20 tagged mcp-tool, measured the same way as everything else here.
Skill Claude CodeCodex
Teaches the agent to use the state-memory-mcp MCP server to track workflow state, tasks, decisions, blockers, artifacts, plans, milestones, and their semantic relationships in a persistent graph database.
Skill Claude CodeCodex
Teaches the agent to process, ingest, analyze, and compare WebM, MP4, and GIF video recordings using vision-memory-mcp and state-memory-mcp.
Skill Claude CodeCodex
Teaches the agent to use the Visual Memory MCP server to cache webpage and application screenshots, matching layout states and avoiding redundant LLM vision calls.
Cursor rule Cursor
This project tracks workflow state, tasks, design decisions, and blockers using state-memory-mcp with project slug "vision-memory-mcp".
Cursor rule Cursor
This project utilizes vision-memory-mcp to cache visual states, record layout transitions, provide element grounding, and avoid repetitive LLM vision calls.
Instructions file GitHub Copilot
Copilot instructions for putervision/vision-memory-mcp, covering visual memory (vision-memory-mcp), 1. mandatory workflow & priority, 2. tool reference summary (15 core mcp tools), state memory (state-memory-mcp) and 1. priority order.
Instructions file
Claude Code instructions for putervision/vision-memory-mcp, covering visual memory (vision-memory-mcp), 1. mandatory workflow & priority, 2. tool reference summary (15 core mcp tools), state memory (state-memory-mcp) and 1. priority order.
MCP server Claude CodeCodexCursor +2
Local visual UI cache for AI agents using perceptual hashing + CLIP to cut vision token use. Runs locally from the @putervision/vision-memory-mcp npm package.
Plugin Claude Code
Magic-wormhole for AI agents — bilateral signed-message bus over local and federated mailbox relays. Rust-native MCP server with Ed25519-rooted identity. Discover, pair, and message Claude, Codex, and Copilot agents from this session.
MCP server Claude CodeCodexCursor +2
MCP server "wire" as configured in SlanchaAI/wire. Launched with wire mcp.
Instructions file CodexOpenCode
AGENTS.md instructions for SlanchaAI/wire, covering agents.md — read this first if you are an ai agent, two modes — pick the one that matches your situation, §0 — talking to other agents (v0.9+), zero-config bootstrap (v0.12) and identity is per session (v0.13+) — not per directory.
Hook
Runs when a session starts, executing session-start.sh. From SlanchaAI/wire.
Skill Claude CodeCodex
Enroll operator + organization identity per RFC-001 (the v0.14 identity layer). Use when the user wants to mint an opdid (long-lived operator anchor), create an orgdid, issue/import membercerts, or republish their card with current enrollment. Personal-tier operators always carry a signing-key opdid regardless of SSO…
Skill Claude CodeCodex
Bootstrap Wire with the canonical wire up flow, creating a per-session DID-derived identity and optionally binding local or federation relays. Use when the user says "wire init", "wire up", "set up wire", or asks how to start using Wire.
Skill Claude CodeCodex
Send a signed message to a paired wire peer. Use when user wants to message another agent by handle/nick. Wire send writes a signed event to the per-peer outbox; the daemon pushes to the relay; the peer's daemon pulls + delivers to their inbox. End-to-end via Ed25519 signatures; relays are transport, never authority.
MCP server Claude CodeCodexCursor +2
MCP server "mcp-http-client-server" as configured in ferPrieto/MCP-Http-Client. Runs locally from the mcp-http-client-server npm package.
MCP server Claude CodeCodexCursor +2
A local MCP server that provides stock-market data from Xueqiu, a Chinese investing and stock-information platform. It runs through the xueqiu-mcp package.
At most 3 mods per repository are shown here — the rest are on their repository pages: