# AgentBodega MCP (npm · @agentbodega/mcp)

Discover AgentBodega paid data tools, contracts, and x402/L402 HTTP payment handoff metadata.

- Trust score: 81/100 (high trust)
- Change this week: −15
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@agentbodega/mcp`: 81/100 (this document), [markdown](https://verifymcp.io/servers/agentbodegastore-agentbodega-mcp/agentbodega-mcp.md), [page](https://verifymcp.io/servers/agentbodegastore-agentbodega-mcp/agentbodega-mcp)

## Channel facts

- Registry: `npm`
- Package: `@agentbodega/mcp`
- Version: `0.1.7`
- 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**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to agentbodegastore/agentbodega).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 27 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 85/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 844 tokens (~93/item across 9 items; 5 tools + 4 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**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 agentbodegastore-agentbodega-mcp -- npx -y @agentbodega/mcp
```

### Codex

```bash
codex mcp add agentbodegastore-agentbodega-mcp -- npx -y @agentbodega/mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add agentbodegastore-agentbodega-mcp --command npx --arg -y --arg @agentbodega/mcp
```

### Hermes

```yaml
mcp_servers:
  agentbodegastore-agentbodega-mcp:
    command: "npx"
    args: ["-y", "@agentbodega/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "agentbodegastore-agentbodega-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@agentbodega/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 81, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-07-31 (score 66, −12)

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

### 2026-07-30 (score 78, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 96, +37)

- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 100
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent

### 2026-07-26 (score 59)

First indexed and scored.

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

## MCP tools (5)

### `agentbodega_plan_task` (~172 tokens)

Plan Cheapest AgentBodega Route

Use this before search_catalog when you have a plain-language task and want AgentBodega to choose the best matching paid route at the lowest useful cost. It calls the free /api/plan planner, returns a recommended endpoint, alternatives, required inputs, examples, and x402 handoff notes. It never executes paid endpoints or creates payments.

Input parameters:

- `budgetUsd` (number): Optional maximum per-call spend for the recommended paid route. The planner itself remains free.
- `limit` (integer): Maximum number of recommendations to return.
- `prefer` (string): Ranking preference for route selection.
- `task` (string, required): Plain-language task to solve with AgentBodega routes, for example: check whether my deploy failure is caused by GitHub, npm, Vercel, Supabase, or OpenAI.

### `agentbodega_search_catalog` (~203 tokens)

Search AgentBodega Catalog

Use this first when you need to choose an AgentBodega paid data endpoint. It fetches the live directory and returns matching endpoint summaries with key, path, price, category, tags, required inputs, and example request. It never executes paid endpoints or creates x402 payments.

Input parameters:

- `department` (string): Optional exact category or tag filter, for example public-data, cloud-status, x402-tools, billing, search, or utility. Leave empty when you do not know the department.
- `limit` (integer): Maximum number of matching endpoint summaries to return. Values are clamped to 1 through 50.
- `maxPriceUsd` (number): Optional maximum per-call price in USD. Use this to find low-cost endpoints before preparing a paid request.
- `query` (string): Optional case-insensitive text search across endpoint key, title, path, descriptions, category, and tags. Use an empty string to list all endpoints before applying filters.

### `agentbodega_get_endpoint` (~148 tokens)

Get AgentBodega Endpoint

Use this after search_catalog when you know the endpoint key, title, path, or URL and need the complete contract before paying. It returns method, URL, price, category, tags, long description, required inputs, input/output schemas, example request, and output example when available. It does not call the paid endpoint.

Input parameters:

- `endpoint` (string, required): Endpoint identifier from search_catalog. Accepts the endpoint key, title, API path such as /api/status/github, or full AgentBodega URL.
- `includeSchemas` (boolean): When true, return the full contract with schemas, examples, and long description. When false, return a compact summary suitable for ranking candidate endpoints.

### `agentbodega_call_snippet` (~110 tokens)

Generate AgentBodega Call Snippet

Use this after selecting an endpoint to prepare an HTTP request an agent or user can run outside MCP. It returns curl and JavaScript snippets with the example JSON body, an X-PAYMENT placeholder, and x402 verification notes. It does not fetch a live 402 challenge, spend funds, or execute the paid call.

Input parameters:

- `endpoint` (string, required): Endpoint identifier from search_catalog or get_endpoint. Accepts the endpoint key, title, API path, or full AgentBodega URL.

### `agentbodega_payment_guide` (~107 tokens)

AgentBodega Payment Guide

Use this when an agent needs to understand how AgentBodega x402 and L402 payment discovery work before making paid HTTP calls. It explains the blockchain-settled per-call model, discovery URLs, balance source of truth, optional owner-approved savings offers, and an optional sample challenge request. It does not validate wallets, issue discounts, or perform payments.

Input parameters:

- `includeCurl` (boolean): When true, include a sample curl command for requesting a live 402 payment challenge.

## Diagnostics

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

## Score history

- 2026-08-03: 81
- 2026-08-02: 81
- 2026-08-01: 66
- 2026-07-31: 66
- 2026-07-30: 78
- 2026-07-29: 96
- 2026-07-28: 96
- 2026-07-27: 96
- 2026-07-26: 59

## Links

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