MCP server Claude CodeCodexCursor +2
MCP server "agent-swarm-dashboard" as configured in valleyboyzz0024-del/Mcpry. Runs locally from the agent-swarm-dashboard Python package.
38,699 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.
MCP server Claude CodeCodexCursor +2
MCP server "agent-swarm-dashboard" as configured in valleyboyzz0024-del/Mcpry. Runs locally from the agent-swarm-dashboard Python package.
Skill Claude CodeCodex
Agent marketplace for A2A trading. Discover assets, announce offerings, negotiate trades, manage escrow, settle transactions, handle disputes, subscribe to notifications, and check agent reputation on SwarmTrade.
AiAgentKarl/agent-reputation-mcp-server-js
MCP server Claude CodeCodexCursor +2
MCP Server for AI agent trust scores, ratings, and reputation tracking. Runs locally from the @aiagentkarl/agent-reputation-mcp-server npm package.
Skill Claude Code
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
MCP server Claude CodeCodexCursor +2
Local Ollama-backed MCP server — 45 tools, smart buffer, execution filters, persistent scratchpad, settings GUI. Runs locally from the localthink-mcp Python package.
AiAgentKarl/agent-commerce-mcp-server
MCP server Claude CodeCodexCursor +2
MCP Server for agent commerce — how AI agents create, compare, and track purchases. Runs locally from the agent-commerce-mcp-server Python package.
MCP server Claude CodeCodexCursor +2
Full MCP server implementation for Django. Expose tools and resources via the Model Context Protocol. Runs locally from the mcp-django-server Python package.
AiAgentKarl/agent-identity-mcp-server
MCP server Claude CodeCodexCursor +2
MCP Server for AI agent identity and authorization — create, verify, and manage agent identities. Runs locally from the agent-identity-mcp-server Python package.
Plugin Claude Code
Bundles 3 skills, 2 hooks · 38 tokens together
Organization agent guardrails — policy-driven skills and hooks for Claude Code.
Plugin Claude Code
Bundles 1 skill · 116 tokens together
Interrogates recently shipped work with seven socratic questions, forcing evidence-backed answers about confidence, blind spots, decay, and unstated assumptions.
Skill Codex
Use NMG as durable memory or temporary multi-Agent coordination when a task may depend on prior user facts, preferences, constraints, decisions, project state, events, reusable experience, or a shared task blackboard; when the user asks to remember or recall something; or when an Agent must start, query, and safely…
clearlove7818/waa-agent-delegation
Skill Codex
Govern an actual agent delegation after the primary agent has chosen one. Use to select exactly one EXECUTIONSUBAGENT, TASKSPECIALISTSUBAGENT, or authorized NAMEDAGENT; check capability, permission, and external-effect boundaries; build a risk-sized TASK-006 packet; apply handshake, failure, delivery, and handoff…
Plugin Claude Code
Bundles 1 skill · 138 tokens together
Reviews how a Claude Code session was conducted rather than what it shipped — classifies its shape, scores the run, flags where the context window went, and turns recurring cost into wire-ins for the skills it used or a named lever on the environment that caused it.
Skill Codex
Keep a reviewable TSV decision trail for long-running or unattended work. Use only when the user explicitly asks for show-me-your-work or a decision log.
Plugin Claude Code
Bundles 12 skills · 732 tokens together
OATDA (One API To Direct All) — Unified access to 10+ LLM providers (OpenAI, Anthropic, Google, Deepseek, Mistral, xAI, Alibaba, MiniMax, ZAI, Moonshot, Bytedance) for text generation, vision analysis, image generation, video generation, audio generation/transcription/translation, model comparison, and balance…
Skill Claude CodeCodex
Install, verify, and re-apply a portable skillferry workspace across Codex, Claude Code, and DeepSeek Harness on macOS, Windows, and Linux.
Plugin Claude Code
Bundles 8 skills · 795 tokens together
A workflow of skills for creating, updating, judging, reviewing, evaluating, and auditing AI skills and agent definitions.
MCP server Claude CodeCodexCursor +2
Model Context Protocol server for Axonity Flow — lets an external agent (e.g. Claude Code) read, draft, and update workflows, agents and tools in an Axonity tenant. Runs locally from the @axonity-ai/mcp npm package.
MCP server Claude CodeCodexCursor +2
Provider-neutral MCP server for AgentDispatch. Runs locally from the @agent-dispatch/mcp-server npm package.
AiAgentKarl/api-to-mcp-converter
MCP server Claude CodeCodexCursor +2
Convert any REST API (OpenAPI/Swagger) into MCP-compatible tools instantly. Runs locally from the api-to-mcp-converter Python package.
Plugin Claude Code
FocusMCP — MCP orchestrator that reduces AI context from 200k to 2k tokens. Compose AI tools (bricks) on demand without polluting context.
MCP server Claude CodeCodexCursor +2
AI-powered multi-agent sales email generation MCP server using OpenAI Agents SDK. Runs locally from the sales-agent-mcp Python package.
Skill Claude CodeCodex
A workflow that delegates long coding, debugging, testing, or interactive command-line tasks to another coding agent running inside tmux, a terminal session manager.
niels-2005/mcp-server-document-search
MCP server Claude CodeCodexCursor +2
A custom MCP server that provides useful tools and resources for AI assistants. Runs locally from the mcp-server Python package.
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: