MCP App StoreMCP App StoreSKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
uxc
Discover, inspect, and invoke schema-exposed remote interfaces (OpenAPI, GraphQL, gRPC, MCP, JSON-RPC) via a single CLI contract with deterministic JSON envelop
hmem (persistent agent memory)
Interactive installer and setup guide for hmem (persistent memory MCP server); automates .mcp.json config, memory dir, and adds agent hooks for Claude Code, Gem
OrchestKit
Automated nightly memory consolidation: prunes stale memory files, merges duplicates, resolves contradictions, and rebuilds MEMORY.md indexes with deterministic
agentops
Orchestrates a three-phase RPI lifecycle (discovery → implementation → validation) for autonomous agent workflows, including complexity classification, routing,
skill-evolve
Iteratively improve an existing Agent Skill by observing real outputs, extracting recurring failure patterns, and applying small, verifiable fixes (OTF + JIT +
caveman
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
raymon
Lightweight searchable Ray-compatible log server (Raymon) exposing an MCP interface for agents to search, list, and fetch full log entries for debugging and tri
beeper-cli
Read-only CLI for agents to list, search, and read local Beeper Desktop chat history (SQLite) with JSON output for integration.
skills
Guides building a small, stateless Bash CLI (eodhd) that safely wraps the EODHD API with OpenClaw-compatible auth and redaction practices.
TerminalSkills Skills Library
Documentation and best-practices for E2B sandboxes: run AI-generated code, install packages, manage files, and return artifacts safely.
multi-agent-shogun
Design, validate and review Claude Code-style SKILL.md files: frontmatter guidance, trigger design, testing patterns, and recommended file structure for robust
notmcp
A local toolbox runner for executable scripts that lets agents discover and run prebuilt tools which interact with external APIs and services.
sigcli
Browse and interact with X (Twitter) from an agent: view profiles, read tweets and threads, search, check trends, like/retweet, follow, bookmark, and post (with
openclawfice
Pixel-art virtual office dashboard for OpenClaw agents: monitor status, record accomplishments, create approval quests, and run team meetings with gamified XP a
fireworks-skill-memory
Provides persistent, per-skill experience memory for Claude Code and Codex, injecting past lessons and distilling new ones across sessions.
botstreet
Run a research-driven virtual portfolio manager: update prices, research, make trades, write a diary entry, and save daily snapshots for a simulated $100k accou
prompts
Detects which execution environment an agent is running in (Claude Code, Vercel Sandbox, or local dev) and exposes available tools and capabilities for safe, en
camoucli
Local Camoufox CLI+daemon for Playwright-based browser automation: persistent sessions, named tabs, snapshot refs, and machine-readable outputs for agent-driven
syke
Local-first cross-harness memex for agents: query, read, and record session memory with commands like `syke ask`, `syke memex`, and `syke record`.
Rosetta
Ensure an agent loads the most current execution context and prep steps (bootstrap, docs, tools) before planning or acting.
total-recall
Autonomous agent memory that passively observes session transcripts, compresses them into prioritized notes, consolidates redundancies, and recovers missed cont
agentmemory
Index of AgentMemory MCP tools and their parameters; helps choose the right memory tool and learn required arguments.
printing-press-library
Query Digg's AI story rankings, GitHub signals, and pipeline events from the terminal; read-only researcher-focused CLI for tracking trending AI news and repo a
paseo
Run a single advisor agent that reads the situation and gives a concise second opinion or recommendation without taking action.
vibe-sunsang
Generates v2 growth reports by analyzing AI-collaboration session logs across six skill axes, producing level scores, radar summaries, and actionable next steps