loading…
Search for a command to run...
loading…
Detect fabrication and hallucination in any LLM output. Score responses from GPT-4o, Claude, Gemini, Llama and 30+ models. Free tier included.
Detect fabrication and hallucination in any LLM output. Score responses from GPT-4o, Claude, Gemini, Llama and 30+ models. Free tier included.
Detect fabrication (hallucination) in any LLM output. Free tier included (1,500 detections/month).
git clone https://github.com/arkheiaai/arkheia-mcp.git ~/.arkheia-mcp
cd ~/.arkheia-mcp
pip install -r requirements.txt
curl -X POST https://arkheia-proxy-production.up.railway.app/v1/provision \
-H "Content-Type: application/json" \
-d '{"email": "[email protected]"}'
Edit your config file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": {
"arkheia": {
"command": "python",
"args": ["-m", "mcp_server.server"],
"cwd": "~/.arkheia-mcp",
"env": {
"PYTHONPATH": "~/.arkheia-mcp",
"ARKHEIA_API_KEY": "ak_live_YOUR_KEY_HERE"
}
}
}
}
On Windows, replace ~/.arkheia-mcp with the full path (e.g. C:/Users/YourName/.arkheia-mcp).
The arkheia_verify and arkheia_audit_log tools will appear automatically.
| Tool | Description |
|---|---|
arkheia_verify |
Score any model output for fabrication risk (LOW/MEDIUM/HIGH) |
arkheia_audit_log |
Review detection history |
run_grok |
Call xAI Grok + screen for fabrication |
run_gemini |
Call Google Gemini + screen for fabrication |
run_together |
Call Together AI (Kimi, DeepSeek) + screen |
run_ollama |
Call local Ollama model + screen |
memory_store / memory_retrieve / memory_relate |
Persistent knowledge graph |
See AGENTS.md for detailed instructions, troubleshooting, and environment variables.
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"arkheia-hallucination-detection-mcp": {
"command": "npx",
"args": []
}
}
}