- Conduid
- Marketplace
- #regression-testing
MCP servers tagged regression-testing
46 live MCP servers tagged "regression-testing", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with regression-testing.
Tracely AI
Trace-native CI/CD for AI agents: grade production traces, cluster failures, freeze them into replayable regression tests, and block PRs that regress. Self-hostable.
Coder Eval
Test that your Claude Code skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, activation checks, A/B experiments, CI gates.
Contract
Contract testing for MCP servers: snapshot your tool surface, then fail CI when a change would break the agents that depend on it. Classifies breaking vs additive vs routing (desc…
Abaqus Agent
AI-driven Abaqus workbench: describe a model in a spec, get a real solved one back. Every capability is backed by a check you can run on your own seat, and the gates refuse a doub…
Eval Gate
CI regression gate for MCP servers: run a golden set of tool calls, diff against a baseline, fail the build when outputs get worse
redline
Zero-infrastructure QA agent — k6 performance + Playwright functional testing with red/green baselines and a deterministic, model-free deploy gate. Clone and run.
Vitest MCP Assert
Vitest integration for mcp-assert: run MCP server assertion YAML files as Vitest tests
Classifier Evals MCP Server
MCP server exposing classifier evaluation tools
Mcpward
Black-box security & contract testing for MCP servers — rug-pull, tool-poisoning, schema-drift & protocol checks for CI (JUnit + SARIF).
Mcpdrift CLI
CI/CD regression tester and snapshot testing tool for Model Context Protocol (MCP) servers
Livekit Agent Simulator
Black-box LiveKit voice agent testing: real WebRTC/SIP calls with an AI caller. Catch barge-in, noise, quiet-mic, and latency failures that text pytest misses. Forensic reports +…
Testivai Oss
Local-first visual regression testing for Playwright, Selenium, WebdriverIO, Python, Java and Ruby. Every screenshot is paired with a DOM and computed-style snapshot, so a diff ar…
Proofseal
Regression memory for coding agents — seal how your repo behaves, then check over MCP (or in CI) that an edit didn't regress it: pass/drift/regressed/missing. With seal history, b…
Mcptracer
Developer preview: local-first MCP traffic recording, replay, diffing, regression testing, and release assurance.
Assertledger
Verify that regression tests catch the bug they claim to prevent. Deterministic, replayable evidence for agent-assisted development.
RedLine
Zero-infrastructure QA agent — k6 performance + Playwright functional testing with red/green baselines and a deterministic, model-free deploy gate. Clone and run.
Complex Ui Tester
CUIT — the deterministic feedback edge for agentic UI engineering. Recorder + harness + spec-gen + data warehouse. complex-ui-tester is the canonical npm/repo name.
Gauntlet
A CI linter for what your MCP server publishes: tool poisoning and prompt injection across every surface an agent sees, definition drift between runs, and schema rot.
Traceplay
VCR-style regression harness for AI agents: record trajectories once, replay offline with zero tokens, and assert behavior in CI.
CompatSentinel
Catch Windows app compatibility regressions before your users do.
Jevitate
Autonomous browser testing that turns discovered bugs into deterministic regression tests. A model may choose what to try; only browser evidence decides pass or fail. CLI + MCP se…
Contract
Contract testing for MCP servers: snapshot your tool surface, then fail CI when a change would break the agents that depend on it. Classifies breaking vs additive vs routing (desc…
Mcpclientcanary
Reproduce native MCP client state regressions with evidence you can inspect.
Proof
MCP server verification toolkit — wire-level protocol conformance, security hygiene, and record/replay contract regression, shipped as a client-ready delivery report plus a CI gat…
Gauntlet
A CI linter for what your MCP server publishes: tool poisoning and prompt injection across every surface an agent sees, definition drift between runs, and schema rot.
Pinnedai
Permanent guardrails for AI-coded apps
Agent Prod
Production AI agent quality gate and risk control framework for LLMOps, agent evaluation, regression detection, gray release, audit, and observability
Behavior
Parity tests for MCP migrations, including tool results and observable side effects.
Claude Code Canary
Regression-test Claude Code releases, plugins, MCP servers and configs with deterministic scenarios, version bisecting and GitHub Actions.
RaceSimQA
QA regression testing tool for 'racing car' type of simulations. Analytics, Data visualisation, LLM chat and AI summary
Eval Harness For Solo Devs
Lightweight CLI + MCP server that lets solo devs run markdown‑based regression tests on any agent, catching silent breaks with instant diffs, cost & latency feedback.
TestTrout
🐟 The testing assistant for coding agents. Reads your repo, connects to your deployment, ranks what's untested, writes real tests, runs them — driven over MCP.
J Rig Skill Binary Eval
Binary-criteria evaluation harness for Claude skills with planned extension to plugins, agents, and MCP servers. Score every change yes/no across 7 layers — package integrity, tri…
Self Test
Automated regression testing for Flutter through direct callback invocation. Test your Flutter apps with AI agents (Claude) using 60+ Playwright-equivalent tools. Works on iOS, An…
Webtest Orch
Token-efficient e2e orchestration skill for Claude Code: explore once, replay deterministically. Playwright + axe-core + run-diff. Tests stay in your repo. MIT.
Agent Invariants
Deterministic behavior contracts for AI agents — preserve approvals, stop semantics, tool scope, recovery, and proof before done.
Yara Detection Harness
Detection-as-code for generated text & code: hand-written YARA rules, a paired synthetic corpus, and a CI harness gating on recall + false-positive rate — plus a VirusTotal enrich…
Staysfixed
Prove that what already worked still works after an agent changed the code. Picture checks, guards for fixed bugs, a pre-release walkthrough and known-good markers — as a CLI and…
Agentrig
Evidence-first regression testing for AI agents: turn production traces into reviewed, replayable cases that gate releases.
Agent Regress
MCP server for regression-testing AI agents — deterministic checks (regex, exact-match, JSON schema, exit code), zero API keys required.
Harnesslab
Record, diff, and gate agent harness behavior as an executable Trace Contract. CI regression tests for lifecycle, tools, approvals, MCP, and adapters.
Stepstitch
Turn a user-reported bug into a runnable Playwright regression test — privacy-safe, no session replay, no PII captured. An open-source, self-hostable evidence layer for regulated…
Agent Reliability Evidence Pack
Public reference fixture, evidence report, and bounded patch for one agent reliability failure
Streamable Http Lifecycle Regressions
Provider-free MCP Python SDK legacy Streamable HTTP lifecycle regression fixtures for issues #3494 and #3503
Openapi Bindcheck
OpenAPI tool-calling regression tests for dropped arguments and parameter-name collisions. Pinned Google ADK, FastMCP, and Open WebUI component reproductions; no LLM calls.
Regression Lab
GitHub Action: catch MCP server releases that silently break agents (tool contract diff, lint, golden tests)