Power your agent
การติดตั้งจากผู้เผยแพร่ ไม่ใช่เอนด์พอยต์ของ PlugMCP
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
An MCP (Model Context Protocol) server that provides semantic search capabilities for Rust crate documentation through vector embeddings.
This MCP server enables AI assistants to search and understand Rust crate documentation by:
sse mcp server that embeds rust docs (with chunking) and allows for querying them from any mcp client
cargo doc# Clone the repository
git clone https://github.com/yourusername/mcp-rust-docs-embed
cd mcp-rust-docs-embed
# Build the project
cargo build --release
Create a .env file with the following variables:
# Required
QDRANT_URL=http://localhost:6334
OPENAI_API_KEY=your_openai_api_key
# Optional
QDRANT_API_KEY=your_qdrant_api_key
PORT=8080 # Default: 8080
cargo run
The server will start on http://127.0.0.1:8080/sse (or your configured port).
To use this server with Claude Code or other MCP clients, add it to your MCP configuration:
{
"rust-docs": {
"type": "sse",
"url": "https://mcp-rust-docs-embed-production.up.railway.app/sse"
}
}
For local development, replace the URL with your local server:
{
"rust-docs": {
"type": "sse",
"url": "http://127.0.0.1:8080/sse"
}
}
embed_crateGenerate and embed documentation for a Rust crate.
Parameters:
crate_name (required): Name of the crate to documentversion (optional): Version to embed (defaults to *, i.e., latest)features (optional): List of features to enable (validated against available features)Example:
{
"crate_name": "tokio",
"version": "1.40.0",
"features": ["full"]
}
Note: The server validates requested features against available crate features and prevents re-embedding with different features unless the existing collection is deleted first.
query_embeddingsSearch embedded documentation using natural language.
Parameters:
query (required): Natural language search querycrate_name (required): Crate to search inversion (optional): Version to search (defaults to latest)limit (optional): Number of results (default: 10)Example:
{
"query": "how to create an async tcp server",
"crate_name": "tokio",
"limit": 5
}
query_embed_statusCheck the status of an ongoing embedding operation.
Parameters:
operation_id (required): ID returned by embed_cratelist_embedded_cratesList all crates and versions that have been embedded, including their features, embedding timestamp, and document count.
query_crate_featuresQuery available features for a specific crate and version.
Parameters:
crate_name (required): Name of the crate to query features forversion (optional): Version to check (defaults to *, i.e., latest)Example:
{
"crate_name": "tokio",
"version": "1.40.0"
}
Documentation Generation (docs_builder.rs)
cargo +nightly doc --output-format=jsonJSON Processing (doc_loader.rs, json_types.rs)
Embedding Generation (documentation.rs)
Storage (data_store.rs)
{crate_name}_v{version} (normalized)The QueryService (query.rs) handles:
rmcp - Rust MCP SDKqdrant-client - Vector database clientcargo - Programmatic cargo operationsasync-openai - OpenAI API clientaxum - Web framework for SSE servertokio - Async runtimesse mcp server that embeds rust docs (with chunking) and allows for querying them from any mcp client
เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
MCP Rust Docs Embed ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-10-26 sse mcp server that embeds rust docs (with chunking) and allows for querying them from any mcp client
