"Open Collective" matching MCP servers:

Open-source verification for evidence-grounded AI. Runs deterministic grounding checks of AI outputs against source evidence, with no LLM judge.

Open behavioral litmus for MCP servers — grades A–F across tool-output injection, egress, sensitive-data, and adversarial-input, with reproducible, content-addressed evidence. Tools: run_litmus, verify_attestation.

Scans any website and produces an Agent Readiness Report scored on the open ASO framework.

An MCP server that gives AI assistants the ability to check open-source packages for vulnerabilities, enrich findings with real-world exploit intelligence, and statically analyse whether vulnerable code is actually reachable in your project.

Enables MCP clients to open websites, capture screenshots at multiple breakpoints, and run automated design audits for issues like overflow, small tap targets, low contrast, missing alt text, tiny text, and clipped content.

Gives your coding agent the review comments left on a running frontend with Maple. It lists open comments with the element, source location and screenshot they point to, waits for new ones, and resolves them when the fix is in.

IFC/BIM toolkit with a free browser 3D viewer: validate IFC with a 0–100 Health Score, check buildingSMART IDS 1.0, read DXF drawings, and open models, floor plans, 3D sketches and live digital twins in 3D. Validation runs locally and files are not uploaded.

Open-source MCP server and CLI. It maps every function to the tests that call it, ranks untested risk, and uses mutation proof to show a test catches a break. Local, MIT.

Enables coding agents to open the same web page across persistent mobile, tablet, and desktop viewports, interact with it, capture screenshots, inspect the accessible DOM, and run responsive layout audits without losing state between calls.

Enables autonomous web-contract verification through MCP tools for planning, classifying, checking, and recording bug patterns, with access to a shared community corpus that strengthens collective detection.

Checks the outcome after an agent handoff, when a request, 200 or ack only shows the handoff. Reads one field of one exact public HTTPS JSON record, with a same-site known-good control, for 20-120 s. Returns PROVED, DISPROVED or INCONCLUSIVE with a signed receipt you can verify. 5 free checks, then USD 1 per completed check, by card (Stripe Checkout) or existing Link wallet. INCONCLUSIVE is free.

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.

Enables AI coding agents to open and exercise web applications in an isolated Chromium browser, capture screenshots and runtime/network diagnostics, and run deterministic page checks with linked evidence.

MCP server for QTM4J (QMetry Test Management for Jira) Open API, enabling test case and cycle management via natural language.

Lets an agent open a running web app in a real browser, perform literal interaction steps, capture screenshots, measure UI rules, diff frames, and store evidence, while leaving all judgment to the calling agent.

Enables an AI to build, inspect, test, and render logic circuits as .dig files, then open them in the Digital app.

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.

Enables MCP clients to inspect, validate, test, export, and query Godot projects, including live state from an open editor via a bridge addon.

Enables interaction with ZenTao open-source instances to query and manage tasks, bugs, stories, test cases, and test runs, using REST v1 with legacy fallback for incompatible routes.

Open a React Native app in a simulated phone: read the accessibility tree, tap, type, and set device state such as permissions, connectivity and payment results.

Enables AI assistants to validate, lint, explain, and test-run Open Lakehouse Contracts locally over stdio, with no network, account, or platform access.

An open-source, local-first MCP server for automated Schema.org JSON-LD generation, GA4 metric validation, /llm.txt auditing, and content stickiness analytics.

An MCP server that gives an AI coding agent real control of Roblox Studio and Roblox Open Cloud, with a test-and-security layer no other Studio MCP has.

Enables AI agents to automate an open PlayCanvas project by creating and editing scenes, entities, scripts, assets, templates, animation, builds, and settings, then launching and inspecting the running app. It also supports screenshots, logs, viewport control, and runtime input for verifying that scenes actually run.

Enables AI agents to audit a web page in one call — title, meta description, canonical, robots, Open Graph, headings, JSON-LD, security headers and page delivery — returning each finding with its evidence and a ready patch to apply. It also compares a deploy preview against production to surface only regressions, keeps audited pages in tabs with history and daily watches, and runs Lighthouse lab tests via PageSpeed Insights.

Enables coding agents to check setup, manage iOS Simulator devices, build/install/launch iOS apps, capture screenshots, send input, and open a live browser preview. It connects local agent workflows to Apple's simulator without requiring a custom emulator or native pane.

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 interaction with Open Traffic Generators (OTG) through a standardized API, allowing configuration, traffic control, and metrics collection via MCP.

Deterministic construction and specialty contractor financial skills, WIP over/under-billing reconciler, AIA G702/G703 retainage analyzer, and LevelBench-100 evaluation harness.