About Crates
Crates is an MCP server for querying crates.io, aimed at Rust developers evaluating packages and their dependencies. It provides package metadata, version history, and both direct and reverse dependency details.
Key features
- 01Search Rust packages by keyword
- 02Retrieve crate metadata and categories
- 03List versions, downloads, and publish dates
- 04Inspect dependencies and their requirements
- 05Find reverse dependencies and adoption
Use cases
- 01Compare crates while choosing a Rust package
- 02Audit a crate's dependency footprint
- 03Check which projects depend on a crate
MCP support
Exposes crates.io search, metadata, version, and dependency tools to MCP clients, through Pipeworx or as a standalone local stdio server.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://gateway.pipeworx.io/crates/mcpclaude mcp add --transport http pipeworx-io-crates https://gateway.pipeworx.io/crates/mcp{"mcpServers":{"pipeworx-io-crates":{"type":"http","url":"https://gateway.pipeworx.io/crates/mcp"}}}Open in Cursor{"servers":{"pipeworx-io-crates":{"type":"http","url":"https://gateway.pipeworx.io/crates/mcp"}}}Open in VS Code{"mcpServers":{"pipeworx-io-crates":{"type":"http","url":"https://gateway.pipeworx.io/crates/mcp"}}}{"mcpServers":{"pipeworx-io-crates":{"serverUrl":"https://gateway.pipeworx.io/crates/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEmcp-crates
Crates.io MCP — wraps the crates.io REST API v1 (free, no auth)
Part of Pipeworx — an MCP gateway connecting AI agents to 1875+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
Tools
| Tool | Description |
|---|---|
search_crates | Search crates.io for Rust packages by keyword. Returns crate name, description, downloads, latest version, and repo URL. |
get_crate | Get full metadata for a specific crate (e.g., 'serde'). Returns description, downloads, latest version, repo, homepage, and categories. |
get_versions | List all published versions for a crate in reverse chronological order. Returns version number, download count, and publish date. |
get_crate_dependencies | List the dependencies of a specific crate version — what itself depends on. Returns each dependency with its version requirement, kind (normal/build/dev), optional flag, enabled features, and target. Version is optional (defaults to the latest stable). Use for "what does depend on", dependency audits, or sizing a crate's footprint. |
get_crate_reverse_deps | List crates that DEPEND ON a given crate (reverse dependencies), most-downloaded first — answers "what uses ", "how widely adopted is ", "who depends on ". Returns the total dependent count plus the top dependents with their version requirement, dependency kind, and download counts. |
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"crates": {
"url": "https://gateway.pipeworx.io/crates/mcp"
}
}
}
What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/crates/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1875+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
No MCP client? Call it over HTTP
curl -X POST https://gateway.pipeworx.io/v1/tools/search_crates \
-H 'Content-Type: application/json' \
-d '{"query":"web framework"}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/search_crates. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
Standalone (no gateway account)
This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:
{
"mcpServers": {
"crates": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-crates"]
}
}
}
Or run it directly to confirm it starts:
npx -y @pipeworx/mcp-crates
It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call
for only this pack's tools — none of the shared meta-tools the gateway
connection above adds. Same source, same tools, no ask_pipeworx routing.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Crates data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.