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.

Oya Browser

REMOTE · OYABROWSER.COM

Real Chrome for coding agents over MCP: browse, replay playbooks, human takeover, HIPAA & BAA.

Available components

+3 this week 84 Trust /100

Last scanned (2 hours ago)

Scores higher than 84% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Browser Automation

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security94
Transport & Reachability100
Schema Quality & AI Usability74
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1880 tokens (~58/item across 32 items; 32 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
  • 93% 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
  • We read all 32 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 32 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
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

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.

  • 21 Nov 26 0
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 20 Nov 26 +1
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 19 Nov 26 0
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 18 Nov 26 0
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 17 Nov 26 +1
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 16 Nov 26 0
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 15 Nov 26 +1
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 14 Nov 26 0
    • This server's schema is too large to store in full, so we cannot compare its tools day to day 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 21 Nov 2026 · Probed https://oyabrowser.com/mcp/pool

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=oyabrowser.com CN=YE2,O=Let's Encrypt,C=US 19 Nov 2026 17 Feb 2027 ECDSA 256 ECDSA-SHA384 5d2b770995740b5723f9aacf686917f2b59
SANs: *.oyabrowser.com, oyabrowser.com
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of oyabrowser.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
oyabrowser.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Enforced and verified

The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.

Result Enforced and verified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer resource_metadata="https://oyabrowser.com/.well-known/oauth-protected-resource/mcp/pool"

Bearer resource_metadata="https://oyabrowser.com/.well-known/oauth-protected-resource/mcp/pool"
Header Value
strict-transport-security max-age=31536000; includeSubDomains

Protected resource metadata

Document https://oyabrowser.com/.well-known/oauth-protected-resource/mcp/pool
Retrieved Yes
Resource https://oyabrowser.com/mcp/pool
Authorisation server https://oyabrowser.com/

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://oyabrowser.com/mcp/pool Verified 200
http (plaintext) http://oyabrowser.com/mcp/pool HTTPS enforced 308 https://oyabrowser.com/mcp/pool
MCP tools · 32 exposed · ~1,880 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
analyze_page ~144

Analyze the current page. Returns its content and every interactive element with an id to use with click/type tools. Ids stay valid until the next analysis or a navigation, so one analysis covers a whole form; each analysis numbers the page afresh. plus page facts (url, title, viewport, scroll, and when they apply: panelScroll, modal, covered, truncated) and each element's state (off-screen, disabled, checked, a field's hint). format picks how it is written: toon (default; one table of blocks, fewer tokens), markdown or jsonl.

NameTypeReqDescription
formatstring–How the page is written; the server default when left out

No output schema declared.

No examples provided.

click ~36

Click an interactive element by its ID number (from analyze_page results).

NameTypeReqDescription
element_idnumberyesThe element ID number from analyze_page

No output schema declared.

No examples provided.

click_coordinates ~64

Click at specific x,y pixel coordinates on the page. Use when you know the exact position (e.g. from a screenshot).

NameTypeReqDescription
xnumberyesX coordinate in pixels from the left edge
ynumberyesY coordinate in pixels from the top edge

No output schema declared.

No examples provided.

complete_mfa ~50

Fill and submit a one-time code (MFA / 2FA) the page asks for, from the persona's authenticator, email or SMS. Call it on a code prompt after signing in.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

double_click ~68

Double-click an element by ID or at specific x,y coordinates.

NameTypeReqDescription
element_idnumber–Element ID to double-click (from analyze_page)
xnumber–X coordinate (used if no element_id)
ynumber–Y coordinate (used if no element_id)

No output schema declared.

No examples provided.

drag ~70

Drag from one point to another. Useful for sliders, drag-and-drop, or selecting text.

NameTypeReqDescription
from_xnumberyesStart X coordinate
from_ynumberyesStart Y coordinate
to_xnumberyesEnd X coordinate
to_ynumberyesEnd Y coordinate

No output schema declared.

No examples provided.

find ~65

Find the elements that match a description ("search box", "add to cart", "next page"), best first, with ids click and type accept. Much shorter than analyze_page when you know what you are looking for.

NameTypeReqDescription
querystringyesThe words the element is known by

No output schema declared.

No examples provided.

go_back ~32

Go back one page in the tab's history, like the browser's back button, and wait for it to load.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

go_forward ~24

Go forward one page in the tab's history and wait for it to load.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

handle_dialog ~58

Answer a native browser dialog (confirm or prompt) blocking the page. Alerts are answered automatically.

NameTypeReqDescription
acceptbooleanyestrue clicks OK, false clicks Cancel
prompt_textstring–Text to enter, for a prompt dialog only

No output schema declared.

No examples provided.

hover ~45

Move the mouse onto an element, for menus, tooltips and previews that open on hover. Tells you what appeared.

NameTypeReqDescription
element_idnumberyesElement ID from analyze_page

No output schema declared.

No examples provided.

keyboard_type ~36

Type text using the keyboard without targeting a specific element. Types into whatever is currently focused.

NameTypeReqDescription
textstringyesText to type

No output schema declared.

No examples provided.

list_playbooks ~30

List the playbooks saved on this key: recorded flows that replay without a model, with their variables.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_saved_logins ~53

List the sites this browser's persona has a saved login for, with the username, never the password. Call it before a sign-in to know whether sign_in can fill the form and which account it will use.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

mouse_move ~55

Move the mouse cursor to specific x,y coordinates without clicking. Useful for triggering hover states, tooltips, or dropdown menus.

NameTypeReqDescription
xnumberyesX coordinate in pixels
ynumberyesY coordinate in pixels

No output schema declared.

