Skip to content
Erik Bethke logo

Erik Bethke MCP server

Which servers in the official MCP registry are Erik Bethke's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-20

← Back to Erik Bethke

Whose server it is
  • Registry namecom.erikbethke/blogverified in the MCP registry

The registry name sits under erikbethke.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-20
  • Stateanswerschecked 2026-10-20
  • Tools10
  • Server calls itselferikbethke.com
  • Server version1.5.0
  • Protocol version2025-06-18

On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 248 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: Query the writing corpus through a read-only MCP server; Verify a quotation against the corpus before attributing it.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • For "Query the writing corpus through a read-only MCP server", the likely first call is search_blog_posts.
  • For "Verify a quotation against the corpus before attributing it", the likely first call is verify_quote.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 2, the first on 2026-10-20
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer834 ms
  • Space in an agent's context≈ 1,847 tokensthe definitions of all its tools (10), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 10 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · Query the writing corpus through a read-only MCP server
  • can do · Verify a quotation against the corpus before attributing it
  • not sure · Read the whole site as plain text via llms.txt

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers10 tools · read 2026-10-20
  • 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…

  • get_blog_post

    Retrieve a specific blog post from erikbethke.com by its ID or slug. Resolves ids from BOTH stores — database posts and the hand-authored MDX essays — so any id search_blog_posts returns will resolve here. Returns title, author…

  • 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…

  • 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…

  • 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…

  • verify_quote

    Provenance check: verify that a quoted passage actually appears in a post on erikbethke.com. Unscoped, it sweeps titles, summaries AND the full body of every published post — the archive back to 1993 included — and reports which field…

  • 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…

  • 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.

  • list_projects

    List interactive projects and experiments on erikbethke.com. Returns names, descriptions, statuses, URLs.

  • 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).

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "blog": {
      "type": "http",
      "url": "https://erikbethke.com/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http erikbethke https://erikbethke.com/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://erikbethke.com/api/mcp as a custom connector in the settings.

OpenAPI spec

5 paths, read 2026-10-20. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.