MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP server for training Linear Regression Model.
★ 12 -
Lastest Visual Regression Testing - Cloud/Self-hosted version
NOASSERTION ★ 22 -
RaceSimQAgithub.com/alxliv/RaceSimQAupdated this year
QA regression testing tool for 'racing car' type of simulations. Analytics, Data visualisation, LLM chat and AI summary
MIT -
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, bisection, and staleness queries.
npm MIT ★ 5 -
@kalisky/skargithub.com/kalisky/skarupdated this year
Skar turns a captured AI agent trace into a committed pytest regression test. MCP server + CLI. Use when a tool-using agent run fails and you want to lock the failure as an executable test.
npm MIT -
Regression-Aware Context Compaction & Witness Replay for Coding Agents (CEGAR-Harness)
MIT -
Compare OpenTelemetry traces across releases, gate latency and error regressions in CI, and inspect the evidence through MCP. Built with Kotlin and SQLite.
MIT ★ 1 -
MCP server for visual regression and interactive design review.
npm SEE LICENSE IN LICENSE -
MCP server for frontend UI debugging — component inspection, visual regression, a11y auditing, and session replay via CDP
npm MIT -
Witness — browser acceptance checks for agent-built web apps. CLI, MCP, AI-drafted checklists, visual regression, and multi-browser reports.
npm MIT -
Prompts shouldn't deploy on hope. This MCP interface catches prompt regressions against labeled edge cases and forces human-in-the-loop release authority.
MIT -
CARBON AI testing harness with Jay: risk-based software testing, exploratory and regression checks, accessibility, triage, and local evidence reports via MCP.
npm MIT -
@mukundakatta/agentsnap-mcpgithub.com/mukundakatta/agentsnap-mcpupdated this year
MCP server: snapshot tests for tool-call traces. Capture, normalize, and diff agent tool-use traces to catch silent regressions. Wraps @mukundakatta/agentsnap for Claude Desktop, Cursor, Cline, Windsurf, and Zed.
npm MIT -
Give your AI agent eyes (screenshot live pages), ears (Sentry/Datadog/Rollbar errors + runtime checks), hands (verify fixes worked), and root-cause tools (source-map trace resolution, git regression blame), and debug tools (run tests, stream logs, query y
npm MIT -
Risk-feature mining toolkit for customer-level wide tables: adaptive-binning IV/WOE, segment logistic regression, decision-tree rule mining, customer trigger scanning and Word reports, plus an LLM indicator agent and MCP server. Synthetic/public data only.风险特征挖掘流水线
MIT -
Nextflow plugin for cross-run benchmarking. Records per-process metrics for every run into a local or shared history store, compares runs against their own history, and flags regressions with likely causes, over-provisioned resources, and retries. Includes a zero-dependency dashboard, an MCP server for AI assistants, and opt-in AI narration.
Apache-2.0 ★ 1 -
Eval-driven SQL reliability for AI agents — generate, validate, safely execute, and regression-test LLM SQL. MCP + FastAPI gateways, execution-truth evals, CI regression gate.
MIT ★ 3 -
Regression testing for LLM applications in CI. Sample your reference and a score drop is read against how much that score moves on its own. A flip from pass to fail is always a regression. Python CLI, pytest plugin, MCP server.
pypi Apache-2.0 ★ 10 -
evalbenchgithub.com/cognis-digital/evalbenchupdated this year
Offline LLM / agent eval harness with regression gates
NOASSERTION -
Agent observability MCP server for querying OpenTelemetry traces, failures, tool health, security evidence, and regressions.
pypi MIT -
MCP server for EdgeGate — set up edge-AI regression gates from Claude Code, Cursor, or Claude Desktop.
npm MIT ★ 1 -
Capture local AI agent traces and inspect failures, approvals, token usage, and run regressions through MCP.
MIT ★ 1 -
superbasedgithub.com/marmutapp/superbasedupdated this year
Screenshot capture, AI analysis, OCR, visual regression testing, token compression — headless server + MCP tools for AI coding CLIs
npm ISC -
MCP server for EdgeGate — set up edge-AI regression gates from Claude Code, Cursor, or Claude Desktop.
npm MIT -
gasprofilergithub.com/cognis-digital/gasprofilerupdated this year
Per-opcode and per-function gas profiler that flags unbounded loops, DoS-prone patterns, and regressions against a committed baseline.
NOASSERTION -
Connect your coding agent to Serpkin: sign in, register your site, upload its route map, and check pull-request previews for SEO regressions.
npm MIT -
A comprehensive MCP (Model Context Protocol) server providing 40+ statistical analysis tools forAI assistants. Supports descriptive statistics, hypothesis testing, regression analysis, and advanced statistical computations using NumPy and SciPy.
★ 3 -
screentest-mcpgithub.com/marilynceo/screentest-mcpupdated this year
Visual testing for AI agents u2014 screenshot capture, pixel-perfect diff, baseline management, element detection, layout analysis. 7 tools: capture_screenshot, compare_screenshots, set_baseline, check_regression, detect_elements, analyze_layout, batch_test.
-
MCP server for Framedash game telemetry: query game analytics, heatmaps, perf regressions, retention, and alerts from Claude and other AI agents
npm MIT -
Code-aware browser testing for AI coding agents. 14 MCP tools, CLI workflows, regression memory, and human-readable QA reports.
npm MIT ★ 18 -
MCP tools that help coding agents test web apps systematically, find bugs, and deliver evidence-backed reports and regression tests for supported findings.
MIT ★ 7 -
wireforge-coregithub.com/hanmahong5-arch/wireforge-coreupdated this year
Local-first toolkit for financial wire messages: SR2026 structured-address CI gate, MT/MX truncation detector, ISO 8583 codec, migration regression evidence. CLI + 12 read-only MCP tools.
Apache-2.0 -
r-stats-skillsgithub.com/kaito41418-ux/r-stats-skillsupdated this year
Ten Claude Code skills for rigorous statistical analysis (regression, ANOVA, factor analysis, survival, time-series, multivariate, etc.) — delivered as Word (.docx) reports. Includes MCP server.
MIT ★ 1 -
flowlens-mcp-servergithub.com/magentic/flowlens-mcp-serverupdated this year
FlowLens is an open-source MCP server that gives your coding agent (Claude Code, Cursor, Copilot, Codex) full browser context for in-depth debugging and regression testing.
Apache-2.0 ★ 109 -
anchorgithub.com/pratik7368patil/anchorupdated this year
Local-first MCP server that gives AI coding agents repo and org memory from GitHub PR history, code, tests, regressions, architecture, and cross-repo impact.
MIT ★ 2 -
Roslyn analyzer, .NET CLI and MCP server for C# complexity analysis. Estimates Big-O, detects costly patterns, measures code metrics, and compares snapshots to identify complexity regressions.
MIT ★ 4 -
argusqa-osgithub.com/ironclawdevs27/argusupdated this year
Argus — the QA layer for AI-assisted development. Claude-native (MCP) Chrome audits across 67 categories — errors, visual regressions, a11y, security, performance — no test files, secrets redacted by default (Aegis).
npm MIT -
rigorgithub.com/mrnh/rigoractive
Verified statistical inference for AI agents -- classical and non-parametric hypothesis testing, correlation/regression, effect sizes, power/sample-size, multiple-comparisons correction, a test-recommendation helper, and a batch pairwise-comparison tool, as a CLI and an MCP server
MIT ★ 1 -
@mobilepixel/mcpgithub.com/mrtrotskiy/mobilepixelupdated this year
AI-powered MCP server for mobile testing: 20 free tools for iOS & Android automation via Claude/Cursor. Natural language commands, Appium-based, npx ready. Pro adds OCR, visual regression, parallel execution.
npm Apache-2.0 -
Agent Skills + MCP servers for AI coding agents (Claude Code, GitHub Copilot, Codex, Cursor, Gemini CLI): bug analysis, regression tracing with git bisect, proven fixes, security audit, APK reverse engineering, ticket reading.
MIT ★ 1 -
crispy-profiling: React re-render profiler and snapshot tests. Finds unnecessary re-renders, explains why, and fails CI on regressions. CLI, MCP server and Agent Skill.
npm MIT -
Benchmark the full voice-AI pipeline on your own audio — STT (batch + streaming), LLM TTFT, speech-to-speech, and TTS. WER by failure mode, keyterm recall, real-time-paced latency, cost columns, a CI regression gate, and an MCP server for coding agents.
MIT ★ 1 -
Taichi is a language-agnostic, plugin-driven test orchestration framework — run API, gRPC, UI, static, and regression tests with one CLI, extend via third-party skill plugins in any language, integrate AI agents for auto-fix loops, and ship JUnit/JSON/HTML reports.
Apache-2.0 ★ 1 -
wpa-mcpgithub.com/tooluse-labs/wpa-mcpupdated this year
C# MCP server exposing Windows ETW (.etl) trace analyzers — CPU, scheduler waits, image loads, file/disk/mmap/network I/O, memory resources, CLR runtime — over Claude Code, Codex, and other MCP clients. Common uses: app startup, slow process creation, AV/EDR stalls, disk regressions.
Apache-2.0 ★ 18 -
Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.
npm NOASSERTION ★ 857 -
Federal Registerno update data
MCP server for the Federal Register. Track proposed rules, final rules, notices, executive orders, FAR cases, and comment periods. Searches Federal Register documents since 1994 with full-text and metadata filters. Includes comment period tracking and FAR case history workflows for monitoring acquisition policy changes. **8 tools.** No authentication required. Hardened across 5 audit rounds with 182 regression tests. Built for GS-1102 contracting officers and regulatory analysts.
smithery -
A flight recorder for AI agents: records every step, ranks the step most likely at fault, then proves it by replaying the run with only that step repaired, at zero model calls. Top-1 0.60 on unseen failures against 0.25 baselines. MCP server, CI regression firewall, on PyPI.
MIT -
An AI tech lead in server form—this intelligent MCP agent validates your coding agent's strategy, analyzes impact, and catches critical issues before any code is written. Like having a senior engineer review every approach, ensuring thoughtful architecture and fewer regressions.
MIT ★ 7 -
eCFRno update data
MCP server for the Electronic Code of Federal Regulations (eCFR). Read FAR, DFARS, and all agency FAR supplements with point-in-time version history. Provides FAR clause lookups, DFARS lookups, agency FAR supplement access, version history, and full-text CFR search across all 50 titles. Updated daily from the source of record. **13 tools.** No authentication required. Hardened across 6 audit rounds with 240 regression tests. Built for GS-1102 contracting officers and acquisition policy researchers.
smithery -
Claude Code QA agent with memory, plus a read-only MCP server (verdict-qa-mcp on PyPI): baseline → delta runs (NEW/REGRESSED), a fact harness so the model judges while the system measures, hash-chained run history, flaky quarantine with expiry, and an exit-code release gate for CI. Ships six scored eval fixtures — misses published.
MIT ★ 4 -
GSA Per Diemno update data
MCP server for GSA Per Diem Rates. Federal travel lodging and M&IE rates for IGCEs, travel CLINs, and contractor travel cost estimation. Look up rates by city, state, or ZIP across all CONUS locations. Returns monthly lodging rates with seasonal variations, M&IE breakdowns, and first/last day travel rates at 75%. **6 tools.** Optional free api.data.gov key for 1,000 req/hr. Without a key, falls back to DEMO_KEY at 30/hr, 50/day. Hardened across 7 audit rounds with 413 regression tests including two live audits. Built for GS-1102 contracting officers and proposal pricing teams.
smithery -
Standalone MCP server for SnapDiff
MIT ★ 5 -
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 as an MCP server.
MIT -
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 as an MCP server.
npm MIT -
DiffiCat clients: CLI, GitHub Action, Claude Code plugin and MCP setup
MIT -
difflens-cligithub.com/byzkhan/difflensupdated this year
MCP server that gives AI coding agents visual diff capabilities for UI work
npm MIT -
Catch the moment your AI agent drifts from its rules.
MIT -
qaclawgithub.com/vlddlv/qaclawupdated this year
Autonomous QA agent - runs browser-based tests via MCP
npm MIT -
telco-mcp-servergithub.com/rashad-malik/telco-mcp-serverupdated this year
This project demonstrates how to build an MCP server that bridges AI assistants with data analysis and machine learning capabilities.
-
Playwright browser automation for AI agents — screenshots, GIF/MP4/WebP recording, JSON feedback sidecar, MCP server.
pypi MIT