF, OCR & Document Processing MCP

  io.github.skavio-eu/processing

  OAuth PDF, OCR, invoice and audio processing with prepaid company credits; card or USDC funding.

  Community remotestreamable-http documentsaudiofinance

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.