# fetchsandbox-mcp

A deterministic eval engine for coding agents. Fires the edge cases your sandbox never sends, then proves a fix: the same scenario fails on the old code and passes on the new.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the package rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 0.5.3
- **Author:** FetchSandbox
- **License:** MIT
- **npm:** fetchsandbox-mcp
- **Source:** https://github.com/fetchsandbox/mcp
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

60/100 (B), scored on the package rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 0 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-09-16T22:54:19.637Z
- **Version scanned:** 0.5.3
- **CVEs:** none found by OSV at scan time

## Tools

14 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `coach` — Conversational integration coach for FetchSandbox. Server-side
- `find_bugs` — FIRST STEP for any API-integration bug — webhooks, payments, auth, email,
- `fix_bug` — FetchSandbox remediation: get a proposed fix for a specific bug in YOUR
- `guide` — ROUTE a symptom to the provider behaviour that explains it. Use this when
- `import_spec` — Ingest an OpenAPI spec and get a working sandbox you can call immediately.
- `list_runs` — List recent workflow runs (and ad-hoc traffic) for a sandbox, newest
- `list_specs` — Browse the FetchSandbox spec catalog — every API (Stripe, GitHub,
- `list_workflows` — List the named, runnable workflows for a previously-imported spec.
- `prove_fix` — THE PROOF STEP. The only way to establish that a fix actually works, and
- `quickrun` — Run a curated proof workflow against a KNOWN, bundled spec (stripe, clerk,
- `run_all_workflows` — Execute EVERY workflow (or a scoped subset) for a sandbox in ONE call.
- `run_workflow` — Execute ONE specific workflow by name and return its step-by-step trace
- `submit_proof` — Receipts are readable by anyone with the link — do not attach bodies the
- `verify_behavior` — Prove a known fix survives a bug — the 'prove' half of reproduce→prove.

## Install

**Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for.
**Cautions** (coverage gaps and advisories — never blocking)
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"fetchsandbox\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"fetchsandbox-mcp\"\n      ],\n      \"env\": {\n        \"FETCHSANDBOX_API_KEY\": \"<YOUR_FETCHSANDBOX_API_KEY>\"\n      }\n    }\n  }\n}"
```
**Credentials it will ask for** (names only — Forge never holds a value):
- `FETCHSANDBOX_API_KEY` — Fetchsandbox API Key (optional)
Placeholders only. Forge never holds, brokers, or transmits a credential value — replace each <YOUR_NAME> in your own config file. Do not send a value back to Forge; no Forge endpoint accepts one.
- This entry needs 1 credential (0 required). The generated config carries placeholders, so it will fail in the editor rather than at runtime if they are left unset.

## Blast radius

Moderate blast radius — holds an api key; runs on your machine.
- Floor 23, ceiling 23 (tier: moderate)
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/fetchsandbox-mcp
- Install plan: https://forgeregistry.com/api/v1/packages/fetchsandbox-mcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/fetchsandbox-mcp
- HTML page: https://forgeregistry.com/registry/fetchsandbox-mcp
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.