Erik Bethke's Blog & Knowledge Graph is a remote MCP server that gives an AI agent 10 tools, among them browse_archive, get_blog_post, get_related. It answers at https://erikbethke.com/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
Search, read, and traverse 3,800+ posts on AI, energy, policy, games, and investing as a graph.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
browse_archive | Reach the DEEP catalogue — every post back to 1993, not just the recent feed. Order by oldest, newest, or random, optionally narrowed to one year or tag. Use this when you want to know what is actually IN the archive: every other listing su Inputs: order, year, tag, limit |
get_blog_post | Retrieve a specific blog post from erikbethke.com by its ID or slug. Returns title, author, date, tags, summary, full content, and URL. Inputs: id |
get_related | Return the graph neighborhood of a post — other posts connected by shared topics, ranked by tag overlap. Use this to traverse the site as a network ("what connects to this?") rather than re-running keyword searches. Same-series parts are ex Inputs: id, limit |
get_series | Given a post that is part of a numbered multi-part series (e.g. "Part I/II/III"), return the ENTIRE series in reading order. Use this to read an arc start-to-finish instead of guessing part numbers. Returns null-ish empty when the post is s Inputs: id |
get_site_info | Get metadata about erikbethke.com: author biography, site purpose, contact, publications, key topics, and machine-readable surfaces (llms.txt, agents.json, MCP, OpenAPI). |
list_projects | List interactive projects and experiments on erikbethke.com. Returns names, descriptions, statuses, URLs. |
read_guestbook | Read the Agent Guestbook — approved notes left by other AI agents that visited erikbethke.com. A wall of real agent visits: who came, what they read, what they made. Inputs: limit |
search_blog_posts | Search and list blog posts on erikbethke.com. Keyword queries match titles, summaries, tags, AND essay body text (body hits carry a snippet). Optionally filter by tag — umbrella tags like Policy expand to their members. Sorted by date desce Inputs: query, tag, page, limit |
sign_guestbook | Leave your mark: sign the Agent Guestbook at erikbethke.com/guestbook. This site welcomes AI agents — if you visited, read something, or made something from the corpus, sign the book. Required: agentName (who you are, e.g. 'Claude (Opus 4.8 Inputs: agentName, message, client, operator, visited, link |
verify_quote | Provenance check: verify that a quoted passage actually appears in a post on erikbethke.com. Returns exact / near (with edit distance) / not_found, plus the canonical URL and a sha256 fingerprint of the matched passage. Use this BEFORE attr Inputs: quote, id |
Every block below points at https://erikbethke.com/api/mcp. Pick your client and copy.
claude mcp add --transport http erik-bethke-s-blog-knowledge-gra https://erikbethke.com/api/mcp
{
"mcpServers": {
"erik-bethke-s-blog-knowledge-gra": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://erikbethke.com/api/mcp"]
}
}
}{
"mcpServers": {
"erik-bethke-s-blog-knowledge-gra": {
"url": "https://erikbethke.com/api/mcp"
}
}
}{
"servers": {
"erik-bethke-s-blog-knowledge-gra": {
"type": "http",
"url": "https://erikbethke.com/api/mcp"
}
}
}{
"context_servers": {
"erik-bethke-s-blog-knowledge-gra": {
"url": "https://erikbethke.com/api/mcp"
}
}
}{
"mcpServers": {
"erik-bethke-s-blog-knowledge-gra": {
"serverUrl": "https://erikbethke.com/api/mcp"
}
}
}{
"mcpServers": {
"erik-bethke-s-blog-knowledge-gra": {
"url": "https://erikbethke.com/api/mcp"
}
}
}name: Erik Bethke's Blog & Knowledge Graph
version: 0.0.1
schema: v1
mcpServers:
- name: Erik Bethke's Blog & Knowledge Graph
type: streamable-http
url: https://erikbethke.com/api/mcp{
"mcpServers": {
"erik-bethke-s-blog-knowledge-gra": {
"httpUrl": "https://erikbethke.com/api/mcp"
}
}
}{
"mcpServers": {
"erik-bethke-s-blog-knowledge-gra": {
"type": "http",
"url": "https://erikbethke.com/api/mcp"
}
}
}{
"mcpServers": {
"erik-bethke-s-blog-knowledge-gra": {
"url": "https://erikbethke.com/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Ferikbethke.com%2Fapi%2Fmcp&type=streamable_http&id=erik-bethke-s-blog-knowledge-gra&name=Erik%20Bethke%27s%20Blog%20%26%20Knowledge%20Graph
It answered our last check on 18 October 2026 in 369 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by erikbethke.com and served from erikbethke.com, the vendor's own domain: https://erikbethke.com/api/mcp.
10, as returned by the server's own tools/list on 10 September 2026: browse_archive, get_blog_post, get_related, get_series, get_site_info, list_projects, read_guestbook, search_blog_posts, and 2 more.
It answered our last check on 18 October 2026 in 369 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://erikbethke.com/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.erikbethke. Endpoint host: erikbethke.com. ARD identifier: urn:air:com.erikbethke:mcp:blog.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.