# io.github.stevemilton/agentmarketplace-mcp (npm · agentmarketplace-mcp)

Discover MCP servers + tools, auto-install into any client, pay for x402 endpoints in USDC.

- Trust score: 50/100 (low)
- Change this week: +21
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `agentmarketplace-mcp`: 50/100 (this document), [markdown](https://verifymcp.io/servers/stevemilton-agentmarketplace-mcp/agentmarketplace-mcp.md), [page](https://verifymcp.io/servers/stevemilton-agentmarketplace-mcp/agentmarketplace-mcp)

## Channel facts

- Registry: `npm`
- Package: `agentmarketplace-mcp`
- Version: `0.3.1`
- 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 (107 of 111), 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 (107 of 111), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 4 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 49/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 447 tokens (~63/item across 7 items; 7 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 23/100
  - 0% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 69% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add stevemilton-agentmarketplace-mcp -- npx -y agentmarketplace-mcp
```

### Codex

```bash
codex mcp add stevemilton-agentmarketplace-mcp -- npx -y agentmarketplace-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add stevemilton-agentmarketplace-mcp --command npx --arg -y --arg agentmarketplace-mcp
```

### Hermes

```yaml
mcp_servers:
  stevemilton-agentmarketplace-mcp:
    command: "npx"
    args: ["-y", "agentmarketplace-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "stevemilton-agentmarketplace-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "agentmarketplace-mcp"
      ]
    }
  }
}
```

## 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 50, +42)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [functional regression] Tool coverage: 0 → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Schema quality: unverified → fair
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: unverified
- [functional] Licence: MIT

### 2026-07-31 (score 8, −3)

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

### 2026-07-30 (score 11, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 29)

First indexed and scored.

## MCP tools (7)

### `search_agents` (~82 tokens)

Input parameters:

- `capability` (string): Filter by capability, e.g. "flight-booking"
- `limit` (integer): Max results (default 20)
- `query` (string): Free-text search across name, description, slug
- `tag` (string): Filter by tag, e.g. "travel", "finance"
- `transport` (string): Filter by transport type

### `get_agent` (~24 tokens)

Input parameters:

- `slug` (string, required): The agent slug, e.g. "hermes/booking"

### `search_tools` (~60 tokens)

Input parameters:

- `limit` (integer): Max results (default 20)
- `listingSlug` (string): Restrict to tools belonging to a specific listing (e.g. "modelcontextprotocol/filesystem")
- `query` (string): Free-text search across tool name and description

### `list_tools_for_agent` (~21 tokens)

Input parameters:

- `slug` (string, required): The agent slug to list tools for

### `install_agent` (~17 tokens)

Input parameters:

- `slug` (string, required): The agent slug to install

### `call_agent` (~51 tokens)

Input parameters:

- `body` (string): Request body (for POST/PUT/PATCH)
- `headers` (object): Extra HTTP headers
- `method` (string): HTTP method
- `slug` (string, required): Agent slug to invoke

### `publish_agent` (~192 tokens)

Input parameters:

- `args` (array): For mcp-stdio args
- `capabilities` (array)
- `command` (string): For mcp-stdio, e.g. "npx"
- `description` (string)
- `envKeys` (array): Env vars the installer must set
- `homepage` (string)
- `name` (string, required): Display name
- `pricingAmount` (integer): Cents, for x402 pricing
- `pricingCurrency` (string)
- `pricingModel` (string)
- `pricingPer` (string)
- `readme` (string)
- `repository` (string)
- `slug` (string, required): Unique slug, e.g. "mycompany/booking" (lowercase, hyphens)
- `tags` (array)
- `transport` (string, required)
- `url` (string): For mcp-http / http-x402 / http

## Diagnostics

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

## Score history

- 2026-08-03: 50
- 2026-08-02: 50
- 2026-08-01: 8
- 2026-07-31: 8
- 2026-07-30: 11
- 2026-07-28: 29
- 2026-07-27: 29

## Links

- npm package: https://www.npmjs.com/package/agentmarketplace-mcp
- Socket report: https://socket.dev/npm/package/agentmarketplace-mcp
- Changelog RSS feed: https://verifymcp.io/servers/stevemilton-agentmarketplace-mcp/agentmarketplace-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/stevemilton-agentmarketplace-mcp/agentmarketplace-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/stevemilton-agentmarketplace-mcp/agentmarketplace-mcp