Arkheia Hallucination Detection MCP
OfficialEnables calling Google Gemini models with integrated fabrication screening to detect and score potential hallucination risks in the generated output.
Enables calling local Ollama models with integrated fabrication screening to detect and score potential hallucination risks in the generated output.
Arkheia MCP Server — Fabrication Detection for LLMs
Detect fabrication (hallucination) in any LLM output. Free tier included (1,500 detections/month).
Quick Start
1. Clone and install
git clone https://github.com/arkheiaai/arkheia-mcp.git ~/.arkheia-mcp
cd ~/.arkheia-mcp
pip install -r requirements.txt2. Get an API key (free)
curl -X POST https://arkheia-proxy-production.up.railway.app/v1/provision \
-H "Content-Type: application/json" \
-d '{"email": "you@example.com"}'3. Add to Claude Desktop
Edit your config file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%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).
4. Restart Claude
The arkheia_verify and arkheia_audit_log tools will appear automatically.
Tools
Tool | Description |
| Score any model output for fabrication risk (LOW/MEDIUM/HIGH) |
| Review detection history |
| Call xAI Grok + screen for fabrication |
| Call Google Gemini + screen for fabrication |
| Call Together AI (Kimi, DeepSeek) + screen |
| Call local Ollama model + screen |
| Persistent knowledge graph |
Pricing
Free: 1,500 detections/month (no credit card)
Single Contributor: $99/month (unlimited)
Professional: $499/month (20 concurrent)
Team: $1,999/month (50 concurrent)
Requirements
Python 3.10+
Git
Full Setup Guide
See AGENTS.md for detailed instructions, troubleshooting, and environment variables.
Links
Website: https://arkheia.ai
Support: support@arkheia.ai
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/arkheiaai/arkheia-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server