Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,985 indexed, measured the same four ways as everything else here.
Educational MCP server for math operations, statistics, visualization, and persistent workspaces. Built with FastMCP. Runs locally from the math-mcp-learning-server Python package.
AI image and video generation, editing, and region repair via Gemini, OpenAI, and Grok. Runs locally from the pixel-surgeon-mcp npm package. Needs 3 environment variables to run.
★not rated 5 4mo agoA
tokens not measured
originalMIT
Turn Lighthouse audits into coding-agent fix packs for Claude Code, Cursor, and Copilot. Runs locally from the @fullstackdegen/agent-audit npm package.
★not rated 5 1mo agoA
tokens not measured
originalMIT
Agent network intelligence for AI agents. Trust scoring, broker discovery, and Ed25519 identity. Runs locally from the moltbridge npm package. Needs 3 environment variables to run.
Search and contribute to a shared knowledge base of AI-discovered problem-solution pairs. Runs locally from the openhive-mcp npm package. Needs 1 environment variable to run.
Allow AI systems to list, search, upload, download, and manage files and folders in Google Drive. Runs locally from the google-drive-mcp npm package. Needs 1 environment variable to run.
MCP server exposing Spinnaker CD platform via Gate API for pipeline and deployment management. Runs locally from the spinnaker-mcp npm package. Needs 4 environment variables to run.
Review, shape, or implement AIppocampus agent-facing UX for foreground recall, hooks, MCP/CLI tools, action cards, recovery cards, onboarding, public demos, and issue triage. Use when work mentions AIppocampus UX, foreground surfaces, source-backed continuity usability, Linear/Raycast/Stripe-style…
MCP server "thronglets" as configured in Shangri-la-0428/Thronglets. Launched with https://github.com/Shangri-la-0428/Thronglets/releases/download/v0.2.0/thronglet.
★not rated 5 4mo agoA
tokens not measured
originalMIT
Visual-diff & change-detection tools that catch agentic UI drift for coding agents. Runs locally from the @corralimited/snapdiff-mcp npm package. Needs 2 environment variables to run.
★not rated 5 24d agoA
tokens not measured
originalMIT
An escape guide for coding agents, providing structured thinking tools to help agents unstick. Runs locally from the agent-never-give-up-mcp npm package.
Persistent, shared memory for AI agents — facts, checkpoints, semantic search. Runs locally from the iranti npm package. Needs 3 environment variables to run.
★not rated 5 3mo agoA
tokens not measured
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: