"Open source MCP (Model Context Protocol) implementations" matching MCP servers:

Enables reproducible evaluation of AI agents on multi-source evidence investigation tasks, providing Docker-based scenarios, MCP tools, and automated scoring for payout reconciliation, performance-claim verification, and incident reconstruction.

Conformance test harness for Model Context Protocol servers, validating JSON-RPC, transport, capability, schema, and more across multiple spec versions.

Enables AI assistants to generate and statically verify IEC 61131-3 Structured Text logic, mutate .csp/.cpj OLE2 project containers, trigger in-GUI Error Check compilation, manage HMI screens, and run deterministic OCS scan-cycle simulations and Modbus telemetry scaling against Cscape 10.2. All physical hardware and firmware-download paths are intercepted fail-closed, so commissioning must be performed manually by authorized field personnel.

Enables inspecting ONNX models, probing the deployment environment, and benchmarking inference latency and FPS either locally or on remote SSH targets such as Linux workstations and Jetson devices. Benchmark results are validated against FPS, P95 latency and model-size constraints to produce PASS/FAIL deployment gates.

Enables running the same prompt(s) across roughly 300 models from Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, Qwen and others, then comparing per-model outputs, latency, token usage, error rates and billed cost side by side. Supports free cost estimates before launching, asynchronous run creation with status polling and cancellation, prepaid x402 credit top-ups, and an optional AI-written comparison summary of the results.

AI-powered code review tool that detects AI-generated code defects invisible to traditional linters — hallucinated packages, deprecated APIs, cross-file contradictions, hidden security anti-patterns, and over-engineering. Works as a standalone CLI, GitHub Action, or MCP server. Supports TypeScript, Python, Java, Go, and Kotlin. Free for individuals, no API key required.

MCP server for Godot Engine enabling AI to autonomously develop, test, and debug games with deterministic playtesting, multiplayer testing, DAP debugging, LSP integration, and token efficiency.

An MCP server for mobile automation that enables LLMs to interact with Android and iOS devices through screenshot, tap, swipe, log analysis, and app lifecycle management.

A local MCP server that lets Claude Code and Codex delegate repository exploration and test proposals to a remote LM Studio model, while enforcing security boundaries by keeping all repository access read-only and never applying patches or running commands remotely.

Enables MCP-compatible clients to discover API endpoints from OpenAPI/Swagger specs, send HTTP requests, validate responses, and analyze status codes for automated API testing.

ModelSafetyMCP is an MCP server for scanning machine learning model artifacts for unsafe serialization, malicious model patterns, risky packaging, URL-based artifact scanning, and directory-level triage.

A server implementation of the Model Context Protocol (MCP) for managing development workflow with features like project management, task tracking, and QA review support.

Enables AI agents to fetch daily deterministic constraint challenges and submit JSON answers for immediate, stateless evaluation via MCP.

Enables running deterministic multi-model prompt regression and golden dataset benchmark suites, exposing structured results and telemetry through the Model Context Protocol for integration with MCP-compliant clients.

Validates governance evidence for Codex development tasks, enforcing requirements alignment, single-active-subject candidates, executable specifications, and independent gates for traceable review packets.

Enables any MCP client to debug programs through the Debug Adapter Protocol, supporting launch/attach, breakpoints, stepping, variable inspection, evaluation, and memory operations via a single debug tool.

Enables auditing an AI agent's guardrails by providing adversarial test prompts and scoring responses against known refusal/guardrail patterns.

Gives AI assistants a fully offline toolchain for FlyThings OS human-machine interface development: converting HTML prototypes into JSON/FTU layouts, packaging and deploying firmware to devices, capturing real-device screenshots for pixel-diff acceptance, and generating i18n, tests, and bug reports. It also bundles a local vector-plus-BM25 knowledge base covering hardware models, UI control semantics, dependency manifests, and reusable components.

Enables agents to run configured JSON equality checks and assigned pinned GitHub checks through a local stdio connector with operator-provisioned API access. It helps verify disclosed automation evidence against explicit check scopes.

An MCP server for Unity that provides 300 typed tools for editor automation, asset analysis, validation, and diagnostics, supporting live Editor, headless batch, and offline modes.