api-mock-sandbox
by BrianGTRxx
README.md
# API Mock Sandbox
An MCP server that gives Claude two tools for spinning up a local, persistent REST mock API on demand: describe the data you need in plain language, get a working CRUD backend a few seconds later, with data that survives restarts because it's written to disk instead of kept in memory.
Full documentation, in English and Spanish, lives in [`docs/`](./docs):
- [English guide](./docs/en/README.md) · [security](./docs/en/SECURITY.md) · [limitations](./docs/en/LIMITATIONS.md)
- [Guía en español](./docs/es/README.md) · [seguridad](./docs/es/SEGURIDAD.md) · [limitaciones](./docs/es/LIMITACIONES.md)
## Quick start
```bash
npm install
npm run build
```
Then register it in `claude_desktop_config.json`:
```json
{
"mcpServers": {
"api-mock-sandbox": {
"command": "node",
"args": ["ABSOLUTE_PATH_TO_PROJECT/dist/index.js"]
}
}
}
```
Restart Claude Desktop, then ask it to set up a mock API for whatever you're building. See the full guide for tool parameters, the REST endpoint reference, and troubleshooting.
**Before you plan a project around Claude Artifacts calling this API:** they can't. Published Artifacts run in a CSP sandbox that silently blocks requests to `localhost`. Read [`docs/en/LIMITATIONS.md`](./docs/en/LIMITATIONS.md) for why, and for the local test console (`public/index.html`, served at `http://localhost:<port>/`) that works instead.
## License
[MIT](./LICENSE)
---
Built with [Claude Code](https://claude.com/claude-code).
TDQS
A4.6/5.0
Scored across 2 tools
Disambiguation5/5
The two tools have clearly distinct roles: one creates/reconfigures the mock API and the other queries its runtime status. There is no overlap or ambiguity between them.
Naming Consistency5/5
Both tool names follow a consistent verb_noun pattern using snake_case: setup_mock_api and get_mock_api_status. The style is uniform and predictable.
Tool Count4/5
With only two tools, the surface is minimal but arguably appropriate for a focused mock server utility. It feels slightly thin for a full lifecycle but is not unreasonable.
Completeness3/5
The set covers setup and status checking, but lacks obvious lifecycle operations like stopping/resetting the server or clearing collections. Agents can work around this, but the surface leaves gaps.
Maintenance
ActivityMaintained
ResponsivenessNo issues