38,601 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.
Cursor rule Cursor
The Model Context Protocol allows applications to provide context for LLMs in a standardized way, separating the concerns of providing context from the actual LLM interaction. This TypeScript SDK implements the full MCP specification, making it easy to.
nevzoom/codex-claude-bridge-mcp
MCP server Claude CodeCodexCursor +2
MCP server "codex-claude-bridge-mcp" as configured in nevzoom/codex-claude-bridge-mcp. Runs locally from the codex-claude-bridge-mcp npm package.
AbhinavVarma02/Agentops-Evalbench-MCP
MCP server Claude CodeCodexCursor +2
MCP server "agentops-evalbench-mcp" as configured in AbhinavVarma02/Agentops-Evalbench-MCP. Runs locally from the agentops-evalbench-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "devin-mcp-bridge" as configured in phenasdev/devin-mcp-bridge. Runs locally from the devin-mcp-bridge npm package.
MCP server Claude CodeCodexCursor +2
Serve any OpenAPI 3.x / Swagger 2.x API as a local MCP (Model Context Protocol) server over stdio, proxying tool calls to the upstream HTTP API. Runs locally from the @swayam5342/api2mcp npm package.
Skill Claude CodeCodex
Provides a highly secure, containerized Linux workspace via the Model Context Protocol (MCP) mounted at /workspace. Uses this skill when the agent needs to autonomously code, test, and debug safely using filesystem, execution, and editing tools, while adhering to strict environment constraints such as mandatory use of…
MCP server Claude CodeCodexCursor +2
Pre-execution policy gate for consequential agent actions with durable trust receipts. Remote server at api.interailabs.dev.
Skill Claude CodeCodex
Use for governance, memory, drift detection, and audit trail via dark-memory-mcp. Covers 52 canonical + 3 red-team tools across 16 namespaces: session lifecycle, agentmemory CRUD+search, vibe-flow spec/artifact publish + drift, LLM-as-judge, delegation+mindset, research, observability, error observatory, governance…
Plugin Claude Code
Bundles 4 skills, 16 hooks, 1 MCP server · 731 tokens together
Push notifications, human-in-the-loop questions, and permission gating for AI agents. When a running agent is about to do something irreversible, is blocked on a decision that is not its to make, or finishes a long task with nobody watching, it reaches you on your phone and you answer from the app or supported…
kira-autonoma/mcp-context-proxy
MCP server Claude CodeCodexCursor +2
MCP proxy that lazy-loads tool schemas to cut context token overhead by 6-7x. Runs locally from the mcp-lazy-proxy npm package.
Skill Claude CodeCodex
Use the delegate MCP tool to offload replaceable grunt work (boilerplate code, mechanical refactors, formatting, translation, summarizing long documents) to cheap models, so you keep your premium tokens for judgment work. Trigger whenever a subtask is mechanical, well-specified, and doesn't need your full reasoning.
Skill Claude CodeCodex
Discover, trial, and pay for 1,600+ x402-payable APIs on the minia2a marketplace. Built-in USDC micropayments (Base + Algorand + 6 more). No API keys required.
Skill Claude CodeCodex
Use this skill when an AI agent needs to act safely through oakallow, the runtime permission, approval, and audit layer for AI agent tool execution. Trigger it whenever you are about to take a tool action that could be risky, irreversible, or that touches another system, and you need to know whether it is allowed…
MCP server Claude CodeCodexCursor +2
Volante — a transparent, user-owned model router and orchestration control plane. Runs locally from the volante Python package. Needs 85 environment variables to run.
MCP server Claude CodeCodexCursor +2
Repair malformed JSON from LLM/agent output; optional JSON Schema coercion. Free + x402 paid. Remote server at jsonaut.jsonaut-shaurya.workers.dev.
Plugin Claude Code
Bundles 1 skill · 38 tokens together
Public-ready Claude Code starter bundle for Notebooklab MCP outcome workflows.
Plugin Claude Code
Bundles 3 skills · 401 tokens together
Skills for creating and reviewing AGENTS.md, CONTEXT.md, and DESIGN.md files that give AI agents persistent, structured context about a codebase.
MCP server Claude CodeCodexCursor +2
MCP Server Template based on recommended practices. Runs locally from the mcp-server-template npm package.
Grail-Computer/Self-Improving-Agent
Skill Claude CodeCodex
Meta-skill for making the agent self-improving. Covers updating AGENTS.md, creating new skills from repeated workflows, and deciding what to systematize. Invoke after completing tasks, when noticing repeated friction, or at session end.
MCP server Claude CodeCodexCursor +2
A Model Context Protocol (MCP) server providing developer-focused documentation for building applications on Amp. Runs locally from the @edgeandnode/amp-mcp npm package.
ex-takashima/google-veo3-1-mcp-server
MCP server Claude CodeCodexCursor +2
MCP Server for Google Veo 3.1 Video Generation API. Runs locally from the google-veo3-1-mcp-server npm package.
backspacevenkat/polydev-claude-code-plugin
Plugin Claude Code
Bundles 4 commands · 34 tokens together
Multi-model AI perspectives - GPT-5, Gemini, Grok & GLM in parallel. One-click setup, auto-detects local CLI tools.
MCP server Claude CodeCodexCursor +2
A local MCP server that provides preset prompts to guide Claude through tasks. It runs through the dev-prompt-mcp package using npx.
MCP server Claude CodeCodexCursor +2
Ephemeral shared workspace for AI agents - cache contexts, bridge multi-agent workflows, and share data between sessions. Free 2-hour temporary storage. Runs locally from the @0pi/mcp-server npm package.