No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by pepe-agent · MCP Server · ★ 67
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is pepe safe to install? View the security audit →
Pepe An Elixir/OTP AI agent runtime. Define agents, connect to any model, and run a tool-calling loop. Web dashboard · OpenAI-compatible HTTP · WebSocket · Telegram · WhatsApp · CLI Website · Documentation · Quickstart · Sponsor Where Pepe comes from. Pepe was born out of solving real problems across a range of companies I provided development services to: some needed a simple way to run their marketing without expanding headcount; others wanted to connect their ERP and database to an agent capable of answering their team's questions, without compromising on security. The project didn't start as open source: it was internal, proprietary tooling, custom-built for each client. But the results proved consistent enough, across different enough businesses, that I decided to give it a name, an identity of its own, and release it as open source, for anyone to use and contribute to. Why "Pepe"? The name nods to Chespirito's comedy uni
| Stars | 67 |
| Forks | 3 |
| Language | Elixir |
| Category | MCP Server |
| License | MIT |
| Quality Score | 69.6669880316458/100 |
| Open Issues | 6 |
| Last Updated | 2026-10-04 |
| Created | 2026-07-08 |
| Platforms | browser, cli, mcp |
| Est. Tokens | ~19k |
Looking for a pepe alternative? If you're comparing pepe with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Notion MCP server for Claude, Cursor, ChatGPT & Claude Desktop. Connect AI agents to Notion via Model Context
An AI agent for your terminal, built on signal theory: every output is signal, not noise. Codes, runs multi-st
Your Digital Companion. Self-hosted Telegram bot orchestrating multiple AI providers (OpenAI, Anthropic, Googl
Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Pe
c4 GenAI Suite
Self-hosted framework for orchestrating fleets of specialist AI agents — ensemble reasoning and a full agentic
Explore other popular mcp server tools:
pepe is An Elixir/OTP AI agent runtime: define agents, connect any OpenAI-compatible model, and run a tool-calling loop. CLI, HTTP API, web dashboard, Telegram, WhatsApp.. It is categorized as a MCP Server with 67 GitHub stars.
pepe is primarily written in Elixir. It covers topics such as agent-runtime, ai-agent, anthropic.
You can find installation instructions and usage details in the pepe GitHub repository at github.com/pepe-agent/pepe. The project has 67 stars and 3 forks, indicating an active community.
pepe is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to pepe on Agent Skills Hub include notion-mcp-server, OSA, chibi. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: