AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
MCP verified Apache-2.0 Self-run

Glubean

mcp-glubean-glubean · by glubean

Workflow verification platform — write API tests in TypeScript, run locally or in CI, let AI agents write and repair them

No reviews yet
0 installs
22 views
0.0% view→install

Install

$ agentstack add mcp-glubean-glubean

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/mcp-glubean-glubean)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude DesktopCursorWindsurf

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Glubean? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Glubean

API quality layer: functional correctness tests and load performance tests in the same TypeScript project, with AI agents that write, run, and repair them.

[](https://www.npmjs.com/package/@glubean/sdk) [](https://github.com/glubean/glubean/actions/workflows/ci.yml) [](LICENSE)

npx glubean config mcp        # AI agent can run and inspect tests
npx skills add glubean/skill   # AI agent learns Glubean patterns
"write a smoke test for /users"
"migrate our Postman collection"
"design the billing API contracts before I build it"
"run a load test and show me p95 latency per endpoint"

The agent writes the test, runs it via MCP, reads the structured failure, fixes it, and reruns — in one conversation.

Two ways to use it

API already exists? Point the agent at your API. It writes tests that run, break, get repaired, and graduate from explore/ to tests/ to CI. Add a load plan alongside to track performance over time.

API doesn't exist yet? Describe what it should do. The agent writes executable contracts in contracts/ — the implementation must satisfy them. After you build the API, the same contracts become your regression tests and can seed load scenarios.

Quick start

npx glubean init      # interactive wizard: try, test existing API, or contract-first
npx glubean run       # run tests
npx glubean load      # run load plans (discover *.load.ts, write structured artifacts)
npx glubean login     # authenticate with Glubean Cloud (browser device flow)

Or with AI:

npx glubean config mcp
npx skills add glubean/skill

Then ask your agent anything — it writes, runs, reads structured failures, and fixes in a loop.

VS Code extension

The extension serves two roles:

  1. Postman replacementexplore/ is your API collection in code. Click the gutter play button to send a request, see full response in the result viewer. Save parameter sets with test.pick, share via git. No Postman account, no per-seat pricing.
  2. Visual layer for test results — run from gutter or Test Explorer, inspect structured traces, debug with typed expected vs actual.

Same TypeScript file works as both API collection entry and CI regression test. No export, no conversion.

Packages

| Package | What it does | |---------|-------------| | [@glubean/sdk](packages/sdk) | Author tests — test(), configure(), assertions, builder flows | | [@glubean/sdk/load](packages/sdk) | Author load plans — loadScenario(), loadRunner(), traffic-mix, feeders | | [@glubean/cli](packages/cli) | Run tests and load plans, manage environments, init projects | | [@glubean/engine](packages/engine) | Environment-agnostic run-loop core (Node runner + browser host) | | [@glubean/runner](packages/runner) | Test and load executor | | [@glubean/scanner](packages/scanner) | Static analysis for IDE integration | | [@glubean/mcp](packages/mcp) | MCP server — agents run and inspect tests | | [@glubean/redaction](packages/redaction) | Sensitive data redaction |

Plugins

| Plugin | Protocol | |--------|----------| | [@glubean/auth](packages/auth) | Bearer, API key, OAuth 2.0 | | [@glubean/browser](packages/browser) | Browser automation (Puppeteer) | | [@glubean/graphql](packages/graphql) | GraphQL queries and mutations | | [@glubean/grpc](packages/grpc) | gRPC unary calls | | [@glubean/oauth-code](packages/oauth-code) | OAuth Authorization Code flow for explore mode |

Links

Contributing

Bug reports, feature requests, and pull requests are welcome — see [CONTRIBUTING.md](CONTRIBUTING.md). Security issues go through [private vulnerability reporting](SECURITY.md), not public issues.

License

[Apache-2.0](LICENSE)

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.