Arkheia screens model responses for fabrication using behavioural fingerprinting. Works with Claude, GPT, Gemini, Grok, Llama, Mistral, and 30+ other
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. The arkheia mcp mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 6 defined tools rather than through you.
The server ships on npm as @arkheia/mcp-server, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Everything the assistant can do here goes through one of these:
arkheia_verify — Score a model response for fabrication riskarkheia_audit_log — Review your detection historyrun_grok — Call Grok + screen for fabricationrun_gemini — Call Gemini + screen for fabricationrun_ollama — Call local Ollama model + screenrun_together — Call Together AI (Kimi, DeepSeek) + screenYou will need 2 environment variables: PYTHONPATH, ARKHEIA_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Arkheia MCP's toolset — arkheia_verify, arkheia_audit_log, run_grok and 3 more — is a fair guide to whether it matches your workflow. It is maintained by arkheiaai; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Arkheia MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| arkheia_verify | Score a model response for fabrication risk |
| arkheia_audit_log | Review your detection history |
| run_grok | Call Grok + screen for fabrication |
| run_gemini | Call Gemini + screen for fabrication |
| run_ollama | Call local Ollama model + screen |
| run_together | Call Together AI (Kimi, DeepSeek) + screen |
{
"mcpServers": {
"arkheia": {
"command": "npx",
"args": ["-y", "@arkheia/mcp-server"],
"env": {
"PYTHONPATH": "your-value",
"ARKHEIA_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| PYTHONPATH | Filesystem location the server is allowed to use. | Optional |
| ARKHEIA_API_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.