Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

SandboxAPIs

NPM · @SANDBOXAPIS/MCP · SCANNED SEP 20

Drop-in read-only replicas of GitHub, Jira, Slack and 18 more, preloaded with one fake company.

Available components

62 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
Schema Quality & AI Usability72
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 757 tokens (~75/item across 10 items; 10 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage75
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 26% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Install

How do I install the SandboxAPIs MCP server?

SandboxAPIs runs locally as an npm package, launched with npx -y @sandboxapis/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @sandboxapis/mcp

# add to Claude Code
claude mcp add dev-sandboxapis-mcp -- npx -y @sandboxapis/mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "dev-sandboxapis-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@sandboxapis/mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "dev-sandboxapis-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@sandboxapis/mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add dev-sandboxapis-mcp -- npx -y @sandboxapis/mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-sandboxapis-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@sandboxapis/mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add dev-sandboxapis-mcp --command npx --arg -y --arg @sandboxapis/mcp
# ~/.hermes/config.yaml
mcp_servers:
  dev-sandboxapis-mcp:
    command: "npx"
    args: ["-y", "@sandboxapis/mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "dev-sandboxapis-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@sandboxapis/mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add dev-sandboxapis-mcp -t stdio -c npx -a -y @sandboxapis/mcp
// mcp.json
{
  "mcpServers": {
    "dev-sandboxapis-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@sandboxapis/mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 62

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/@sandboxapis/mcp@0.3.13

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 96 packages
Packages resolved 96
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 10 exposed · ~683 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
check_budget ~126

Costs nothing — call it before any loop of more than a handful of requests. Returns this server's real hourly window (limit, remaining, when it resets) read from the provider's own budget endpoint, which is exempt from the budget it reports, plus whether a key is set and where to raise the limit. The window is ONE bucket per caller shared across every provider host, so the numbers apply to all of them.

NameTypeReqDescription
providerstringThe host you are about to call. Optional — the budget is one shared window, so the numbers are the same for every provider.

No output schema declared.

No examples provided.

get_pull_request ~72

Fetch one PR (GitHub) / MR (GitLab) plus its reviews (GitHub) / approvals (GitLab). Returns both in one result; each carries provider-form ids for cross-referencing.

NameTypeReqDescription
numberintegeryes
providerstringyes
repostring

No output schema declared.

No examples provided.

get_repository ~58

Fetch one repository by name (default: the flagship repo). Provider-shaped, with provider-form ids.

NameTypeReqDescription
providerstringyes
repostringRepo name, e.g. 'parthenon'. Defaults to the flagship repo.

No output schema declared.

No examples provided.

get_snapshot ~49

Return the pinned, reproducible hostname for a provider — point your client's base URL at it for drift-free CI. A snapshot regenerates byte-identically on every request.

NameTypeReqDescription
providerstringyes

No output schema declared.

No examples provided.

get_user ~50

Fetch a user by login/username. Provider-shaped, with provider-form ids.

NameTypeReqDescription
loginstringyesThe user's login (GitHub) / username (GitLab).
providerstringyes

No output schema declared.

No examples provided.

list_issues ~45

List a repo's issues. Optional state filter (open/closed/all).

NameTypeReqDescription
providerstringyes
repostring
statestring

No output schema declared.

No examples provided.

list_pull_requests ~54

List a repo's pull requests (GitHub) or merge requests (GitLab). Optional state filter.

NameTypeReqDescription
providerstringyes
repostring
statestringProvider state filter.

No output schema declared.

No examples provided.

list_repositories ~45

List repositories for the universe's org. Results are identical to the provider's REST API and carry provider-form ids (node_id / numeric id).

NameTypeReqDescription
providerstringyes

No output schema declared.

No examples provided.

orient ~98

START HERE. Returns everything needed to use SandboxAPIs with no docs: the universe/theme, every API surface and its base URL (git hosts and issue trackers), live-vs-snapshot modes and how to pin, the org and its teams/repos, notable entry points (each with a ready-to-run REST path), where the coverage manifest lives, and this server's access block — whether a key is set and how many requests are left this hour.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

search_commits_by_author ~86

Find commits authored by a given login in a repo. Returns SHAs (identical across GitHub and GitLab, invariant #5) with a REST path to fetch each — so you can cross-reference against either provider.

NameTypeReqDescription
authorstringyesAuthor login, e.g. 'athena'.
providerstring
repostring

No output schema declared.

No examples provided.

Common questions

What is the SandboxAPIs MCP server?

SandboxAPIs is an MCP server listed in the public MCP registry as dev.sandboxapis/mcp. Drop-in read-only replicas of GitHub, Jira, Slack and 18 more, preloaded with one fake company. This page covers its npm package (@sandboxapis/mcp).

Is the SandboxAPIs MCP server safe to use?

SandboxAPIs scores 62 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the SandboxAPIs MCP server expose?

SandboxAPIs exposes 10 tools: orient, check_budget, list_repositories, get_repository, list_pull_requests, and 5 more. Their descriptions and schemas cost roughly 683 tokens of context every time the server is loaded.

Is the SandboxAPIs MCP server still maintained?

SandboxAPIs is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the SandboxAPIs MCP server under?

SandboxAPIs declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.