fetchsandbox-mcp

MCPcommunity
v0.5.3FetchSandboxMITUpdated 4d agonpmGitHub

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.

Works in
ClaudeCursorCopilotGemini

Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
790Downloads/wk
1GitHub stars
4d agoLast update
Reads these credentials
  • FETCHSANDBOX_API_KEYAPI keyoptional

    Optional. Sign in without a browser — useful in CI. Left unset, the server runs anonymously and asks you to sign in the first time a run produces a receipt.

Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.

Package
AuthorFetchSandbox
LicenseMIT
Version0.5.3
Sourcenpm+mcp-registry
npmfetchsandbox-mcp
GitHubfetchsandbox/mcp
SBOMCycloneDX 1.6 ↓
Trust Status
B
60/100Good
✓Listed in Forge index+10/10
—Publisher identity verified+0/20
→ Publisher: run `forge publish` from the package repo to claim ownership
—Ed25519 publish signature+0/5
→ Included automatically when the publisher runs `forge publish`
—Domain verification+0/5
→ Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
—npm Trusted Publishing (Sigstore)+0/5
→ Publish from GitHub Actions with --provenance so the attestation binds this package to this repo
—npm maintainer match+0/5
→ Earned once your identity is verified above and that login is an npm maintainer of this package
✓CVE scan · clean+30/30
✓Static analysis · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
Dependencies✓ 60 resolved+ · none vulnerable
Tool surface14 tools · none privileged
Security scan✓ Cleanv0.5.3 · todayHow well does this scan work?
EvalsNone
IndexedSep 14, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

14 tools · none privileged
Statically extracted from the published packagev0.5.3 · 11h ago

Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.

coachConversational integration coach for FetchSandbox. Server-side

Conversational integration coach for FetchSandbox. Server-side

No input schema was published for this tool.

find_bugsFIRST STEP for any API-integration bug — webhooks, payments, auth, email,

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

No input schema was published for this tool.

fix_bugFetchSandbox remediation: get a proposed fix for a specific bug in YOUR

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

No input schema was published for this tool.

guideROUTE a symptom to the provider behaviour that explains it. Use this when

ROUTE a symptom to the provider behaviour that explains it. Use this when

No input schema was published for this tool.

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

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

No input schema was published for this tool.

list_runsList recent workflow runs (and ad-hoc traffic) for a sandbox, newest

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

No input schema was published for this tool.

list_specsBrowse the FetchSandbox spec catalog — every API (Stripe, GitHub,

Browse the FetchSandbox spec catalog — every API (Stripe, GitHub,

No input schema was published for this tool.

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

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

No input schema was published for this tool.

prove_fixTHE PROOF STEP. The only way to establish that a fix actually works, and

THE PROOF STEP. The only way to establish that a fix actually works, and

No input schema was published for this tool.

quickrunRun a curated proof workflow against a KNOWN, bundled spec (stripe, clerk,

Run a curated proof workflow against a KNOWN, bundled spec (stripe, clerk,

No input schema was published for this tool.

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

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

No input schema was published for this tool.

run_workflowExecute ONE specific workflow by name and return its step-by-step trace

Execute ONE specific workflow by name and return its step-by-step trace

No input schema was published for this tool.

submit_proofReceipts are readable by anyone with the link — do not attach bodies the

Receipts are readable by anyone with the link — do not attach bodies the

No input schema was published for this tool.

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

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

No input schema was published for this tool.

14 of 14 tools published a description.

Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.

About

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.

Keywords
mcpmodel-context-protocolverificationagent-verificationintegration-testingwebhook-testingidempotencyapi-sandboxstripepaddleclaudecursoropenapi
Alternatives
Comparing tool surfaces…

Tools exposed

14 tools · none privileged · observed by static extraction. A tool surface is what one scan read on one day, not a live capability list.

Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.

Dependency tree

What one Forge scan resolved from npm metadata on 2026-09-16 — observed resolution, not a publisher declaration.

60 packages resolved · 1 direct · none carrying advisories Resolution stops at depth 4 and 60 packages.

The crawl stopped at the depth-4 limit. Anything below that level was never resolved.

The crawl stopped at the 60-package limit. The rest of the tree was never resolved.

36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)

Declared but not resolved

53 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.

+41 more not listed. The counts by reason above cover all of them.

Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.

Topics

Related in payments & commerce