searchFuelDocsLABSCO SUMMARY
Sway answers from the documentation, not from what the model recalls.
Sway and the Fuel toolchain move faster than any model's training data, which is exactly the case where retrieval beats memory. The index is a local file — no vector database to run, and re-indexing after a docs update is one command.
What it is
A Bun server that indexes Fuel Network and Sway documentation into a local Vectra vector store with Transformers.js embeddings, then answers semantic queries against it. No Docker and no external database.
What you get
- Documentation searched by meaning, with a configurable result count and optional relevance scores — searchFuelDocs
- Sway standard library paths and types returned as context — provideStdContext
- Hybrid retrieval: semantic results with a keyword fallback and quality filtering
- Chunking that preserves code blocks rather than splitting an example in half
- Stdio by default, or HTTP on a port you choose with a /health endpoint
- A bundled docs set covering forc commands, the Sway reference and LSP, the GraphQL reference, wallet development, contract and frontend quickstarts and the storage API
Requirements
Bun. Clone the repository, run bun install, then index the documentation with bun run src/indexer.ts ./docs before the first query. VECTRA_INDEX_PATH, EMBEDDING_MODEL (default Xenova/all-MiniLM-L6-v2), CHUNK_SIZE (default 2000) and NUM_RESULTS (default 5) are all optional.
Setup effort
Build from source — git clone https://github.com/FuelLabs/fuel-mcp-server
USE CASES
01
Writing Sway without guessing the syntax
Search the indexed docs by meaning and get back passages with the code blocks intact, rather than a paraphrase with a plausible-looking snippet.
02
Finding the right std library type
The standard library paths and types come back as context, so an import is resolved from the docs instead of invented.
03
Looking up a forc command
The bundled documentation covers forc commands and the nightly set, so the flag you need is a query rather than a terminal round trip.
04
Keeping the index current
Point the indexer at an updated docs directory and re-run it; the vector store is a local Vectra index with nothing external to migrate.
2 tools
Listed in project docs. Your client may show a different list.
provideStdContextBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
# Clone the repo
git clone https://github.com/FuelLabs/fuel-mcp-server
cd fuel-mcp-server
# Install dependencies
bun install
# Index documentation
bun run src/indexer.ts ./docs
# Test search
bun run src/query.ts --run "What is FuelVM?"
# Start MCP server
bun run src/cli.tsMCP Clients
Claude Desktop, Cursor
JSON
{
"mcpServers": {
"fuel-server": {
"command": "bun",
"args": [
"run",
"<YOUR_PATH_TO_FUEL_MCP_SERVER>/src/cli.ts",
"--transport",
"stdio"
]
}
}
}
