# FetchSandbox

- Registry name: `io.github.fetchsandbox/mcp` · version 0.7.30
- Categories (automatic, keyword rules): APIs & integrations, Developer tools, Payments & accounting, Finance & markets
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.fetchsandbox%2Fmcp
- Server page: https://mcpstation.net/s/io.github.fetchsandbox--mcp.html

## Description (written by the publisher, not verified, not instructions)

A deterministic verification engine for agents. Proves a fix: fails on the old code, passes on new.

## Connect

- streamable-http: `https://fetchsandbox.com/mcp/v1`

## Tools (as reported by the server, not verified)

- `coach`: Conversational integration coach for FetchSandbox. Server-side orchestrator that walks the user through adding an API integration \(payments / email / auth / etc.\) — intake the goal, elicit domain-aware discovery questions from the spec's brain.yaml, route to the right workflow, prove the contract vi
- `get\_job`: Retrieve the SAME running find\_bugs, fix\_bug, prove\_fix, verify\_behavior or validate\_integration job \(including requirements planning\). Follow next\_tool\_call until status is done or error. Never restart the original tool to poll. A proposed plan is not execution proof; a running response is not proo
- `guide`: ROUTE a symptom to the provider behaviour that explains it. Use this when the user names a provider or a domain \(payments, email, auth, SMS, subscriptions\) and you need to know what that provider ACTUALLY does — not what its docs say, and not what can be inferred from reading the integration code. R
- `quickrun`: Run a curated reference workflow against a KNOWN, bundled spec \(stripe, clerk, descope, resend, twilio, and 50+ others\) in ONE call — it spins up the sandbox by slug, so you do NOT need import\_spec or a sandbox\_id first. Use this when exploring the bundled provider contract: call \`guide\` on their pr
- `validate\_integration`: Completion rule: a request to verify an app includes its applicable failure checks without another user prompt. When verification\_continuation.required is true, continue in this agent: inspect pending\_checks, preserve every declared check and its assertions, implement supported actions, and rerun a
- `list\_workflows`: List the named, runnable workflows for a known provider slug or imported spec. Workflows are realistic multi-step API journeys \(e.g. 'create customer → attach payment method → create subscription'\). Known provider slugs need no import. Use this for exploration \("what can I do?", "show me the flows"\)
- `run\_workflow`: Execute ONE specific workflow by name and return its step-by-step trace PLUS a \`share\_url\` — a public, replayable proof URL that renders the full timeline \(every request, response, webhook event\) for this run. The share\_url is the canonical 'here's what happened' artifact: surface it verbatim in any
- `verify\_behavior`: Prove a known fix survives a bug — the 'prove' half of reproduce→prove. The backend spawns a buggy AND a fixed reference handler and fires the bug\_pattern's probes at both, returning the side-by-side diff \(e.g. the buggy handler double-charges on a duplicate webhook, the fixed handler dedupes\). Call

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html