"author:ChristofMilius" matching MCP servers:

Provides agents with MCP tools for typed probabilistic decisions—Choice, Noul, and Score—with calibrated probabilities and abstention, using local OpenAI-compatible models via LM Studio logprobs.

Enables MCP-aware agents to fetch documentation pages, strip navigation noise, convert HTML to clean markdown, and emit or return timestamped .md files ready for LLM contexts.

Enables AI agents to read, send, and reply to GPG-encrypted email over IMAP/SMTP, manage a contact book with key provenance, and archive and search everything read. Key material and message bodies are kept out of the model's context window, with encryption enforced by default.