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
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| 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": "python",
"args": [
"-m",
"mcp_server.server"
],
"cwd": "~/.arkheia/mcp",
"env": {
"PYTHONPATH": "~/.arkheia/mcp",
"ARKHEIA_API_KEY": "YOUR_ARKHEIA_API_KEY"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| PYTHONPATH | Declared in the maintainer’s client configuration. | Check documentation |
| ARKHEIA_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
Queries the NIST National Vulnerability Database (NVD) via its API.
Scans projects for security vulnerabilities and automatically updates vulnerable dependencies using Trivy.
Remote MCP for C2PA intake verifier MCP, structured receipts, audit logs, and reviewer-ready evidenc
MCP gateway that adds per-tool RBAC and an exportable audit log to any MCP server, plus per-tenant isolation, PII redaction on tool results, per-tenant rate limits, and tenant-level allow/deny…
Administer Keycloak via its Admin REST API: users, roles, clients, groups, IdP, events.
Read-only access to VAAST vulnerability scan findings, workspaces, and targets for AI agents