Pipeworx vs mcp.so
live data gateway vs MCP server directory
one unified MCP gateway with ~290 first-party live data sources.
browsing and discovering third-party MCP servers from a catalog.
mcp.so is an MCP server directory that indexes third-party servers across many domains. Pipeworx is a single MCP gateway running ~290 first-party data packs behind one URL. Use mcp.so to discover what's available in the broader ecosystem; use Pipeworx when you want a curated live-data layer with consistent auth, telemetry, and reliability across many sources behind one connection.
Side-by-side
| Pipeworx | mcp.so | |
|---|---|---|
| Model | Single gateway, first-party packs | Directory of third-party MCP servers |
| Coverage | ~290 packs, ~1,000 tools (live data) | Wide variety, quality varies |
| Setup | One URL → ~290 sources | One config per server |
| Auth uniformity | Anonymous / BYO key / account — all unified | Per-server |
| Meta-tools | ask_pipeworx, discover_tools, entity_profile, etc. | None |
| Citable URIs | Yes — pipeworx://… | Per server |
When to use which
Use mcp.so if
- You want to browse the third-party MCP ecosystem
- You need a niche server outside the live-data category
- You're submitting your own server for listing
Use Pipeworx if
- You want broad, curated live-data access through one URL
- You need uniform auth and rate limiting across many sources
- You're building agents that need reliable, citable primary-source data
Connect Pipeworx in one line
Add this to your MCP client (Claude Desktop, Cursor, VS Code, Claude Code, etc.) — no API keys required for public data sources.
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
} Common questions
Is Pipeworx listed on mcp.so?
Pipeworx is independently hosted at https://gateway.pipeworx.io/mcp. Submission to MCP directories like mcp.so is in progress; the canonical entry point is always the gateway URL.
Should I use a directory or a gateway?
It depends on goal. A directory helps you discover servers. A gateway gives you one connection to many curated sources. If you're building an agent that needs live data across multiple domains, a gateway is usually cheaper and more reliable than wiring 20+ third-party servers individually.