A Rust-powered MCP (Model Context Protocol) server providing AI assistants with deep code understanding through 90 specialized tools.
A Rust-powered MCP (Model Context Protocol) server providing AI assistants with deep code understanding through 90 specialized tools. The narsil mcp mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 12 defined tools rather than through you.
Everything the assistant can do here goes through one of these:
EMBEDDING_API_KEY — Generic API key for any providerVOYAGE_API_KEY — Voyage AI specific API keyOPENAI_API_KEY — OpenAI specific API keyEMBEDDING_SERVER_ENDPOINT — Custom embedding API endpoint URL (optional, allows using self-hosted models)Feature — Descriptiongraph — + RDF knowledge graph, SPARQL, CCG toolsfrontend — + Embedded visualization web UIneural — + TF-IDF vector search, API embeddingsneural-onnx — + Local ONNX model inferencewasm — Browser build (no file system, git)Configuration — The Configuration tool exposed by this serverPresets — The Presets tool exposed by this serverBeing a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
You will need 8 environment variables: NARSIL_REPOS, NARSIL_PROFILE, NARSIL_PRESET, NARSIL_ENABLED_CATEGORIES, NARSIL_DISABLED_TOOLS, VOYAGE_API_KEY, EMBEDDING_API_KEY, OPENAI_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Narsil MCP's toolset — EMBEDDING_API_KEY, VOYAGE_API_KEY, OPENAI_API_KEY and 9 more — is a fair guide to whether it matches your workflow. It is maintained by postrv; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| EMBEDDING_API_KEY | Generic API key for any provider |
| VOYAGE_API_KEY | Voyage AI specific API key |
| OPENAI_API_KEY | OpenAI specific API key |
| EMBEDDING_SERVER_ENDPOINT | Custom embedding API endpoint URL (optional, allows using self-hosted models) |
| Feature | Description |
| graph | + RDF knowledge graph, SPARQL, CCG tools |
| frontend | + Embedded visualization web UI |
| neural | + TF-IDF vector search, API embeddings |
| neural-onnx | + Local ONNX model inference |
| wasm | Browser build (no file system, git) |
| Configuration | The Configuration tool exposed by this server. |
| Presets | The Presets tool exposed by this server. |
{
"mcpServers": {
"narsil": {
"command": "npx",
"args": ["-y", "narsil-mcp"],
"env": {
"NARSIL_REPOS": "your-value",
"NARSIL_PROFILE": "your-value",
"NARSIL_PRESET": "your-value",
"NARSIL_ENABLED_CATEGORIES": "your-value",
"NARSIL_DISABLED_TOOLS": "your-value",
"VOYAGE_API_KEY": "your-value",
"EMBEDDING_API_KEY": "your-value",
"OPENAI_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| NARSIL_REPOS | Configuration value read at startup. | Optional |
| NARSIL_PROFILE | Configuration value read at startup. | Optional |
| NARSIL_PRESET | Configuration value read at startup. | Optional |
| NARSIL_ENABLED_CATEGORIES | Configuration value read at startup. | Optional |
| NARSIL_DISABLED_TOOLS | Configuration value read at startup. | Optional |
| VOYAGE_API_KEY | Credential the server authenticates with. | Yes |
| EMBEDDING_API_KEY | Credential the server authenticates with. | Yes |
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.