Observed MCP server

troth

A persistent AI partner MCP server that keeps identity, memory, goals and refusals in a local SQLite substrate, renting language work from Claude, ChatGPT, Kimi, local models or any BYOK OpenAI-compatible provider, with governed shell/fs/http tools, MCP "hands" gated by state-transition-validated cognition, loopback-only security, and tamper-evident audit.

Security score

—/100

Awaiting a completed comparable scan.

Seven-category assessment pending: authentication, tool poisoning, prompt injection, dangerous capabilities, dependency risk, data exfiltration, and transport security.

Score history

Pending

Immutable methodology-versioned snapshots

Schema drift

Pending

No normalized tool schema observed

Fingerprint

Pending

Repository/package-backed identity

Public findings

No public findings recorded

This is not a safety claim. Check the coverage and revision status before relying on absence of findings.