Every pillar, one tag. The range, not a skills list.
A fleet of thirteen small servers that give agents real hands. What they wrap, the two house styles I build them in, and why they all start read-only.
A marketing API exposes 115 operations; my server hands the agent six tools. The boundary is set by token budget and model focus, not REST purity.
A catalogue of the guards I actually ship: typed confirmations, blast-radius escalation, pay-to-play gating, ordered workflows, and read-only by default.
The thing you want an agent to drive only has a CLI. execFile it, hand back stdout, and put bounds on the call so it cannot eat your process.
You want an MCP server that exposes one read-only tool plus one destructive variant an agent cannot trip into by accident. Zod schema is the fence.
An MCP server that drives a Dokku PaaS over SSH.
An MCP server for Google Search Console properties, sitemaps, and analytics.
An MCP server that posts, verifies, and deletes tweets as one author account.
An MCP server that generates and edits images by driving the local Codex CLI.
An MCP server for Netlify sites, deploys, and build debugging.
An MCP server over my projects, money, and time data.
An MCP server for MongoDB backups, restores, and read queries.
An MCP server for the Mailchimp Marketing API.
An MCP server for S3 buckets, objects, and static website hosting.
An MCP server for GoDaddy domains and DNS records.
An MCP server for Parse Server over its REST API.
An MCP server for Cloudflare DNS, zones and records.
An MCP server for GitHub Issues, Actions, Environments, and repo secrets.
whisper_schedule