Getkin Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Getkin Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Agent infrastructure that runs itself. One MCP server, six tools.
| Tool | Description | Price |
|---|---|---|
recommend_model | Get the optimal LLM for any task across 17 models and 6 providers | Free |
check_availability | Real-time availability and latency for LLM provider APIs | $0.005 USDC |
route_llm_call | Route chat completions through GetKin's proxy (OpenAI-compatible) | 3% margin |
compress_memory | Compress session dumps into structured 3-tier memory | First 5 free, then $0.03 USDC |
list_models | List all available models with current pricing | Free |
check_memory_usage | Check free tier compression usage for an agent | Free |
Connect to the GetKin MCP server using any MCP-compatible client:
{
"mcpServers": {
"getkin": {
"url": "https://getkin-mcp.fly.dev/mcp"
}
}
}Once connected, your agent has access to all six tools. The recommend_model tool is free and requires no payment — use it to find the cheapest or fastest model for any task.
Paid tools use x402 payments via Solana USDC. The compress_memory tool includes 5 free compressions per agent.
Anthropic, OpenAI, Google, Mistral, DeepSeek, Meta (via Together AI)
MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.