# PathCourse Health (PCH) (npm · @pathcourse/mcp-server)

Cheaper LLM inference, USDC agent payments via x402, agent identity / reputation lookup.

- Trust score: 62/100 (medium)
- Change this week: +17
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@pathcourse/mcp-server`: 62/100 (this document), [markdown](https://verifymcp.io/servers/pathcourse-health-mcp-server/pathcourse-mcp-server.md), [page](https://verifymcp.io/servers/pathcourse-health-mcp-server/pathcourse-mcp-server)
- pypi · `pch-mcp-server`: 24/100, [markdown](https://verifymcp.io/servers/pathcourse-health-mcp-server/pch-mcp-server.md), [page](https://verifymcp.io/servers/pathcourse-health-mcp-server/pch-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@pathcourse/mcp-server`
- Version: `1.0.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 84 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 783 tokens (~55/item across 14 items; 14 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 89/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 67% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add pathcourse-health-mcp-server -- npx -y @pathcourse/mcp-server
```

### Codex

```bash
codex mcp add pathcourse-health-mcp-server -- npx -y @pathcourse/mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pathcourse-health-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@pathcourse/mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add pathcourse-health-mcp-server --command npx --arg -y --arg @pathcourse/mcp-server
```

### Hermes

```yaml
mcp_servers:
  pathcourse-health-mcp-server:
    command: "npx"
    args: ["-y", "@pathcourse/mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "pathcourse-health-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@pathcourse/mcp-server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 62, +57)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 5, −15)

- [functional regression] Tool coverage: 100 → unverified

### 2026-07-31 (score 20, −25)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 45, +20)

- [functional regression] Dependency health: partial → unverified
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-28 (score 25, −20)

- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 45)

First indexed and scored.

## MCP tools (14)

### `pch_inference` (~82 tokens)

Run LLM inference on a PCH model. Returns the model response. Uses your PCH_API_KEY from environment.

Input parameters:

- `max_tokens` (number): Maximum tokens to generate (default 500)
- `model` (string, required): Model to use
- `prompt` (string, required): The user message/prompt
- `system` (string): Optional system message

### `pch_models` (~27 tokens)

List all PCH models with pricing, tier requirements, and descriptions. No authentication required.

### `pch_balance` (~26 tokens)

Check your remaining USDC balance and current tier. Uses your PCH_API_KEY.

### `pch_estimate` (~73 tokens)

Estimate the cost of an inference request before running it. Useful for budgeting. No authentication required.

Input parameters:

- `estimated_tokens` (number, required): Estimated total tokens (or images/characters/minutes per the model billing unit)
- `model` (string, required)
- `tier` (string): Your certification tier (default uncertified)

### `pch_status` (~22 tokens)

Check PCH gateway health and service status. No authentication required.

### `pch_provision` (~64 tokens)

Get USDC payment instructions to obtain a PCH API key. Returns the treasury wallet, payment_context_id, and step-by-step instructions. No authentication required.

Input parameters:

- `deposit_usdc` (number): Amount to deposit in USDC (minimum 5 for Developer tier)

### `pch_pay` (~129 tokens)

Submit USDC payment proof after sending the deposit. Completes the x402 payment flow and returns your API key plus the first inference result. Call pch_provision first to get the payment_context_id and treasury wallet.

Input parameters:

- `buyer_wallet` (string, required): Your wallet address that sent the USDC
- `max_tokens` (number)
- `model` (string)
- `payment_context_id` (string, required): From the pch_provision response
- `prompt` (string): Prompt for your first inference request
- `tx_hash` (string, required): Your USDC transfer transaction hash on Base

### `pch_lookup_agent_identity` (~52 tokens)

Look up an agent's ERC-8004 identity record (cert tier, Path Score, services). Public, no API key required.

Input parameters:

- `agent_id` (string, required): The agent_id to look up

### `pch_get_path_score` (~42 tokens)

Look up an agent's Path Score (0-1000) and tier. Public, no API key required.

Input parameters:

- `agent_id` (string, required)

### `pch_check_agent_reputation` (~56 tokens)

Deeper reputation lookup: trust recommendation, total settled, months active, capabilities verified. Costs $0.001 USDC per query (deducted from your PCH balance).

Input parameters:

- `agent_id` (string, required)

### `pch_get_agent_history` (~48 tokens)

Twelve-month trend of an agent's Path Score broken into payment / volume / reliability / age / diversity components. Public, no API key required.

Input parameters:

- `agent_id` (string, required)

### `pch_my_account` (~31 tokens)

Self-service dashboard: balance, certification, models available, recent activity. Uses your PCH_API_KEY.

### `pch_verify_certification` (~44 tokens)

Verify a PCH-issued certification credential by cert_id. Returns validity, agent, tier. Public, no API key required.

Input parameters:

- `cert_id` (string, required)

### `pch_compare_costs` (~87 tokens)

Compare the cost of running a prompt across PCH models and major third-party providers (gpt-4o, claude-sonnet-4, claude-haiku-4-5). Useful for budgeting. No API key required.

Input parameters:

- `estimated_tokens` (number, required): Total tokens (input + output)
- `tier` (string): PCH tier (default uncertified)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/pathcourse-health-mcp-server/pathcourse-mcp-server#diagnostics

## Score history

- 2026-08-03: 62
- 2026-08-02: 62
- 2026-08-01: 5
- 2026-07-31: 20
- 2026-07-30: 45
- 2026-07-28: 25
- 2026-07-27: 45

## Links

- npm package: https://www.npmjs.com/package/@pathcourse/mcp-server
- Socket report: https://socket.dev/npm/package/@pathcourse/mcp-server
- Repository: https://github.com/pathcourse-health/pch-mcp-server
- Website: https://pathcoursehealth.com/
- Changelog RSS feed: https://verifymcp.io/servers/pathcourse-health-mcp-server/pathcourse-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/pathcourse-health-mcp-server/pathcourse-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/pathcourse-health-mcp-server/pathcourse-mcp-server