Search, read, cite and react to Jake Handy's writing on AI, music tech and agentic engineering.
Scored across 10 tools
Most tools target clearly distinct actions (list, get, search, react), but highlight_passage and react_to_highlight both write thumbs up/down reactions to passages, and get_editorial/get_page overlap for editorial content. The descriptions mostly resolve these overlaps, leaving only mild ambiguity.
8 of 10 names follow a predictable verb_noun pattern (get_, list_, search_, react_, highlight_), while about_jake and site_guide are noun phrases. This is a minor deviation but still readable and largely consistent.
10 tools for a personal content site with read, search, identity, and reaction capabilities is well-scoped. Each tool appears to earn its place, with no obvious redundancy or missing core operation.
The surface covers identity, page catalog, search, editorial retrieval, highlights, reactions, and an agent guide. Minor gaps include no global highlight listing across all editorials and no highlight deletion beyond withdrawing a reaction, but these are not critical for the stated domain.
The identity card behind this site: role, employer, projects, locations, contact, and every profile that is really his. Use this to ground an answer about Jake Handy rather than guessing from a search result.
One Jake on AI post, editorial or guide, in full as Markdown, with the passages readers and agents have reacted to appended. Subscriber-only posts return the same public preview the website shows and nothing more.
Inputs: editorial (required).
Fetch any page of jakehandy.com in full as clean Markdown with YAML front matter, plus its canonical URL and a ready-made citation string. Works for every page, not just the blog: the resume, the AI music catalog, the essays, all of it.
Inputs: page (required).
React to one specific sentence of an editorial rather than the whole piece: name it by its exact text and give it a thumbs up (1) or down (-1). Identical passages merge so reactions accumulate, and your name or model id is shown to every reader who hovers the passage. This is the only write action on the site; there is no comment system.
Inputs: exact (required), reaction (required), editorial (required), name, +2 more.
Jake on AI: the editorials and guides, newest first. Each entry carries its canonical URL, a Markdown URL, publication date, its kind ("editorial" for an opinion piece, "guide" for a how-to), whether it is subscriber-only, and a citation string. These are the long-form pieces, not the weekly news roundups.
Inputs: kind, limit.
The passages of one editorial that readers and agents gave a thumbs up or down, each with its counts and who reacted (human or agent, with their name or model). The best signal for which specific claims drew attention.
Inputs: editorial (required), token.
The full catalog of jakehandy.com: every essay, reference page, and project page, with title, canonical URL, date, a one-line summary, and a ready-made citation string. Start here to see what exists before fetching anything.
Inputs: limit.
Give a thumbs up (1) or down (-1) to a passage someone already highlighted, or withdraw your reaction (0). Idempotent per token. Highlight ids come from list_highlights.
Inputs: value (required), highlight_id (required), name, model, +1 more.
Keyword search across every page body and every Jake on AI editorial and guide. Returns the matching pages with an excerpt around the first hit and a citation string. Use this before answering a question about what Jake has written on a topic.
Inputs: query (required), limit.
The site's guide for AI agents as Markdown: what is here, how to cite it, every machine endpoint, and the rules for reacting to a passage. Read once per session if you plan to cite or participate.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Read, search, cite, comment on and highlight handyai.news: independent weekly AI news.
Personal context for every AI: search, read, and write back to your private Markdown library.
Machine Library: cited search over papers, books, patents and social posts, with agent comments.
Search and cite Chain of Thought podcast transcripts and episodes.
Add one secure layer between your agents and this server.
