- EdgeGate @frozo-ai/edgegate-mcpRegression-test AI models on real Snapdragon and Jetson hardware, with signed evidence for CI.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Invigil @invigil/invigilLinters check your code. Invigil checks whether your repo is legible — to newcomers and AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- andon @gulmezeren2-byte/andonDeterministic verification for AI-generated analysis: run a spec, inspect or diff a workbook4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- regressGuard @bharath-code/regressguardDeterministic API regression checks for AI agents: snapshot a baseline, catch broken contracts.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.1 GitHub stars.
- Evidrift @bm1016bm-svg/evidriftCatch TypeScript API and OpenAPI contract drift in AI-generated code, then revalidate it in CI.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- GAUNTLEX @sanjoy1234/gauntlexConcurrent Builder + Breaker agents generate code and adversarial tests at once, gated in CI.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Drone CI/CD MCP Server @yusiwen/drone-mcp-serverMCP server for Drone CI/CD: 45 tools for builds, repos, secrets, users and templates4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- Aiglare @nugehs/aiglareAudit AI/LLM features for governance guardrails: confidence, fallback, validation, human-in-loop.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- bouncer @nugehs/bouncerStatic compliance-controls checker for UK Online Safety Act & ICO Children's Code. CLI + MCP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Deterministic @archradhq/deterministicDeterministic IR/IR-LINT validation, policy packs, drift vs exports (archrad). Apache-2.0.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- ProofSlip @proofslip/mcp-serverReceipt-based verification for AI agent workflows — create, verify, and poll ephemeral proof objects5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Tewip @hmamut39/tewipProves software work: triages failing tests, checks whether a test can fail, and reads migrations.Not assessed yet.Runs on your machine, installed from npm.
- orm-preflight @sikandar100/orm-preflightChecks TypeORM migrations for data loss, table locks, and deploy problems before they run.Not assessed yet.Runs on your machine, installed from npm.
- ClaimGate - claim check before you publish @caseone115/claimgateFlag marketing claims your evidence cannot substantiate, before you publish.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- ClaimGate starter kit - set up a publish gate @caseone115/claimgate-kitSet up a publish gate for AI-assisted marketing copy: policy, evidence folder and CI job.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Depot MCP by usefulapi @usefulapi/depotInspect Depot builds, CI runs, job logs and Actions runners; retry or cancel CI runs.Not assessed yet.A remote server; no sign-in.
- Codemagic MCP by usefulapi @usefulapi/codemagicTrigger and inspect Codemagic CI builds, apps and artifacts.Not assessed yet.A remote server; no sign-in.
- DiffCI @adityankale190895/diffciChange-aware CI validation and affected-test guidance for coding agents.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agentic Ops @wrenk/agentic-opsWrenk — managed Salesforce, ServiceNow & HubSpot operations from your own AI.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- spendtron @swantron/spendtronFinds the GitHub Actions workflow eating your CI bill and suggests fix diffs, verified against runs.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- DiffCI @diffci/diffciFail-closed, change-aware verification for AI coding agents with affected-test guidance.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Rupa3D @tiranyx/rupa3dChecks GLB assets against a spec without Blender and embeds the measured proof inside the GLB.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Django Chainsaw @syrian963/django-chainsaw-mcpFinds what will hurt in a Django project: cascades, N+1, unsafe migrations, tenant leaks.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Shipi18n @shipi18n/shipi18nCheck locale files for broken placeholders, plurals and missing keys. Validators need no API key.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
