Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.xidik12/oculo

NPM · OCULO-MCP

AI-powered native browser with 12 MCP tools. ~30 tokens per page.

Available components

0 this week 82 Trust /100

Last scanned (6 hours ago)

Scores higher than 72% of npm servers

Category Browser Automation

Trust breakdown (7 categories)

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 Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 30 of 92 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability72
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2226 tokens (~139/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "shell" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 17 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
Changelog

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.

  • 28 Oct 26 +1
    • Stability: 0.97 → pass security
  • 27 Oct 26 −1
    • Stability: pass → 0.97 functional
  • 21 Oct 26 +1
    • Stability: 0.97 → pass security
  • 20 Oct 26 −1
    • Stability: pass → 0.97 functional
  • 17 Oct 26 +3
    • Stability: 0.83 → pass security
  • 15 Oct 26 −3
    • Stability: pass → 0.80 functional
  • 14 Oct 26 +1
    • Stability: 0.97 → pass security
  • 12 Oct 26 +1
    • Security disclosure: unverified → fail ▼ functional
Diagnostics

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 npm/oculo-mcp@0.4.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 92 packages
Packages resolved 92
Stale 30
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 16 exposed · ~1,993 tokens

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 →

Tool Tokens
abort ~50

Cancel a pending tool call by callId, or pass callId="all" to cancel everything.

NameTypeReqDescription
callIdstringyesThe call ID to cancel, or "all" to cancel all pending calls

No output schema declared.

No examples provided.

act ~595

Perform an action in Oculo browser: click, navigate, scroll, press key, hover, type, login. Elements found by ref (from a11y snapshot), text, role, label, placeholder, or CSS selector. After click/navigate/back/forward/reload, returns fresh ref-tagged snapshot. Use newTab with background=true to open tabs without switching, then use tabId to run actions in parallel.

NameTypeReqDescription
actionstringyesAction to perform
amountnumber–Scroll amount in pixels
attributestring–Attribute name for getAttribute action
autoSubmitboolean–Auto-submit after login (default: true)
backgroundboolean–For newTab: open in background without switching (default: false). Returns tab ID for parallel execution.
clearboolean–Clear existing content before typing (for type action). Works with both regular inputs and contenteditable fields.
contentstring–File content for writeFile action
cookiesarray–Cookies array for importCookies action
directionstring–Scroll direction
expressionstring–JavaScript expression for evaluate action
fromobject–Drag source: {x, y} or {text, selector}
keystring–Key to press (Enter, Tab, Escape, etc.)
labelstring–Label text associated with the element
modifiersarray–Modifier keys (Ctrl, Shift, Alt, Meta)
namestring–Accessible name of the element
nthnumber–Which match to use (0-indexed, default: 0)
placeholderstring–Placeholder text of the input
proxyobject–Proxy config for setProxy action: {type, host, port, username?, password?, bypass?}
refstring–Element ref from a11y snapshot (e.g. "e5"). Preferred over text/selector — use page({detail:"a11y"}) first.
rolestring–ARIA role (button, link, textbox, etc.)
screenshotboolean–Attach screenshot after action
selectorstring–CSS selector (fallback)
sitestring–Site domain for login action (uses credential vault)
tabIdstring–Target a specific tab by ID (for parallel execution). Omit for active tab.
textstring–Visible text on the element to interact with
toobject–Drag target: {x, y} or {text, selector}
urlstring–URL for navigate action
valuestring–Value for select action, file path for readFile/writeFile
xnumber–X coordinate for clickAtPoint/drag
ynumber–Y coordinate for clickAtPoint/drag

No output schema declared.

No examples provided.

fill ~129

Fill form fields in Oculo browser by label, placeholder, or data-placeholder text. Handles text, select, checkbox, textarea, and contenteditable (DraftJS, ProseMirror). Use visible labels as keys.

NameTypeReqDescription
fieldsobjectyesObject mapping field label → value (e.g. {"Email": "hi@oculo.com"})
screenshotboolean–Attach screenshot after filling
submit––Submit form. true = first submit button, string = button text
tabIdstring–Target a specific tab by ID (for parallel execution). Omit for active tab.

No output schema declared.

No examples provided.

lens ~55

Visual analysis of the current page via screenshot. Describe what you see or answer questions about the page visually.

NameTypeReqDescription
questionstringyesWhat to analyze or look for in the page
tabIdstring–Target tab ID

No output schema declared.

No examples provided.

media ~204

Generate images (Nano Banana 2 / DALL-E 3) or videos (Veo 3.1) via Oculo. Returns saved file path. Supports image-to-image editing with reference image.

NameTypeReqDescription
durationnumber–Video duration: 4, 6, or 8 seconds
imagestring–Path to reference image for image-to-image editing/transformation (Gemini only)
modelstring–Image model: nano-banana-2 (default), nano-banana-pro, nano-banana
promptstringyesWhat to create
providerstring–Override: gemini, openai, stability
sizestring–Image: 1024x1024, 2K, 4K. Video: 16:9, 9:16
stylestring–natural, vivid, cinematic, anime
typestringyesGenerate an image or video

No output schema declared.

