# comfy_agent_compute

One token's delivered compute from the points engine: compute_og (cumulative 0G delivered to compute for its pool, as the Infinity index records it), pool, ladder tier, and the basis sentence. The engine does not expose an agent router address, so router is null with a reason; nothing is invented. A token the index does not know as launched is data:null; an index the engine could not read is live:false with outcome compute_unknown.

Agent View of the PolicyLayer registry record for `comfy_agent_compute`. HTML page: https://policylayer.com/tools/0g-axion-comfy-mcp/comfy-agent-compute

## Facts

- Tool: `comfy_agent_compute`
- Server: Comfy (`@0g-axion/comfy-mcp`) — https://policylayer.com/tools/0g-axion-comfy-mcp.md
- Install: `npx -y @0g-axion/comfy-mcp`
- Homepage: https://www.npmjs.com/package/@0g-axion/comfy-mcp
- Risk category: Read (Low risk)
- Registry record: grade B, identity unverified
- Server rate-limited: no
- Parameters: 1 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `token` | string | yes | Token contract address (0x…, 40 hex chars). |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "comfy_agent_compute",
    "arguments": {
      "token": "<token>"
    }
  }
}
```

## Why comfy_agent_compute is rated Low

Even though comfy_agent_compute only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Risk signals: Handles credentials or secrets (token)

## Use case

AI agents call comfy_agent_compute to retrieve information from Comfy without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Comfy:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "comfy_agent_compute": {}
  }
}
```

## Other tools on Comfy (8)

- `comfy_bazaar` — Read — https://policylayer.com/tools/0g-axion-comfy-mcp/comfy-bazaar.md
- `comfy_compute_funded` — Read — https://policylayer.com/tools/0g-axion-comfy-mcp/comfy-compute-funded.md
- `comfy_jobs` — Read — https://policylayer.com/tools/0g-axion-comfy-mcp/comfy-jobs.md
- `comfy_task` — Read — https://policylayer.com/tools/0g-axion-comfy-mcp/comfy-task.md
- `comfy_tasks` — Read — https://policylayer.com/tools/0g-axion-comfy-mcp/comfy-tasks.md
- `comfy_token` — Read — https://policylayer.com/tools/0g-axion-comfy-mcp/comfy-token.md
- `comfy_tokens` — Read — https://policylayer.com/tools/0g-axion-comfy-mcp/comfy-tokens.md
- `comfy_trades` — Read — https://policylayer.com/tools/0g-axion-comfy-mcp/comfy-trades.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=0g-axion-comfy-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0g-axion-comfy-mcp