# Hermes Plant MCP Risk Score

> Hermes Plant MCP Risk Score is a paid API for AI agents from hermesplant.com, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-14).

Scores an MCP (Model Context Protocol) server or agent tool for operator safety risks such as weak auth, over-broad scope, sensitive egress, and destructive actions, returning a risk rating and recommended action.

## Facts

- Endpoint: GET https://hermesplant.com/api/agent-services/mcp-risk/score
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/hermes-plant-mcp-risk-score-f1222f9d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_UnmWF_1q9FLjQCcM7P1GJ

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 hermes-plant-mcp-risk-score-f1222f9d
```

Example prompt: Before we install this MCP server, run a Hermes Plant risk score on it — I need to know if it has weak auth, overly broad scope, or any destructive actions, and whether it should be blocked until approved.

## When to prefer this

Use this endpoint when an AI agent operator or orchestration layer needs to gate-check an MCP server or tool plugin before installation or execution — especially in regulated, enterprise, or high-stakes trading environments where weak auth, sensitive data egress, or destructive tool calls pose meaningful risk. Prefer this over manual review when you need a deterministic, test-backed score with a clear pass/block recommendation.

## Known failure modes

- Missing or malformed MCP server payload returns 400 with validation error
- Insufficient USDC balance or x402 payment failure returns 402
- Unrecognized MCP schema version may result in incomplete scoring
- Network timeout returns 504 with no score produced
- Rate limiting may return 429 if too many calls in a short window

## How this service works

Analyze an MCP server manifest for security risk before install — destructive actions, over-broad scopes, sensitive-data egress, weak auth, prompt-injection surface, and permission diff. Returns per-tool, per-factor findings with severity, why, and a concrete fix (not just a score).

## Output

A JSON object containing a risk level (e.g. 'critical'), a status of 'scored', a breakdown of risk factors (weak-auth, over-broad-scope, sensitive-egress, destructive-action each scored 0 or 1), total findingsCount, a requiresApproval boolean, and a recommendedAction string such as 'block_install_until_scoped_and_approved', plus a unique requestId.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "tools": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "name"
    ],
    "properties": {
     "name": {
      "type": "string"
     },
     "scopes": {
      "type": "array",
      "items": {
       "type": "string"
      }
     },
     "network": {
      "type": "boolean"
     },
     "description": {
      "type": "string"
     },
     "inputSchema": {
      "type": "object"
     },
     "permissions": {
      "type": "array",
      "items": {
       "type": "string"
      }
     }
    }
   },
   "description": "The server's tool manifest"
  },
  "server": {
   "type": "string",
   "description": "MCP server name/URL (optional)"
  },
  "authModel": {
   "type": "string",
   "description": "e.g. oauth, token, none"
  },
  "priorTools": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "Tool names from a prior manifest, to diff capability growth"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "risk": "critical",
  "status": "scored",
  "service": "mcp-risk-score",
  "byFactor": {
   "weak-auth": 1,
   "over-broad-scope": 1,
   "sensitive-egress": 1,
   "destructive-action": 1
  },
  "requestId": "mcp_<uuid>",
  "findingsCount": 5,
  "requiresApproval": true,
  "recommendedAction": "block_install_until_scoped_and_approved"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/hermes-plant-mcp-risk-score-f1222f9d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from hermesplant.com](https://www.zero.xyz/host/hermesplant.com/llms.txt)