Skip to main content
Glama
Benighter

ReleaseGuard AI

by Benighter

ReleaseGuard AI

ReleaseGuard AI is an evidence-first release readiness agent for the Alexa+ primary track and AWS Builder mini-challenge of the 2026 Amazon Build, Ship, Shape Hackathon.

Watch the 1:52 demo · View the submitted Devpost project

Ask: “Is version 2.8 safe to release?” ReleaseGuard runs or accepts concrete build, API, browser, visual, performance, and security evidence; groups related regressions; and returns a defensible SHIP, REVIEW, or HOLD recommendation.

ReleaseGuard AI architecture

What works

  • Self-hosted MCP server over Streamable HTTP at /mcp

  • MCP 2025-11-25 compatibility, plus the SDK's 2026 protocol support

  • assess_release MCP tool with structured evidence and output

  • run_demo_release MCP tool with a real allowlisted API and Playwright journey

  • Deterministic failure clustering and release decision

  • Evidence dashboard with a real HOLD-to-SHIP demo

  • Optional Amazon Bedrock narrative through the AWS SDK Converse API

  • Origin validation on the MCP endpoint

  • Target allowlisting, browser timeout, console capture, and screenshot evidence

ReleaseGuard deliberately does not expose arbitrary shell execution through MCP. New repositories and CI providers are added as reviewed project adapters.

Related MCP server: blop

Run locally

Requirements: Node.js 20 or newer.

npm install
npm run dev

Open http://127.0.0.1:3210.

  1. Select Run failing RC.1. A real API check receives HTTP 500, Playwright finds the checkout button disabled, and ReleaseGuard returns HOLD.

  2. Select Verify fixed RC.2. The API returns HTTP 201, the browser completes checkout, and ReleaseGuard returns SHIP.

MCP endpoint: http://127.0.0.1:3210/mcp

The server exposes:

  • assess_release — assess structured evidence from CI or another agent.

  • run_demo_release — run the included, bounded release-candidate demo.

Optional Bedrock integration

ReleaseGuard's verdict is deterministic and never delegated to a model. When enabled, Amazon Bedrock adds a concise narrative grounded in the generated report.

  1. Copy .env.example values into your environment.

  2. Configure AWS credentials through the normal AWS credential chain.

  3. Set RELEASEGUARD_USE_BEDROCK=1 and a model available to your account.

The runtime integration is implemented in src/bedrock.ts with BedrockRuntimeClient and ConverseCommand.

Verify

npm run check
npm start
# in another terminal
npm run smoke:mcp

Safety model

  • Decisions cite only checks supplied to the assessment.

  • No arbitrary commands, repository writes, deployment actions, or release actions are exposed.

  • Browser/build execution uses named project adapters and explicit budgets.

  • A SHIP recommendation is advisory; ReleaseGuard does not publish a release.

Hackathon requirements tracked

  • Primary: Alexa+ — self-hosted MCP server, MCP 2025-11-25+, Streamable HTTP

  • Mini-challenge: AWS Builder — documented Amazon Bedrock runtime integration

  • Apache-2.0 open-source license

  • Architecture diagram and verified screenshots in docs/

  • Product feedback and friction log in docs/

License

Apache-2.0. See LICENSE.

Related MCP Connectors

Related MCP Servers

  • A
    license
    B
    quality
    B
    maintenance
    MCP-native release confidence control plane that turns browser execution into auditable go/no-go decisions by combining business-critical journey context, evidence-heavy QA runs, and risk governance.
    28
    1
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    An evidence-first integration decision service that assesses GitHub repositories and returns transparent scores, adoption recommendations, and verification gates.
    MIT
  • A
    license
    B
    quality
    B
    maintenance
    Enables AI clients to analyze software test results and defect records, producing explainable GO, CONDITIONAL_GO, or NO_GO release-readiness recommendations with deterministic risk scoring, failed-test retrieval, defect hotspot ranking, and regression test planning.
    4
    MIT