API Tools

fetchsandbox.com

Helps developers find, diagnose, and fix API integration bugs across webhooks, payments, auth, email, SMS, and subscriptions.

1 endpoint16 known toolsFirst detected June 5, 2026Last detected September 13, 2026

ENDPOINT 1

https://fetchsandbox.com/mcp/v1

No auth detected

MCP server metadata

Name: fetchsandbox
Version: 0.5.6

Capabilities

tools

Known tools 16

coach

Conversational integration coach for FetchSandbox.

Inferred read-only

find_bugs

FIRST STEP for any API-integration bug — webhooks, payments, auth, email, SMS, subscriptions.

Potential side effects

fix_bug

FetchSandbox remediation: get a proposed fix for a specific bug in YOUR code.

Inferred read-only

prove_fix

THE PROOF STEP.

Inferred read-only

guide

ROUTE a symptom to the provider behaviour that explains it.

Inferred read-only

quickrun

Run a curated proof 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.

Inferred read-only

list_specs

Browse the FetchSandbox spec catalog — every API (Stripe, GitHub, Twilio, Notion, OpenAI, Polar, GitLab, and 40+ more) that has a ready-to-use sandbox with curated workflows.

Inferred read-only

import_spec

Ingest an OpenAPI spec and get a working sandbox you can call immediately.

Inferred read-only

list_workflows

List the named, runnable workflows for a previously-imported spec.

Inferred read-only

run_all_workflows

Execute EVERY workflow (or a scoped subset) for a sandbox in ONE call.

Potential side effects

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.

Potential side effects

verify_behavior

Prove a known fix survives a bug — the 'prove' half of reproduce→prove.

Inferred read-only

submit_proof

Receipts are readable by anyone with the link — do not attach bodies the user would not paste into a public PR.

Inferred read-only

list_runs

List recent workflow runs (and ad-hoc traffic) for a sandbox, newest first.

Inferred read-only

list_scenarios

List the FAILURE SCENARIOS this sandbox can inject on demand — the specific ways the real provider misbehaves in production.

Inferred read-only

set_scenario

ARM a failure scenario on a sandbox, so the next requests hit the provider misbehaving instead of the happy path.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.fetchsandbox]
url = "https://fetchsandbox.com/mcp/v1"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "fetchsandbox": {
      "type": "http",
      "url": "https://fetchsandbox.com/mcp/v1"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: fetchsandbox
Remote MCP URL: https://fetchsandbox.com/mcp/v1

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "fetchsandbox": {
      "url": "https://fetchsandbox.com/mcp/v1"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "fetchsandbox": {
      "type": "http",
      "url": "https://fetchsandbox.com/mcp/v1"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "fetchsandbox",
  "transport": "streamable-http",
  "url": "https://fetchsandbox.com/mcp/v1"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.