No examples provided.

page ~195

Describe the current page in Oculo browser. Default: compact (~30-80 tokens). Use detail="a11y" for ref-tagged accessibility tree — interactive elements get [ref=e1],[ref=e2]... refs usable in act tool. Use detail="markdown" for full article content as clean markdown.

NameTypeReqDescription
detailstring–compact (default ~30-80 tokens), a11y (ref-tagged accessibility tree ~200-500 tokens), or markdown (article extraction via Readability)
includearray–What to include: "forms", "buttons", "links", "headings", "text", "images"
scopestring–CSS selector to scope description to a section of the page
screenshotboolean–Attach a screenshot (default: false)
tabIdstring–Target a specific tab by ID (for parallel execution). Omit for active tab.

No output schema declared.

No examples provided.

preview ~43

Pre-fetch a URL without navigating. Returns page description without leaving current page.

NameTypeReqDescription
tabIdstring–Target tab ID
urlstringyesURL to preview

No output schema declared.

No examples provided.

read ~127

Extract structured data from the page in Oculo browser (search results, tables, lists, articles).

NameTypeReqDescription
fieldsarray–Specific fields to extract
formatstring–Output format (default: text)
limitnumber–Max items to return (default: 10)
scopestring–CSS selector to narrow extraction scope
tabIdstring–Target a specific tab by ID (for parallel execution). Omit for active tab.
whatstringyesWhat to extract: "search results", "products", "table data", etc.

No output schema declared.

No examples provided.

research ~65

Deep web research on a topic. Opens multiple tabs, reads pages, synthesizes findings.

NameTypeReqDescription
depthnumber–Research depth (1-3). Default: 2
tabIdstring–Target tab ID
topicstringyesResearch topic or question

No output schema declared.

No examples provided.

run ~231

PREFERRED for any task with 2+ actions. Executes a multi-step pipeline in a SINGLE call — use this instead of multiple act/fill calls. Example — post on X: run({steps:[{act:{action:"navigate",url:"https://x.com/compose/post"}},{wait:{timeout:2000}},{act:{action:"type",text:"Hello world",role:"textbox"}},{act:{action:"click",text:"Post",role:"button"}}]}). Each step is an object with exactly ONE key: page, act, fill, read, wait, or if. Cached for replay.

NameTypeReqDescription
descriptionstring–Short description for caching
returnAllboolean–Return results from all steps (default: false)
stepsarray–Array of steps. Each step is an object with exactly ONE key: page, act, fill, read, wait, or if.
tabIdstring–Target a specific tab by ID (for parallel execution). Omit for active tab.
workflowstring–Replay a cached workflow by ID

No output schema declared.

No examples provided.

shell ~72

Execute a shell command (ls, npm, git, node, python, etc.) via Oculo and return stdout+stderr. Non-interactive only.

NameTypeReqDescription
commandstringyesThe shell command to execute
timeoutnumber–Timeout in milliseconds (default: 30000, max: 120000)

No output schema declared.

No examples provided.

status ~24

List all pending tool calls with their callId, toolName, and elapsed time.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

tabs ~29

List all open browser tabs with their URLs and titles.

NameTypeReqDescription
tabIdstring–Target tab ID

No output schema declared.

No examples provided.

translate ~65

Translate page content or specific text to another language.

NameTypeReqDescription
tabIdstring–Target tab ID
textstring–Text to translate (omit for full page)
tostringyesTarget language code (e.g., "en", "es", "zh")

No output schema declared.

No examples provided.

webmcp_call ~63

Call a WebMCP tool registered by the current page. Use webmcp_list first to discover available tools.

NameTypeReqDescription
argsobject–Arguments to pass to the tool
namestringyesTool name to call (from webmcp_list)

No output schema declared.

No examples provided.

webmcp_list ~46

Discover WebMCP tools registered by the current page via navigator.modelContext.registerTool() or <form toolname="..."> elements. Returns list of available page-declared tools.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Install

How do I install the io.github.xidik12/oculo MCP server?

io.github.xidik12/oculo runs locally as an npm package, launched with npx -y oculo-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · oculo-mcp

# add to Claude Code
claude mcp add xidik12-oculo -- npx -y oculo-mcp
Common questions

What is the io.github.xidik12/oculo MCP server?

io.github.xidik12/oculo is an MCP server listed in the public MCP registry as io.github.xidik12/oculo. AI-powered native browser with 12 MCP tools. ~30 tokens per page. This page covers its npm package (oculo-mcp).

Is the io.github.xidik12/oculo MCP server safe to use?

io.github.xidik12/oculo scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. 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 io.github.xidik12/oculo MCP server expose?

io.github.xidik12/oculo exposes 16 tools: page, act, fill, read, run, and 11 more. Their descriptions and schemas cost roughly 1,993 tokens of context every time the server is loaded.

Is the io.github.xidik12/oculo MCP server still maintained?

io.github.xidik12/oculo 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 io.github.xidik12/oculo MCP server under?

io.github.xidik12/oculo declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.