Open-source API gateway for AI providers. Logs every request with token counts and dollar costs.
Llmkit MCP server exists for a simple reason — assistants are far more useful when they can act on Llmkit directly instead of describing what you should do. Open-source API gateway for AI providers. Logs every request with token counts and dollar costs.
Installation goes through your MCP client rather than a global install: point it at @f3d1/llmkit-cli on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Once Llmkit is connected, these are the calls the assistant has available:
uses — smigolsmigol/llmkit/.github/actions/llmkit-budget@mainLayer — WhatEncryption — Provider keys: AES-256-GCM, random IV, context-bound AADHashing — User API keys: SHA-256, never stored in plaintextRuntime — Cloudflare Workers: no filesystem, no .env, nothing to exfiltrateProvenance — npm packages published with Sigstore provenance via GitHub Actions OIDCPre-commit — 19 secret patterns + credential file blocking + gitleaksPackage — DescriptionYou will need 5 environment variables: LLMKIT_API_KEY, LLMKIT_KEY, SUPABASE_URL, SUPABASE_KEY, ENCRYPTION_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.
Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Llmkit's toolset — uses, Layer, Encryption and 5 more — is a fair guide to whether it matches your workflow. It is maintained by smigolsmigol; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| uses | smigolsmigol/llmkit/.github/actions/llmkit-budget@main |
| Layer | What |
| Encryption | Provider keys: AES-256-GCM, random IV, context-bound AAD |
| Hashing | User API keys: SHA-256, never stored in plaintext |
| Runtime | Cloudflare Workers: no filesystem, no .env, nothing to exfiltrate |
| Provenance | npm packages published with [Sigstore provenance](https://docs.npmjs.com/generating-provenance-statements) via GitHub Actions OIDC |
| Pre-commit | 19 secret patterns + credential file blocking + gitleaks |
| Package | Description |
{
"mcpServers": {
"llmkit": {
"command": "npx",
"args": ["-y", "@f3d1/llmkit-cli"],
"env": {
"LLMKIT_API_KEY": "your-value",
"LLMKIT_KEY": "your-value",
"SUPABASE_URL": "your-value",
"SUPABASE_KEY": "your-value",
"ENCRYPTION_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| LLMKIT_API_KEY | Credential the server authenticates with. | Yes |
| LLMKIT_KEY | Credential the server authenticates with. | Yes |
| SUPABASE_URL | Endpoint or connection string the server talks to. | Yes |
| SUPABASE_KEY | Credential the server authenticates with. | Yes |
| ENCRYPTION_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.