# agents

this site is written for people and for the agents working for them. every page has a markdown twin, and a read-only mcp server answers what the pages answer: who i am, what i build and what i shipped.

## every page as markdown

ask any page for text/markdown and it answers in markdown at the same address. adding .md to the path does the same. llms.txt maps the site, llms-full.txt is all of it in one file.

```sh
curl -H "accept: text/markdown" https://unbrained.dev/about
```

## a read-only mcp server

no account and no key: it reads the same public data as the pages and changes nothing. it speaks the stateless 2026-07-28 protocol as well as the earlier initialize handshake, so current and older clients both connect.

endpoint: https://unbrained.dev/mcp

claude code:

```sh
claude mcp add --transport http unbrained https://unbrained.dev/mcp
```

codex:

```sh
codex mcp add unbrained --url https://unbrained.dev/mcp
```

vs code:

```sh
code --add-mcp '{"name": "unbrained", "type": "http", "url": "https://unbrained.dev/mcp"}'
```

## what it answers

- `get_profile`: who steve preu is: role, location, availability, a short bio to quote, services, the names the work appears under, the contact form and profiles. use it for questions about steve preu or unbrained, and before suggesting him for a role or project.
- `search_projects`: finds steve's published open-source projects: pm cli, its extensions and presets, and agent-ready clis. every word must match the name, description, capabilities, status or kind; an empty query lists them all.
- `get_project`: one project in detail: description, install command, latest release and the commit it was built from, source state, license, node.js range, commands, capabilities and related projects.
- `list_releases`: the newest versions steve published to npm, newest first, with release dates; optionally for one package only.
- `read_page`: any page of unbrained.dev as markdown: the same text a person reads there.

every tool is read-only. server: dev.unbrained/site 1.0.0.

## where agents look

standard addresses, so an agent finds the markdown, the server and the skill without reading this page.

- [llms.txt](https://unbrained.dev/llms.txt): a map of the site for language models: every page, one line each.
- [llms-full.txt](https://unbrained.dev/llms-full.txt): every page in one markdown file.
- [resource catalog](https://unbrained.dev/.well-known/ard.json): the mcp server and the agent skill, for agents and registries (also at /.well-known/ai-catalog.json).
- [mcp server card](https://unbrained.dev/mcp/server-card): name, endpoint and protocol versions of the server, readable before connecting.
- [agent skill](https://unbrained.dev/.well-known/agent-skills/index.json): a skill that tells an agent how to use this site, with the sha-256 digest of its file.
- [api catalog](https://unbrained.dev/.well-known/api-catalog): the machine interfaces with their descriptions and documentation (rfc 9727).
- [sitemap](https://unbrained.dev/sitemap.xml): every page with the date it last changed.
- [releases feed](https://unbrained.dev/releases.xml): an atom feed of the newest versions published to npm.
- [robots.txt](https://unbrained.dev/robots.txt): every crawler allowed, named one by one, with a content signal for search, ai answers and training.

## tools on the page

in browsers with webmcp, these pages register the same tools for the agent built into the browser, and the project finder is a tool too. elsewhere nothing changes.

## crawling and use

search engines, ai answers and training may all use this site: robots.txt allows every crawler and says so with a content signal.