3,488 tagged mcp, measured the same way as everything else here.
Browse within: model-context-protocol 187claude-code-plugin 110Multi-Agent 89knowledge-management 77ai-memory 63mcp-client 60ai-assistant 59gtd 59mcp-gateway 58defi 57mcp-security 55code 49bug-bounty 44bugcrowd 44
Agent Claude Code
Use this agent when you need expert guidance on testing strategies, test implementation, or test improvements for the pgEdge Postgres MCP Server project. Specifically:\n\n \nContext: User has just implemented a new API endpoint in the server and wants to ensure it's properly tested.\nUser: "I've added a new endpoint…
Agent Claude Code
You are the independent verifier for the Changelog Drafter loop.
Agent Claude Code
Independent checker for loop-produced changes. Rejects unless tests pass and scope is minimal. Never implement fixes.
Agent Claude Code
Attempts to break implementations.
Agent Claude Code
Security analysis using narsil-mcp.
Agent Claude Code
Chief Wiggum - Loop health supervisor and arbiter.
Agent Claude Code
gent to implement code changes for a task that has already been planned by lead and analyzed by explorer. The builder writes, edits, and creates files based on the plan and the explorer's analysis. Invoke only after the explorer has completed its action. Never invoke without a canonical handoff addressed to builder.
Agent Claude Code
gent to read and map the codebase for a specific task. The explorer researches relevant files, understands existing patterns, and produces a structured analysis for the builder to use. Invoke after the lead has defined a plan and before the builder starts. Never invoke for tasks that require writing or modifying files.
Agent Claude Code
Agent "lead" from enmanuelmag/agent-harness-kit, covering lead agent — @cardor/agent-harness-kit, available research tools, provider delegation guidance, lead agent — @cardor/agent-harness-kit and !! absolute constraint — read before anything else !!.
Agent Claude Code
Agent "README" from echoVic/blade-code, covering claude code subagents collection, available subagents, development & architecture, language specialists and infrastructure & operations.
Agent Claude Code
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
Agent Claude Code
Optimizes prompts for LLMs and AI systems. Use when building AI features, improving agent performance, or crafting system prompts. Expert in prompt patterns and techniques.
Agent Claude Code
Implements an approved GitWand plan, one step at a time, test-first. Full edit access. Use after a plan is approved to write the actual code on a feature branch.
Agent Claude Code
Turns a GitWand spec or roadmap item into a step-by-step implementation plan. Read-only except for writing the plan document. Use when you have an approved design/spec and need a detailed, reviewable implementation plan before any code is written.
Agent Claude Code
Adversarially verifies a GitWand change before PR — runs the test suites, checks AGENTS.md compliance, and reviews the diff. Read-only (no Edit/Write) so the review stays honest. Use after the executor finishes, before opening a PR.
Agent Claude Code
A read-only technical adviser that gives a second opinion on difficult engineering decisions. It reviews evidence supplied by the caller and compares possible approaches, risks, and compatibility concerns.
Agent Claude Code
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
Agent Claude Code
A small read-only helper agent defined by a project. It analyzes only the context supplied by the caller and returns a concise conclusion in Simplified Chinese.
Dicklesworthstone/mcp_agent_mail_rust
Agent
Use this screen to check which agents are alive, what they are running, and where work is currently landing.
Agent
Expert database query agent with schema awareness. Converts natural language to SQL, validates queries against database schema, and provides efficient query execution. Supports schema versioning and time-travel queries. Uses GFS branching for safe destructive operations.
Agent
Tests web applications end-to-end using Glance browser MCP. Navigates pages, fills forms, clicks buttons, takes screenshots, runs assertions, and reports bugs. Use when you want to verify an app works correctly — login flows, forms, navigation, responsiveness — with real browser interaction.
Agent Claude Code
Internal agent for reviewing staged code changes against CAS rules. Checks for rule compliance, patterns, and quality. Spawned before commits or on demand.
Agent Claude Code
Internal agent for generating session summaries at stop. Creates a concise summary of work done, decisions made, and learnings captured. Spawned by Stop hook.
Agent Claude Code
Internal agent for verifying task completion. Spawned automatically on task close. Do not invoke directly.
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: