Kitsune
PYPI · KITSUNE-BROWSER-MCP
Let your coding agent use the Firefox, Zen, or LibreWolf browser you already have open.
Available components
Last scanned (15 minutes ago)
Scores higher than 58% of PyPI servers
Category Browser Automation
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security50
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 0 of 14 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 1 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability75
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 2584 tokens (~95/item across 27 items; 27 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management40
- Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage98
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 95% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 28 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 4 Nov 26 +16
- Malware scan: unverified → pass ▲ security
- 3 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- Tool coverage: 100% → 95% ▼ functional
- Package version: 0.7.1 → 0.7.2 functional
- 2 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.
- 31 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 29 Oct 26 0
- Malware scan: pass → unverified ▼ security
- Package version: 0.7.0 → 0.7.1 functional
- 28 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
- 26 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed pypi/kitsune-browser-mcp@0.7.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 14 packages
| Packages resolved | 14 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
browser_ask_user ~81
Ask the user to do what you cannot: sign in, pass a CAPTCHA (human_check), click a control that ignores your clicks (trusted_input), or choose (other).
| Name | Type | Req | Description |
|---|---|---|---|
| message | string | yes | What the user should do, addressed to them. |
| reason | string | yes | – |
| tab_id | integer | – | Default: current tab. |
No output schema declared.
No examples provided.
browser_click ~100
Perform click on a web page
| Name | Type | Req | Description |
|---|---|---|---|
| button | string | – | Button to click, defaults to left |
| doubleClick | boolean | – | Whether to perform a double click instead of a single click |
| element | string | – | Human-readable element description used to obtain permission to interact with the element |
| modifiers | array | – | Modifier keys to press |
| target | string | yes | Exact target element reference from the page snapshot, or a unique element selector |
No output schema declared.
No examples provided.
browser_close ~12
Close the page
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
browser_console_messages ~106
Returns all console messages
| Name | Type | Req | Description |
|---|---|---|---|
| all | boolean | – | Return all console messages since the beginning of the session, not just since the last navigation. Defaults to false. |
| filename | string | – | File name to save the console messages to. Relative file names are resolved against the workspace root. If not provided, messages are returned as text. |
| level | string | yes | Level of the console messages to return. Each level includes the messages of more severe levels. Defaults to "info". |
No output schema declared.
No examples provided.
browser_drag ~106
Perform drag and drop between two elements
| Name | Type | Req | Description |
|---|---|---|---|
| endElement | string | – | Human-readable target element description used to obtain the permission to interact with the element |
| endTarget | string | yes | Exact target element reference from the page snapshot, or a unique element selector |
| startElement | string | – | Human-readable source element description used to obtain the permission to interact with the element |
| startTarget | string | yes | Exact target element reference from the page snapshot, or a unique element selector |
No output schema declared.
No examples provided.
browser_drop ~142
Drop files or MIME-typed data onto an element, as if dragged from outside the page. At least one of "paths" or "data" must be provided.
| Name | Type | Req | Description |
|---|---|---|---|
| data | object | – | Data to drop, as a map of MIME type to string value (e.g. {"text/plain": "hello", "text/uri-list": "https://example.com"}). |
| element | string | – | Human-readable element description used to obtain permission to interact with the element |
| paths | array | – | Absolute paths to files to drop onto the element. |
| target | string | yes | Exact target element reference from the page snapshot, or a unique element selector |
No output schema declared.
No examples provided.
browser_emulate_media ~112
Emulate CSS media features for the page, for example switch between the light and dark color scheme. Omitted parameters are left unchanged; null clears an override.
| Name | Type | Req | Description |
|---|---|---|---|
| colorScheme | – | – | Emulates the prefers-color-scheme media feature |
| contrast | – | – | Emulates the prefers-contrast media feature |
| forcedColors | – | – | Emulates the forced-colors media feature |
| media | – | – | Changes the CSS media type of the page |
| reducedMotion | – | – | Emulates the prefers-reduced-motion media feature |
No output schema declared.
No examples provided.
browser_evaluate ~121
Evaluate JavaScript expression on page or element
| Name | Type | Req | Description |
|---|---|---|---|
| element | string | – | Human-readable element description used to obtain permission to interact with the element |
| filename | string | – | File name to save the result to. Relative file names are resolved against the workspace root. If not provided, result is returned as text. |
| function | string | yes | () => { /* code */ } or (element) => { /* code */ } when element is provided |
| target | string | – | Exact target element reference from the page snapshot, or a unique element selector |
No output schema declared.
No examples provided.
browser_file_upload ~46
Upload one or multiple files
| Name | Type | Req | Description |
|---|---|---|---|
| paths | array | – | The absolute paths to the files to upload. Can be single file or multiple files. If omitted, file chooser is cancelled. |
No output schema declared.
No examples provided.
browser_fill_form ~25
Fill multiple form fields
| Name | Type | Req | Description |
|---|---|---|---|
| fields | array | yes | Fields to fill in |
No output schema declared.
No examples provided.
browser_find ~185
Search the accessibility snapshot of the current page for text or a regular expression. Returns matching snapshot nodes with a few lines of surrounding context (like search snippets), each shown under its path from the root of the tree, which is cheaper than capturing the whole snapshot when you only need to locate an element and its ref.
| Name | Type | Req | Description |
|---|---|---|---|
| filename | string | – | Save results to a file instead of returning them in the response. Relative file names are resolved against the workspace root. |
| regex | string | – | Regular expression to search for in the page snapshot. Matching is case-sensitive by default; wrap the pattern in slashes to add flags, e.g. "/error/i" for case-insensitive. Provide either text or re… |
| text | string | – | Plain text to search for in the page snapshot (case-insensitive substring match). Provide either text or regex, not both. |
No output schema declared.
No examples provided.
browser_handle_dialog ~44
Handle a dialog
| Name | Type | Req | Description |
|---|---|---|---|
| accept | boolean | yes | Whether to accept the dialog. |
| promptText | string | – | The text of the prompt in case of a prompt dialog. |
No output schema declared.
No examples provided.
browser_hover ~55
Hover over element on page
| Name | Type | Req | Description |
|---|---|---|---|
| element | string | – | Human-readable element description used to obtain permission to interact with the element |
| target | string | yes | Exact target element reference from the page snapshot, or a unique element selector |
No output schema declared.
No examples provided.
browser_navigate ~26
Navigate to a URL
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The URL to navigate to |
No output schema declared.
No examples provided.
browser_navigate_back ~20
Go back to the previous page in the history
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
browser_network_request ~118
Returns full details (headers and body) of a single network request, or a single part if `part` is set. Use the number from browser_network_requests.
| Name | Type | Req | Description |
|---|---|---|---|
| filename | string | – | File name to save the result to. Relative file names are resolved against the workspace root. If not provided, output is returned as text. |
| index | integer | yes | 1-based index of the request, as printed by browser_network_requests. |
| part | string | – | Return only this part of the request. Omit to return full details. |
No output schema declared.
No examples provided.
browser_network_requests ~117
Returns a numbered list of network requests since loading the page. Use browser_network_request with the number to get full details.
| Name | Type | Req | Description |
|---|---|---|---|
| filename | string | – | File name to save the network requests to. Relative file names are resolved against the workspace root. If not provided, requests are returned as text. |
| filter | string | – | Only return requests whose URL matches this regexp (e.g. "/api/.*user"). |
| static | boolean | yes | Whether to include successful static resources like images, fonts, scripts, etc. Defaults to false. |
No output schema declared.
No examples provided.
browser_press_key ~44
Press a key on the keyboard
| Name | Type | Req | Description |
|---|---|---|---|
| key | string | yes | Name of the key to press or a character to generate, such as `ArrowLeft` or `a` |
No output schema declared.
No examples provided.
browser_resize ~37
Resize the browser window
| Name | Type | Req | Description |
|---|---|---|---|
| height | number | yes | Height of the browser window |
| width | number | yes | Width of the browser window |
No output schema declared.
No examples provided.
browser_resume ~108
Continue a call whose result has call and resume_token (a needs_user stop, batch, parallel or workflow); nothing that ran ok is sent again.
| Name | Type | Req | Description |
|---|---|---|---|
| call | integer | yes | – |
| observed | object | – | Unknown container step's progress path ("0.1") -> "not_applied" (send again) or "applied" (mark ok). |
| resume_token | string | yes | – |
| wait | number | – | Seconds to wait for the user, 0-300. |
No output schema declared.
No examples provided.
browser_run_code_unsafe ~144
Run a Playwright code snippet. Unsafe: executes arbitrary JavaScript in the Playwright server process and is RCE-equivalent.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | – | A JavaScript function containing Playwright code to execute. It will be invoked with a single argument, page, which you can use for any page interaction. For example: `async (page) => { await page.ge… |
| filename | string | – | Load code from the specified file. Relative file names are resolved against the workspace root. If both code and filename are provided, code will be ignored. |
No output schema declared.
No examples provided.
browser_select_option ~82
Select an option in a dropdown
| Name | Type | Req | Description |
|---|---|---|---|
| element | string | – | Human-readable element description used to obtain permission to interact with the element |
| target | string | yes | Exact target element reference from the page snapshot, or a unique element selector |
| values | array | yes | Array of values to select in the dropdown. This can be a single value or multiple values. |
No output schema declared.
No examples provided.
browser_snapshot ~125
Capture accessibility snapshot of the current page, this is better than screenshot
| Name | Type | Req | Description |
|---|---|---|---|
| boxes | boolean | – | Include each element's bounding box as [box=x,y,width,height] in the snapshot. Coordinates are viewport-relative, in CSS pixels (Element.getBoundingClientRect) |
| depth | number | – | Limit the depth of the snapshot tree |
| filename | string | – | Save snapshot to a file instead of returning it in the response. Relative file names are resolved against the workspace root. |
| target | string | – | Exact target element reference from the page snapshot, or a unique element selector |
No output schema declared.
No examples provided.
browser_tabs ~86
Manage tabs; request a handoff.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| confirm_token | string | – | request: approval token. |
| index | number | – | Tab index (close defaults to current). |
| reason | string | – | request: reason shown to user. |
| tab_id | integer | – | request: ID instead of index. |
| url | string | – | new: URL. |
No output schema declared.
No examples provided.
browser_take_screenshot ~236
Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.
| Name | Type | Req | Description |
|---|---|---|---|
| element | string | – | Human-readable element description used to obtain permission to interact with the element |
| filename | string | – | File name to save the screenshot to. Relative file names are resolved against the workspace root. If not specified, the screenshot is saved into the output directory as `page-{timestamp}.{png|jpeg|we… |
| fullPage | boolean | – | When true, takes a screenshot of the full scrollable page, instead of the currently visible viewport. Cannot be used with element screenshots. |
| scale | string | yes | Image resolution scale. "css" produces a screenshot sized in CSS pixels (smaller, consistent across devices). "device" produces a high-resolution screenshot using device pixels (larger, accounts for… |
| target | string | – | Exact target element reference from the page snapshot, or a unique element selector |
| type | string | – | Image format for the screenshot. If unset, inferred from the filename extension, otherwise png. |
No output schema declared.
No examples provided.
browser_type ~118
Type text into editable element
| Name | Type | Req | Description |
|---|---|---|---|
| element | string | – | Human-readable element description used to obtain permission to interact with the element |
| slowly | boolean | – | Whether to type one character at a time. Useful for triggering key handlers in the page. By default entire text is filled in at once. |
| submit | boolean | – | Whether to submit entered text (press Enter after) |
| target | string | yes | Exact target element reference from the page snapshot, or a unique element selector |
| text | string | yes | Text to type into the element |
No output schema declared.
No examples provided.
browser_wait_for ~68
Wait for text to appear or disappear or a specified time to pass
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | – | The text to wait for |
| textGone | string | – | The text to wait for to disappear |
| time | number | – | The time to wait in seconds, at most 30 |
No output schema declared.
No examples provided.
How do I install the Kitsune MCP server?
Kitsune runs locally as a PyPI package, launched with uvx kitsune-browser-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · kitsune-browser-mcp
claude mcp add junyeong-nero-kitsune -- uvx kitsune-browser-mcp
What is the Kitsune MCP server?
Kitsune is an MCP server listed in the public MCP registry as io.github.junyeong-nero/kitsune. Let your coding agent use the Firefox, Zen, or LibreWolf browser you already have open. This page covers its PyPI package (kitsune-browser-mcp).
Is the Kitsune MCP server safe to use?
Kitsune scores 61 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Kitsune MCP server expose?
Kitsune exposes 27 tools: browser_resume, browser_ask_user, browser_close, browser_resize, browser_console_messages, and 22 more. Their descriptions and schemas cost roughly 2,464 tokens of context every time the server is loaded.
Is the Kitsune MCP server still maintained?
Kitsune is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Kitsune MCP server under?
Kitsune declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.