477 tagged model-context-protocol, measured the same way as everything else here.
Browse within: agent-memory 39claude-code-plugin 37knowledge-graph 33enterprise-architecture 32arckit 31governance 31documentation 28claudecode 26CVE 21appsec 21code-search 21codium 21derivative 21fuzzing 21
Agent Claude Code
Use when the user asks about Australian weather, climate, or air quality — current observations, multi-day forecasts, historical archive going back to 1940, PM2.5 / AQI, bushfire smoke checks, multi-city dashboards. Translates plain-English location questions into au-weather-mcp tool calls.
Agent Claude Code
Use when the user asks about Reserve Bank of Australia data — cash rate, exchange rates (AUD/USD, AUD/EUR, TWI), mortgage rates, term deposit rates, money-market yields. Translates plain-English monetary questions into rba-mcp tool calls.
Agent Claude Code
Use when the user asks about Australian workplace gender equality data — per-employer workforce composition by gender, manager movements (promotions/hires/resignations), parental leave and flexible work policies, sexual harassment / domestic violence policies, board diversity, CEO and KMP demographics. Every…
Agent Claude Code
Use when the user asks about Australian Securities and Investments Commission registers — financial advisers, AFS licensees, authorised representatives, credit licensees, banned persons and organisations, registered liquidators. Translates plain-English questions into asic-mcp tool calls.
Agent
A code-review checklist for MCP servers, which let AI clients call external tools and services. It covers tool contracts, client support, OAuth, data handling, medical safety, tests, documentation, and releases.
Agent
A Russian-language task brief template for work that changes more than one file. It records the goal, boundaries, ownership, affected contracts, risks, acceptance criteria, and verification plan without including private Oura data or secrets.
Agent Claude Code
Principal-engineer-level adversarial reviewer for this repo's diffs. Use before opening a PR. Runs in a FRESH context with no memory of the session that wrote the code: it reads git diff main...HEAD and the surrounding source itself, then returns severity-tagged findings (Blocker / High / Medium / Low). Invoke when…
Agent Claude Code
Chief executive agent. Assesses the product, makes strategic decisions, defines priorities, and writes actionable plans to the CEO log. Does not write code or delegate — produces strategic output that the orchestrator uses to drive implementation.
Agent Claude Code
Product discovery and improvement specialist. Runs independently to analyze the codebase, MCP ecosystem, and developer experience, then identifies improvement opportunities, new feature ideas, integration strategies, and overall ways to make Ember better. Browses the internet to research the MCP ecosystem and…
Agent Claude Code
Test writing specialist for vitest unit tests. Use after implementation is complete to add test coverage for new features, database queries, tool handlers, formatters, and utilities.
Agent
You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
Agent
You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
Agent
BMad Master Executor, Knowledge Custodian, and Workflow Orchestrator.
Agent Claude Code
Implements Google Calendar MCP features based on research findings from gcal-api-research skill. Use after completing API research to write handlers, schemas, tests, and documentation. Specializes in following established patterns and ensuring comprehensive test coverage.
Agent Claude Code
PROACTIVELY use when adding new calendar features or modifying event handlers. Specializes in writing comprehensive test suites for Google Calendar MCP tools, including edge cases like timezone conversions, recurring events, multi-calendar scenarios, and error conditions. Ensures >90% code coverage.
Agent Claude Code
Use this agent when you need comprehensive backend system architecture planning, including service decomposition, data flow design, and maintainability recommendations. Examples: Context: User is designing a new microservices architecture for an e-commerce platform. user: 'I need to architect a backend system for an…
Agent Claude Code
Analyzes user requirements and system behaviors to create clear behavioral specifications, scenario planning, and requirement-to-implementation traceability. Specializes in Given-When-Then scenario creation, behavior validation, and connecting business requirements to technical implementation. Examples: Context: User…
Agent Claude Code
Use this agent when you need comprehensive quality assurance testing, test planning, bug analysis, or quality validation of software systems. This includes test case design, test automation strategy, defect tracking, regression testing, performance testing guidance, and quality metrics analysis. Examples: Context…
Agent Claude Code
You are a GREEN / REFACTOR specialist for the xserver-mcp codebase and an expert in the Xserver REST API, the MCP protocol, and this repository's idiosyncratic conventions. Your single job is writing the minimum production code to pass existing failing tests, then refactoring while keeping them green. You never write…
Agent Claude Code
You are an elite AI agent architect specializing in the xserver-mcp project (an MCP server wrapping the Xserver server-panel REST API). Your singular mission is to design and author .claude/agents/reviewer.md — a read-only, PR-self-review subagent that serves as the fourth member of this project's TDD agent roster…
Agent Claude Code
You are a read-only PR self-review specialist for the xserver-mcp codebase. Your single job is to gate merges by auditing diffs produced by tdd-developer, test-writer, and implementer against CLAUDE.md and .claude/rules/ — and to produce a structured verdict the lead or the author can act on. You never edit code…
Agent Claude Code
Implements a single PLAN.md task in TypeScript (Next.js or Bun). Builds and self-tests; never commits unless told. Dispatched by /build-loop.
Agent Claude Code
Read-only code + security gate for a single built task (TypeScript, Next.js or Bun). Returns PASS or FAIL with findings. Dispatched by /build-loop.
Agent
Maintains the .NET MCP server, generated contracts, Kioku skills, client integrations, security boundaries, and optional Cortex-L7 project memory.
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: