Arkheia Hallucination Detection

Detect fabrication and hallucination in any LLM output. Score responses from GPT-4o, Claude, Gemini, Llama and 30+ models. Free tier included.

Arkheia MCP Server — Fabrication Detection for AI Agents

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.

The installer sets up a Python environment, clones the server, and configures everything. Takes about 60 seconds.

- Node.js 18+
- Python 3.10+
- An API key (free — see below)

curl -X POST https://arkheia-proxy-production.up.railway.app/v1/provision \ -H "Content-Type: application/json" \ -d '{"email": "[email protected]"}'

Save the key. You won't see it again.

{ "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/mcpwithC:/Users/YourName/.arkheia/mcp.

Add to yourclaude_desktop_config.json(macOS:~/Library/Application Support/Claude/, Windows:%APPDATA%\Claude\):

{ "mcpServers": { "arkheia": { "command": "python", "args": ["-m", "mcp_server.server"], "cwd": "~/.arkheia/mcp", "env": { "PYTHONPATH": "~/.arkheia/mcp", "ARKHEIA_API_KEY": "ak_live_your_key_here" } } } }

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/mcpwith your API key.

Restart your agent after adding the configuration.

For local Enterprise Proxy audit-log retrieval, setARKHEIA_PROXY_AUTH_TOKENto a proxy JWT session token. This is distinct fromARKHEIA_API_KEY: the MCP client sends it only toARKHEIA_PROXY_URLasAuthorization: Bearer ...for protected local endpoints such asarkheia_audit_log.

"Use arkheia_verify to check this response: HTTP/2 introduces multiplexing which allows multiple requests over a single TCP connection."

You should see aLOWrisk result — that's a truthful response.

"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 aHIGHrisk result — the Kafka 4.1 ConsumerLease API doesn't exist. Arkheia caught it.

These exercise different detection scenarios. Run them through your agent to see how it handles each:

- "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."

- "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."

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.

Copy this into your project'sCLAUDE.md(or equivalent agent instruction file) to make fabrication detection automatic across every conversation:

# Fabrication Detection This project uses Arkheia for runtime fabrication detection. The arkheia_verify MCP tool is available in every conversation. ## Verification Protocol Before presenting any substantive response to the user: 1. Call arkheia_verify with the model name, prompt, and response 2. Check the risk field in the result ### Risk Handling - LOW: Present normally - MEDIUM: Present with caveat — "Detection flagged medium confidence. Key claims should be verified." - HIGH: Do not present as-is. Investigate the specific claims. If unverifiable, regenerate or escalate. ### Sub-Agent Outputs When spawning background agents or parallel workers: - Verify each agent's output independently before merging - A HIGH risk from any agent blocks the merge until investigated - Log all detection results for audit ### What NOT to Do - Do not skip verification because the response "looks correct" - Do not suppress HIGH findings — the user needs to know - Do not retry the same prompt expecting a different risk score

A ready-to-use template file is available atCLAUDE_MD_TEMPLATE.md.

1. Draft agent generates a response 2. arkheia_verify screens the response → risk score 3. If LOW: accept 4. If MEDIUM: second agent reviews the specific claims 5. If HIGH: regenerate with a different model, or flag for human review

If your model isn't listed,let us knowand we'll characterise it. We add new models regularly.

POST https://arkheia-proxy-production.up.railway.app/v1/detect

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 touchand we'll help you set it up.

- GitHub Issues:https://github.com/arkheiaai/arkheia-mcp/issues— bugs, feature requests, questions
- Email:[email protected]— anything at all

- Website:https://arkheia.ai
- GitHub:https://github.com/arkheiaai/arkheia-mcp
- Support:[email protected]

Audited tarot, I Ching, and Xiao Liu Ren divination MCP server. Local seeded entropy; the model only interprets JSON output.