20,069 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Nine tools for deterministic MCP validation that catch confidence inflation, circular logic, fabricated numbers, arithmetic errors, and concurrency hazards before bad LLM output ships. Runs locally from the ct-mcp npm package.
★not rated 0 5mo agoA
tokens not measured
originalMIT
Use when the user wants to convert a Jira ticket (or set of tickets) into TestRail test cases. Triggers on phrases like "turn JIRA-123 into test cases", "create TestRail cases from this ticket", "generate test cases for ", or when the user pastes a Jira ticket key/URL and asks for QA coverage. Requires both a Jira MCP…
A command-line testing setup for checking bot and plugin commands in PowerShell, Command Prompt, or Bash without connecting to real QQ accounts or channels.
MCP server "enterprise-ai-agent-eval-platform" as configured in ad-github1/ENTERPRISE-AI-AGENT-EVALUATION-PLATFORM. Runs locally from the enterprise-ai-agent-eval-platform Python package.
Structured, reviewable test/automation/demo runs against a remote Mac controlled via the vnc-mac-agent MCP tools (screen/mouse/keyboard/clipboard/apps). Records each step with a screenshot, purpose, feature tested, and a self-assessed evaluation with cited evidence, reviewable afterward at the viewer's /reports page.…
Independent safety assessment specialist for ISO 26262 compliance verification, V&V planning and review, test case evaluation, functional safety audits, safety manual review, and certification support for ASIL-D automotive systems.
Find repeated expensive read-only checks, duplicate tool calls, and cold concurrent misses in AI agent workloads before native-first, policy-gated reuse.
An agent explores the product. CI replays the path with no AI. A broken step is a named report. Runs locally from the @premierstudio/browser-engine npm package.
★not rated 0 1mo agoA
tokens not measured
originalApache-2.0
Let Claude drive and inspect real web pages in long-lived Chromium sessions: accessibility-tree snapshots with clickable refs, console and network diagnostics, and a built-in agent that runs a task and reports what broke.
★not rated 0
changed 1mo agoA
tokens not measured
originalMIT
MCP server that gives an AI agent real email inboxes: create, waitforotp, send and more, for Claude Desktop, Cursor and any MCP client. Runs locally from the mailflat-mcp Python package. Needs 2 environment variables to run.
★not rated 0 1mo agoASocket: warn
tokens not measured
originalMIT
AI QA that runs your app in a browser on every pull request: set up a test target, read what it found on a pull request, and plan tests for a local diff.
★not rated 0
changed 20d agoA
tokens not measured
originalMIT
Run a battery of PCB design-hygiene checks against the board open in EasyEDA Pro, through the easyeda MCP tools, and produce a scored report. Use when the user says "/pcb-lint", "lint the board", "run PCB checks", "check my layout", "is this board ready to fab?", or finishes a PCB layout iteration and is about to…
Install, control and verify Windows apps through WinAuto MCP. Choose UIA state checks, guarded multi-control batches with Pillow/OpenCV, or explicitly permitted short foreground sequences for custom controls and focus-dependent interactions. Includes capture/cache, journal and partial-failure recovery. For browser…
Develop, test, gate, and release the mattermost-mcp connector. Use this skill when changing the connector's API mappings, MCP tools, packaging, documentation, or repository gates.
Use when working on a user-approved local codebase through the Local Workspaces app, including exploring, implementing, debugging, reviewing, testing, or visually checking a desktop/web UI produced by that workspace.
★not rated 0 12d agoA45 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: