OpenAI-compatible multi-model inference via ComputeFlux (Polkadot testnet, TEE-verifiable). stdio.
Zero-dependency MCP (Model Context Protocol) server. Give any MCP host — Cursor, Claude Desktop, Windsurf, any MCP client — one OpenAI-compatible endpoint, and call models on ComputeFlux as plain tools: list what's available, then run a chat completion.
Your MCP agents hit flash-tier models over one OpenAI-compatible endpoint.
npm install to run the server (only the optional
client/ e2e harness pulls SDK deps).| Tool | What it does |
|---|---|
computeflux_models | Lists the model ids served by the endpoint. |
computeflux_chat | Runs a non-streaming chat completion (model + OpenAI messages; optional max_tokens, temperature). Returns model, finish reason, latency, usage, and the assistant text. |
| Variable | Required | Default | Notes |
|---|---|---|---|
COMPUTEFLUX_API_KEY | yes | — | Bearer key for the endpoint. |
COMPUTEFLUX_BASE_URL | no | https://api.computeflux.ai/v1 | Any OpenAI-compatible base URL. |
export COMPUTEFLUX_API_KEY="your_c***_key"
# export COMPUTEFLUX_BASE_URL="https://your-openai-compat-host/v1" # optional
Published on the official MCP Registry (.mcpb bundle, no npm step):
io.github.computeflux2026isgod/mcp-computeflux — listed on the official MCP Registry (search by this name).
Any MCP client / agent that supports registry install (mcp add, Cursor, Claude Desktop,
Claude Code) can pull it by name. Direct git-clone quickstart:
git clone https://github.com/computeflux2026isgod/mcp-computeflux
export COMPUTEFLUX_API_KEY="your_...key"
node /path/to/mcp-computeflux/server.mjs # stdio JSON-RPC
mcpServers snippet:
{
"mcpServers": {
"computeflux": {
"command": "node",
"args": ["/path/to/mcp-computeflux/server.mjs"],
"env": { "COMPUTEFLUX_API_KEY": "your_c***_key" }
}
}
}
client/ contains a tiny harness using the official MCP SDK — the exact path
Cursor / Claude Desktop use. It spawns the server over stdio, lists tools, and runs
one chat completion with a unique-token round-trip fidelity check.
cd client && npm install && npm run e2e # expects COMPUTEFLUX_API_KEY in the .env it points to
Newline-delimited JSON-RPC 2.0 over stdio. Only protocol messages are written to stdout; logs go to stderr.
MIT
This listing does not have a supported local package template. Use the maintainer’s documentation for its hosted endpoint, authentication, and client-specific setup. No install command has been inferred.
https://github.com/computeflux2026isgod/mcp-computeflux/releases/download/v1.0.0.0/send_mcp-computeflux.mcpbothermcp-computeflux works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.
~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.~/.cursor/mcp.jsonRestart Cursor for changes to take effect..vscode/mcp.jsonReload VS Code window for changes to take effect.~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect..mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.