Pricing

Pay per event

MCP.so Server Directory Scraper

Scrape the complete MCP.so server directory — the 3rd canonical MCP registry alongside Smithery and Glama. Extracts server name, author, category, tags, capabilities, install command, GitHub repo URL, README, and more for every listed MCP server.

Pricing

Pay per event

Rating

0.0

(0)

Developer

BowTiedRaccoon

Actor stats

Bookmarked

Total users

Monthly active users

3 days ago

Last modified

What does it scrape?

MCP.so is one of the top-3 community indexes for Model Context Protocol (MCP) servers — the protocol used by Claude Desktop, Cursor, Windsurf, and Codex to connect AI models to external tools. This scraper enumerates every server in the directory and returns a structured record per entry.

Data fields returned

Field	Description
`server_id`	Unique identifier in `<slug>/<author>` format
`server_name`	Display name of the MCP server
`server_slug`	URL slug
`author_username`	GitHub username of the author
`author_avatar_url`	Author avatar image URL
`tagline`	Short description
`description`	Full description
`category`	Category (databases, developer-tools, etc.)
`tags`	Comma-separated tags
`capabilities`	MCP capability types present (tools, resources, prompts)
`tool_count`	Number of MCP tools exposed
`install_command`	npx / uvx / docker installation command
`npm_package`	NPM package name (if applicable)
`pypi_package`	PyPI package name (if applicable)
`docker_image`	Docker image name (if applicable)
`github_repo`	GitHub repository URL
`is_official`	Whether this is an official MCP team server
`is_verified`	Whether marked as featured/verified
`listed_at`	Date first listed on mcp.so
`updated_at`	Last update timestamp
`readme_markdown`	Full README content
`profile_url`	URL of the mcp.so server page
`scraped_at`	Scrape timestamp

Usage

Set maxItems to limit the number of servers returned. The directory has ~2,000 servers across two sitemaps.

Input

{
  "maxItems": 100
}

Output sample

{
  "server_id": "redis/modelcontextprotocol",
  "server_name": "Redis",
  "server_slug": "redis",
  "author_username": "modelcontextprotocol",
  "category": "databases",
  "tags": "redis, database, key-value-store",
  "capabilities": "tools",
  "tool_count": 13,
  "install_command": "docker run -i --rm mcp/redis {redis_url}",
  "docker_image": "mcp/redis",
  "github_repo": "https://github.com/modelcontextprotocol/servers/tree/main/src/redis",
  "is_official": true,
  "is_verified": true,
  "listed_at": "2025-03-20T06:04:26.794Z",
  "profile_url": "https://mcp.so/server/redis/modelcontextprotocol"
}

Triple MCP Coverage

This scraper completes our 3-index MCP directory coverage:

Registry	Actor
Smithery	`jungle_synthesizer/smithery-mcp-registry-scraper`
Glama	`jungle_synthesizer/glama-mcp-registry-scraper`
MCP.so	This actor

Use all three to build an exhaustive MCP server catalog for agent platform development, ecosystem analysis, or security research.

Notes on data availability

The following fields are not stored by mcp.so and will be null in all records: github_stars, github_forks, language, license, view_count, install_count. These require GitHub API enrichment as a separate step.

MCP Server Directory Scraper: MCP Discovery Export

lovely_sequoia/mcp-directory-scraper

Aggregate public MCP server, ChatGPT app, and Claude connector listings from Glama.ai, PulseMCP, mcp.so, and MCP App Store into one deduplicated dataset.

Kris Jensen

TopAI.tools Scraper: export AI tool listings

lovely_sequoia/topai-scraper

Export public TopAI.tools listings for AI market research, category mapping, pricing checks, deal monitoring, and directory building. Start with 5 to 50 tools, then scale.

Kris Jensen

🎯 Sales Intelligence MCP

nexgendata/sales-intelligence-mcp

MCP server bundling 10 lead-generation and enrichment actors as AI-agent tools — a pay-per-result alternative to Apollo, ZoomInfo and Clay. Works with Claude Desktop, Cursor, n8n and any MCP-compatible client. No seats, no contracts, no quotas.

NexGenData

Elder Care Facility Intelligence MCP Server

ryanclinton/elder-care-facility-intelligence-mcp

Nursing home and assisted living due diligence intelligence via the Model Context Protocol.

Ryan Clinton

Google Scholar Lite - Cheap Bulk Academic Papers API

johnvc/google-scholar-lite-api

Search Google Scholar for academic papers in bulk and export clean JSON: title, authors, journal, year, citation count, and PDF links. Fast bibliometric search for literature reviews, citation discovery, and research datasets. Pay per paper from $1.50 per 1,000, with no setup or per-run fee.

John

5.0

(4)

Google Images API - $0.10 per 1,000 - Fast Image API

johnvc/google-images-api

Scrape Google Images at scale and export clean JSON: image URL, width and height, thumbnail, source site, domain, and the page link. Bulk image search for SEO research, training datasets, and AI agents. Pay per image from $0.10 per 1,000 results, with no setup or per-run fee.

John

YouTube Transcript Scraper Pro (Captions + AI Fallback)

codepoetry/youtube-transcript-ai-scraper

Extract YouTube transcripts at scale without burning through your budget. It starts with free captions whenever they're available, then switches to AI only for videos that don't have them. You stay in control of costs, and the output — JSON, SRT, VTT, plain text, or LLM-ready format

CodePoetry

326

Deutsche Bahn Ticket Scraper

jindrich.bar/deutsche-bahn-ticket-scraper

Scrape Deutsche Bahn connection options and ticket prices with this Actor. Stay on top of the data of Germany's largest railway company.

Jindřich Bär

5.0

(1)

PubMed Scraper

labrat011/pubmed-scraper

Search 35M+ medical citations from PubMed/MEDLINE. Extract articles, abstracts, authors, MeSH terms, and citations for research, competitive intelligence, or AI/RAG pipelines. No API key required.