About Pyfile LLM & Data API
Pyfile LLM & Data API is a Node.js service for MCP clients and OpenAI-compatible chat callers that need pay-per-request LLM access over Lightning. It also offers a model list and L402 discovery manifest.
Key features
- 01MCP chat tool over HTTP
- 02OpenAI-compatible chat endpoint
- 03Lightning invoice-based payments
- 04Model listing and L402 manifest
Use cases
- 01Calling an LLM through an MCP client
- 02Using chat completions with L402 payments
- 03Checking available models and payment metadata
MCP support
Exposes a streamable HTTP MCP endpoint at `/mcp` with a `chat` tool. Each request is gated by an L402 Lightning invoice.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://pyfile-agent.taile3ff35.ts.net:8443/mcpclaude mcp add --transport http pyfile-toolkit-pyfile-llm https://pyfile-agent.taile3ff35.ts.net:8443/mcp{"mcpServers":{"pyfile-toolkit-pyfile-llm":{"type":"http","url":"https://pyfile-agent.taile3ff35.ts.net:8443/mcp"}}}Open in Cursor{"servers":{"pyfile-toolkit-pyfile-llm":{"type":"http","url":"https://pyfile-agent.taile3ff35.ts.net:8443/mcp"}}}Open in VS Code{"mcpServers":{"pyfile-toolkit-pyfile-llm":{"type":"http","url":"https://pyfile-agent.taile3ff35.ts.net:8443/mcp"}}}{"mcpServers":{"pyfile-toolkit-pyfile-llm":{"serverUrl":"https://pyfile-agent.taile3ff35.ts.net:8443/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 READMEl402-llm-mcp
Pay-per-query LLM access over Lightning (L402), exposed as an MCP server.
Website: pyfile-toolkit.github.io — overview, pricing and discovery across x402, Lightning (L402) and Nano.
What it is
A single Node.js server that serves two things:
- MCP endpoint
POST /mcp(streamable HTTP, tool:chat) - OpenAI-compatible
POST /v1/chat/completions
Payment is enforced by the L402 protocol: every request returns a Lightning invoice
(10 sats short, 50 sats long). Models are proxied to a free LLM backend
(gemini-3.6-flash, gpt-oss-120b).
Endpoints
| Path | Method | Price | Description |
|---|---|---|---|
/mcp | POST | 10 sats | MCP streamable-HTTP, tool chat |
/v1/chat/completions | POST | 10-50 sats | OpenAI-compatible chat |
/v1/models | GET | free | model list |
/.well-known/l402.json | GET | free | L402 manifest |
Run
export LNBOT_API_KEY=... WALLET_ID=...
node server.js
Discovery
Listed in the 402 Index and 402.pub (Nostr kind 31402).
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.