parallelix-mcp
v0.1.1
Published
MCP server for the ParalleliX Compute API. Offload parallel inference sub-tasks to a distributed GPU network, paid in $PRLX credits.
Maintainers
Readme
parallelix-mcp
An MCP (Model Context Protocol) server for the ParalleliX Compute API. It gives an MCP client (Claude Code, Claude Desktop) tools to offload parallel inference sub-tasks to the ParalleliX network, paid in $PRLX credits.
The pattern: your frontier agent orchestrates and reasons; the distributed open-source fleet runs the cheap, embarrassingly-parallel parts. Bulk classify, extract, summarize, or translate hundreds of items in one parallel_map call instead of burning frontier tokens on a loop.
What you need
- An API key. Create one in the ParalleliX app under Developers (connect a wallet, add $PRLX credits, create a key). The key looks like
pk_live_…and is shown once. - Node 18 or newer.
Tools
parallel_map(items, instruction, model?)Run the same instruction over many items in parallel across the network. Returns one result per item with a Proof-of-Execution hash.infer(prompt, model?)Run a single prompt on the network. Returns the completion, the serving node id, and its PoE hash.network_status()List the models the network currently serves.usage()Show this key's request count, $PRLX credits spent, and remaining balance.
Use with Claude Desktop
Add this to claude_desktop_config.json:
{
"mcpServers": {
"parallelix": {
"command": "npx",
"args": ["-y", "parallelix-mcp"],
"env": {
"PARALLELIX_API_KEY": "pk_live_your_key_here"
}
}
}
}Use with Claude Code
claude mcp add parallelix --env PARALLELIX_API_KEY=pk_live_your_key_here -- npx -y parallelix-mcpConfiguration
| Env var | Required | Default | Notes |
| --- | --- | --- | --- |
| PARALLELIX_API_KEY | yes | none | Your pk_live_… key. |
| PARALLELIX_BASE_URL | no | https://api.parallelix.io | Point at a local coordinator for testing. |
Honest notes
- The network runs open-source models (currently 7B-class, e.g.
qwen2.5:7b). It is not a frontier model and is not meant to replace one. It is a cheap parallel executor for bulk independent sub-tasks. - Capacity is real and finite. Large batches queue;
usageandnetwork_statusshow you what's available. - Credits are metered off-chain by the coordinator (deposit $PRLX once on-chain, no per-call gas). v1 is custodial.
License
MIT
