nokk
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NOKK_PROXY | No | Upstream proxy, e.g. socks5://host:1080 | |
| NOKK_NO_AUTO_SOLVE | No | 1: do not solve challenges during navigation | |
| NOKK_ROTATE_FINGERPRINT | No | 1: each session gets its own coherent fingerprint |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
A headless browser with Chrome's fingerprint. Call open first; the other tools act on the page it opened. Cloudflare challenges are solved during open. snapshot shows the page compactly with numbered controls (e12) that click and fill accept.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| openA | Load a page in the browser and wait until it has loaded. Returns the final
|
| solve_challengeA | Solve the Cloudflare challenge on the current page: the "Just a moment..."
page or a Turnstile widget, pressing its checkbox if it shows one. Only needed
when |
| challenge_stateA | Report whether the current page is behind a bot check. |
| snapshotA | Show the current page as a compact outline: headings and text in reading
order, and every link, button and form field numbered ( |
| read_textA | Return the visible text of the current page, or of the first element
matching |
| read_htmlA | Return the HTML of the current page as it is now (after its scripts ran),
or the outer HTML of the first element matching |
| clickA | Click an element: a ref from |
| fillA | Type |
| evaluateA | Run a JavaScript expression in the current page and return its value as JSON (a promise is awaited). For data the other tools do not read. |
| linksA | Return the absolute addresses of all links on the current page. |
| resetA | Close the browser session: cookies and page state are dropped, and the
next |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
The reading tools (snapshot, read_text, read_html) overlap in that all return page content, but the descriptions clearly carve out distinct roles — numbered interactive outline vs visible text vs raw HTML — and explicitly recommend snapshot over read_html. challenge_state and solve_challenge are cleanly split into report vs act, and evaluate is explicitly framed as a fallback for 'data the other tools do not read'.
All names are snake_case, which avoids casing chaos, but conventions are mixed: action verbs (open, click, fill, evaluate, reset, solve_challenge) sit alongside bare nouns (snapshot, links, challenge_state). Readable and semi-predictable (nouns for getters, verbs for actions), but not a uniform verb_noun pattern.
Eleven tools is well within the sweet spot for a browser automation server, and each has a clear, non-redundant role in the open → snapshot → act → read lifecycle. Nothing feels padded or missing at the count level.
Core lifecycle (open, solve challenge, inspect, click/fill, reset) is fully covered, but common browser operations like back/forward navigation, key presses, select/hover, and downloads lack dedicated tools. The evaluate escape hatch lets agents work around most of these gaps, so they are minor rather than blocking.