MCP server that fetches and converts website pages into clean markdown for agents, with sitemap-based discovery, disk caching, and polite crawling (robots.txt, rate limiting).
Enables AI agents to exchange structured work items with an auditable lifecycle, supporting send, acknowledge, block, complete, and cancel operations via a shared SQLite-backed inbox.
A Model Context Protocol server that gives AI agents bounded, auditable access to propose changes to an Obsidian vault stored in GitHub, with per-agent expiring tokens, read/write/deny path policies, mutability rules, frontmatter checks, and human-reviewed proposal branches.
An MCP server that builds structured research source packs for a topic, extracting verified facts, quotes, numbers, dates, and primary links with a coverage map of claims across sources.
A local-first MCP server that lets AI agents use gated APIs without holding keys, enforcing declarative policies, injecting secrets server-side, and auditing access without content.