# ONNX Graph Pruner MCP

> ONNX Graph Pruner MCP is a paid API for AI agents from api.m2mcent.com, paid per call via x402, $0.3/call, status unknown (last checked 2026-09-14).

Prunes and optimizes ONNX computational graphs by removing redundant nodes, unused operators, or dead branches to reduce model size and inference cost.

## Facts

- Endpoint: POST https://api.m2mcent.com/onnx-graph-pruner-mcp/api/process
- Price: $0.3/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/onnx-graph-pruner-mcp-0cbba049
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_d3wrMKc29ubFhWjcGdjlH

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability onnx-graph-pruner-mcp-0cbba049 -d '<json body>'
```

Example prompt: Can you prune this ONNX model graph to remove unused nodes and dead branches? Here's the serialized graph data: [graph_data].

## When to prefer this

Choose this endpoint when you need automated pruning of ONNX computational graphs — especially after exporting from PyTorch or TensorFlow when the graph contains tracing artifacts, dead branches, or unused operators. Prefer this over manual graph editing when you want a programmatic, repeatable pruning step in an ML pipeline.

## Known failure modes

- Invalid or malformed ONNX graph data returns an error
- Empty or missing data field causes request rejection
- Unsupported ONNX opset versions may fail silently or return unchanged graph
- Very large graph data may time out
- Non-ONNX formatted input data returns a parsing error

## How this service works

The premier global index of 1,069 monetized MCP nodes across 205 specialized subdomains. Gasless USDC runtime settlements via x402 V2 Spec on Base L2. Save 95% token context.

## Output

Returns the pruned ONNX graph with redundant nodes, dead branches, and unused operators removed, resulting in a leaner computational graph suitable for faster inference or further optimization steps.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "payload": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "success": true
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/onnx-graph-pruner-mcp-0cbba049/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.m2mcent.com](https://www.zero.xyz/host/api.m2mcent.com/llms.txt)