No examples provided.

navigate ~26

Navigate the browser to a URL.

NameTypeReqDescription
urlstringyesThe URL to navigate to

No output schema declared.

No examples provided.

pool_status ~15

Show pool size and connected browsers.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

press_key ~78

Press a safe navigation key. Allowed: Enter, Escape, Tab, ArrowDown, ArrowUp, ArrowLeft, ArrowRight, Backspace, Delete, Space, Home, End, PageUp, PageDown. Do NOT use for F-keys, Meta, Control, Alt, or Shift.

NameTypeReqDescription
keystringyesKey to press

No output schema declared.

No examples provided.

reload ~27

Reload the page and wait for it to load. For a page stuck loading or showing stale data.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

run_playbook ~80

Replay a saved playbook on this browser with the given variables. Much faster and cheaper than doing the task step by step; a step that no longer fits the page is finished by the agent.

NameTypeReqDescription
namestringyesThe playbook, from list_playbooks
variablesobject–Values for its variables; its defaults fill the rest

No output schema declared.

No examples provided.

run_script ~141

Run JavaScript that READS the page and returns data, for what analyze_page does not show well: every row of a long table, attributes, counts, text across many elements. The body of an async function: `return` the value (JSON-serialisable, cut at 8000 chars). It runs where the page cannot see it and must not change anything: no clicks, typing, requests or navigation; act with the element tools, which replay. Example: return [...document.querySelectorAll('table tr')].map(r => r.innerText);

NameTypeReqDescription
scriptstringyesThe function body; `return` what you want to read

No output schema declared.

No examples provided.

run_task ~83

Hand a whole task to Oya's own browser agent on this browser and get its report back (DONE: or FAILED:). Uses this key's configured model; the run can be saved as a playbook afterwards.

NameTypeReqDescription
dataobject–Values the task uses, referred to as {{name}}
taskstringyesWhat to do, in plain words

No output schema declared.

No examples provided.

screenshot ~19

Capture a screenshot of the visible browser tab as an image.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

scroll ~37

Scroll the page up or down.

NameTypeReqDescription
amountnumber–Pixels to scroll (default 500)
directionstringyesScroll direction

No output schema declared.

No examples provided.

select_option ~69

Choose an option in a native dropdown (a select element from analyze_page) by the option text you see. Accepts {{placeholders}} and filters.

NameTypeReqDescription
element_idnumberyesThe select element ID from analyze_page
optionstringyesThe visible text of the option to choose

No output schema declared.

No examples provided.

sign_in ~45

Sign in on the current page with the credentials stored for this site in the browser's persona. You never see them. Call it on a login form you were not given values for.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

solve_captcha ~46

Solve a CAPTCHA (reCAPTCHA, hCaptcha, Turnstile) on the current page with the configured solver. Call it when a CAPTCHA blocks you, then analyze_page again.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

start_browser ~97

Start a new browser on this key and make it the one every other tool drives. Uses the key's configured provider unless one is given. It costs a session until stop_browser.

NameTypeReqDescription
namestring––
personastring–Persona id, 'auto' (least recently used under its concurrency cap) or 'default'
providerstring––
urlstring–Navigate here once the browser is ready

No output schema declared.

No examples provided.

stop_browser ~33

Stop a browser and release its session. Defaults to the browser the tools are driving.

NameTypeReqDescription
browser_idstring––

No output schema declared.

No examples provided.

type ~72

Type text into an input element by its ID number (from analyze_page results). Clears existing content first. Typing keeps every id valid: fill the next field straight away, without analyzing again.

NameTypeReqDescription
element_idnumberyesThe element ID number from analyze_page
textstringyesThe text to type

No output schema declared.

No examples provided.

wait ~50

Wait for an element matching a CSS selector to appear on the page.

NameTypeReqDescription
selectorstringyesCSS selector to wait for
timeoutnumber–Max wait time in ms (default 10000)

No output schema declared.

No examples provided.

wait_for ~132

Wait until the page is ready: some text shows, the url contains something, and/or the network has gone quiet. With no text or url it waits for the network to settle. Use it after an action that loads results in the background, rather than analyzing again and again.

NameTypeReqDescription
network_idleboolean–Also wait for no new requests for a moment
textstring–Text that must appear on the page
timeoutnumber–Max wait in ms (default 10000, at most 20000)
urlstring–Part of the url the page must reach

No output schema declared.

No examples provided.

Install

How do I install the Oya Browser MCP server?

Oya Browser is a hosted endpoint at https://oyabrowser.com/mcp/pool, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · oyabrowser.com

# add to Claude Code
claude mcp add --transport http oyadotai-oya-browser 'https://oyabrowser.com/mcp/pool'
Common questions

What is the Oya Browser MCP server?

Oya Browser is an MCP server listed in the public MCP registry as io.github.OyadotAI/oya-browser. Real Chrome for coding agents over MCP: browse, replay playbooks, human takeover, HIPAA & BAA. This page covers its hosted endpoint (https://oyabrowser.com/mcp/pool).

Is the Oya Browser MCP server safe to use?

Oya Browser scores 84 out of 100 on VerifyMCP. 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 Oya Browser MCP server expose?

Oya Browser exposes 32 tools: select_option, run_script, wait_for, find, hover, and 27 more. Their descriptions and schemas cost roughly 1,880 tokens of context every time the server is loaded.

Does the Oya Browser MCP server require authentication?

Yes. Oya Browser asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the Oya Browser MCP server still maintained?

Oya Browser is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Oya Browser MCP server?

VerifyMCP ran 13 checks on Oya Browser, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.