idun-agent-platform — security grade SAFE, quality 71/100

Security audit verdict: SAFE · quality 71/100

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 Idun-Group · MCP Server · ★ 201

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is idun-agent-platform safe to install? View the security audit →

About idun-agent-platform

English العربية Productionize LangGraph & ADK agents. Self-hosted. Open source. No vendor lock-in. Cloud · Try the demos · Quickstart · Docs · Discord · [Book a dem

a2a-protocolag-ui-protocolagent-platformagentic-aiagentsclaude-codeclaude-skillscopilotkitgoogle-adkgovernance

Quick Facts

Stars201
Forks13
LanguagePython
CategoryMCP Server
LicenseGPL-3.0
Quality Score71.3896449361396/100
Open Issues110
Last Updated2026-09-22
Created2025-05-28
Platformsclaude-code, mcp, python
Est. Tokens~17k

Compatible Skills

These tools work well together with idun-agent-platform for enhanced workflows:

  • packmind — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (52%)
  • giselle — semantic(0.16)+complementary+same_lang+similar_pop+shared_platform (50%)
  • evo-ai — semantic(0.34)+rare_topics+same_lang+similar_pop+shared_platform (46%)

idun-agent-platform alternative? Top 6 similar tools

Looking for a idun-agent-platform alternative? If you're comparing idun-agent-platform 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.

  • DeepMCPAgent by cryxnet · ⭐ 806

    Model-agnostic plug-n-play LangChain/LangGraph agents powered entirely by MCP tools over HTTP/SSE.

  • oreilly-ai-agents by sinanuozdemir · ⭐ 299

    An introduction to the world of AI Agents

  • platform by agynio · ⭐ 232

    Agyn is an open-source Kubernetes-native runtime that moves AI agents like Claude Code and Codex from laptops

  • Fast-LLM-Agent-MCP by omerbsezer · ⭐ 90

    This repo covers LLM, Agents, MCP Tools, Skills concepts with sample codes: LangChain & LangGraph, AWS Strands

  • preloop by preloop · ⭐ 66

    The open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime obs

  • samples by strands-agents · ⭐ 852

    Agent samples built using the Strands Agents SDK.

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is idun-agent-platform?

idun-agent-platform is 🟪 Open-source runtime that ships any LangGraph or Google ADK agent as a production-ready FastAPI service. Bundled , AG-UI copilotkit API, chat UI, 15+ guardrails, MCP, OpenTelemetry, OIDC. One pip in. It is categorized as a MCP Server with 201 GitHub stars.

What programming language is idun-agent-platform written in?

idun-agent-platform is primarily written in Python. It covers topics such as a2a-protocol, ag-ui-protocol, agent-platform.

How do I install or use idun-agent-platform?

You can find installation instructions and usage details in the idun-agent-platform GitHub repository at github.com/Idun-Group/idun-agent-platform. The project has 201 stars and 13 forks, indicating an active community.

What license does idun-agent-platform use?

idun-agent-platform is released under the GPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to idun-agent-platform?

The top alternatives to idun-agent-platform on Agent Skills Hub include DeepMCPAgent, oreilly-ai-agents, platform. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse MCP Server tools