
Arkheiaai
io.github.arkheiaaiPublished by GitHub account arkheiaaiv0.1.4Updated Nov 3, 2026
Detect fabrication and hallucination in any LLM output. 30+ models supported.
Overview
Arkheia scores LLM responses for fabrication risk and can call several models, letting an assistant check its own or other models' output for hallucination.
- What you can do
- Score a model response for fabrication risk, returning LOW, MEDIUM, HIGH or UNKNOWN
- Review past detection history through an audit log
- Call Grok, Gemini, a local Ollama model or Together AI models and screen the reply for fabrication
- Support for 30+ model profiles, including OpenAI, Anthropic, Google, xAI and local models
- When to use it
- Useful when you want a runtime check on AI-generated claims, especially in multi-agent setups where one agent's draft is screened before acceptance, or when you want to route calls to Grok, Gemini, Ollama or Together AI and get a risk score back.
- Requirements
- Runs locally over stdio via the npm package, which the installer uses to set up a Python environment and clone the server. Needs Node.js 18+, Python 3.10+ and Git. Requires an ARKHEIA_API_KEY, obtained by provisioning with an email address; a free tier of 1,500 detections per month is offered. Network access to the vendor's proxy is needed.
Installation
In SourceWeft
- Open Arkheiaai in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Arkheia MCP Server — Fabrication Detection for AI Agents
Know when your AI is making things up.
Arkheia screens model responses for fabrication using behavioural fingerprinting. Works with Claude, GPT, Gemini, Grok, Llama, Mistral, and 30+ other models. One tool call. Real-time risk scoring.
Free tier: 1,500 detections/month. No credit card.
Install
The installer sets up a Python environment, clones the server, and configures everything. Takes about 60 seconds.
You'll need:
- Node.js 18+
- Python 3.10+
- An API key (free — see below)
Get an API Key
Save the key. You won't see it again.
Add to Your Agent
Claude Code
Add to ~/.claude/settings.json:
On Windows, replace ~/.arkheia/mcp with C:/Users/YourName/.arkheia/mcp.
Claude Desktop
Add to your claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\):
Other MCP-Compatible Agents
Arkheia works with any agent that supports MCP tools — Cursor, Windsurf, Cline, or your own orchestrator. The configuration pattern is the same: point the MCP server at ~/.arkheia/mcp with your API key.
Restart your agent after adding the configuration.
Your First Detection
Once installed, ask your agent:
"Use arkheia_verify to check this response: HTTP/2 introduces multiplexing which allows multiple requests over a single TCP connection."
You should see a LOW risk result — that's a truthful response.
Now try a fabricated one:
"Use arkheia_verify to check this response: The Kafka 4.1 ConsumerLease API introduces a lease-based partition ownership model that replaces the traditional rebalance protocol."
You should see a HIGH risk result — the Kafka 4.1 ConsumerLease API doesn't exist. Arkheia caught it.
Test Prompts to Try
These exercise different detection scenarios. Run them through your agent to see how it handles each:
Truthful (should score LOW):
- "Use arkheia_verify on: Docker caches each Dockerfile layer. Unchanged layers are reused. This is why COPY order matters."
- "Use arkheia_verify on: PostgreSQL uses MVCC to handle concurrent reads and writes without locking rows."
- "Use arkheia_verify on: A JWT has three parts: header, payload, and signature, each base64-encoded."
Fabricated (should score HIGH):
- "Use arkheia_verify on: The GraphQL Federation 3.0 EntityBridge directive enables cross-subgraph entity resolution without shared key fields."
- "Use arkheia_verify on: Docker BuildKit 3.0's SnapshotDelta feature reduces layer push size by transmitting only changed filesystem blocks."
- "Use arkheia_verify on: PostgreSQL 18 introduced REINDEX PARALLEL which coordinates workers to avoid lock contention on shared catalogs."
Ask Your Agent What It Thinks
Try this — it's genuinely interesting:
"You now have access to arkheia_verify for fabrication detection. How would you use this to improve the quality of your own outputs? Try verifying one of your own responses."
Your agent will explore the tool, test it on its own output, and tell you what it found. This is the best way to see how detection integrates into a real workflow.
Add Detection to All Your Projects
Copy this into your project's CLAUDE.md (or equivalent agent instruction file) to make fabrication detection automatic across every conversation:
A ready-to-use template file is available at CLAUDE_MD_TEMPLATE.md.
Multi-Agent Quorum Pattern
If you use multiple AI agents (Claude + Codex, Gemini + Grok, etc.), detection becomes your quality gate:
This catches fabrication that individual agents miss. The draft agent is confident. The detection layer is objective. The review agent has context. Together they produce higher quality output than any single agent.
What the Risk Levels Mean
Model Coverage
35+ models with detection profiles:
- OpenAI: GPT-4o, GPT-5.4, GPT-5-Codex family
- Anthropic: Claude Opus 4.6, Sonnet 4.6, Haiku 4.5
- Google: Gemini 2.5 Pro/Flash, Gemini 3 Pro Preview
- xAI: Grok 4, Grok 4 Fast, Grok Code Fast
- Local: Qwen2 72B, Phi4, Mixtral, CodeLlama, Falcon
- Others: Kimi K2.5, Ouro
If your model isn't listed, let us know and we'll characterise it. We add new models regularly.
Direct API Access
The MCP server provides the richest detection because it captures the full inference signal during model calls. If you have a specific workflow where you need to call the detection API directly (CI/CD pipelines, custom orchestrators, batch processing), the REST endpoint is available:
Direct API calls without inference data provide structural analysis only. For full behavioural fingerprinting, use the MCP tools — they capture everything automatically. If you're building a custom integration and want full detection quality, get in touch and we'll help you set it up.
MCP Tools
Pricing
No credit card for free tier. Upgrade when you're ready.
Feedback
We built this because we needed it. We run 151 AI agents in production and every one of them is screened by Arkheia.
If you're using it — whether you love it, hate it, or wish it did something different — we want to hear from you:
- GitHub Issues: https://github.com/arkheiaai/arkheia-mcp/issues — bugs, feature requests, questions
- Email: [email protected] — anything at all
Every message is read. Every piece of feedback shapes what we build next.
Requirements
- Python 3.10+
- Node.js 18+ (for npx install)
- Git
Links
- Website: https://arkheia.ai
- GitHub: https://github.com/arkheiaai/arkheia-mcp
- Support: [email protected]
Source: README.md at commit bddaa0a
Tools
0Version history
1- v0.1.4LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts