What is kimi-webbridge?

A browser-control skill that connects an AI assistant to the user's existing browser, including its logins and cookies. It uses a local helper service and browser extension to work with open web pages.

Use it to open pages, click buttons, type into forms, collect page content, take screenshots, and investigate live website problems.

It lets the assistant interact with websites that require a real browser session instead of only reading public page data. This is useful when login state or visible page actions matter.

kimi-webbridge — Skill for Claude Code and Codex by Nimm0ny

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Nimm0ny/kimi-webbridge-mcp --skill kimi-webbridge

Clone the repo

git clone --depth 1 https://github.com/Nimm0ny/kimi-webbridge-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nimm0ny/kimi-webbridge-mcp/kimi-webbridge/github.svg)](https://agentmods.dev/skills/nimm0ny/kimi-webbridge-mcp/kimi-webbridge)

Your own site

<a href="https://agentmods.dev/skills/nimm0ny/kimi-webbridge-mcp/kimi-webbridge"><img src="https://agentmods.dev/badge/skills/nimm0ny/kimi-webbridge-mcp/kimi-webbridge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nimm0ny/kimi-webbridge-mcp/kimi-webbridge"><img src="https://agentmods.dev/badge/skills/nimm0ny/kimi-webbridge-mcp/kimi-webbridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 215 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,272 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00215	$0.02272
Opus 5.5	$0.00086	$0.00909
Sonnet 5.5	$0.00043	$0.00454
Haiku 4.5	$0.00021	$0.00227

Measured 2mo ago against content hash ff0927f2bf1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kimi-webbridge scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Prefer this over curl, ad-hoc shell, playwright scripts, or chrome-devtools when the task needs the

skills/kimi-webbridge/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kimi WebBridge

Skill = thin playbook. MCP = tools. Default profile is compact (Claude-in-Chrome sized). Prefer accuracy over calling many tools.

0. Agent 主动建链（硬前置 · 实测）

建链主体是 Agent，不是用户去点扩展。
用户侧扩展一般早已装好；MCP 挂上 ≠ 本任务已连通。Agent 必须在业务前主动调工具把链路拉起来。

链路分层

Agent  wb_*
   →  MCP (kimi-webbridge)          ensureDaemon / command
   →  本机 daemon :10086            kimi-webbridge start（按需）
   →  浏览器扩展（通常已安装）       extension_connected
   →  真实浏览器标签 / 登录态

层	谁拉起	标志
MCP 工具面	宿主已配好	能调 `wb_*`
daemon	Agent 调 `wb_status` → MCP `ensureDaemon`（未跑则 `kimi-webbridge start`）	`running=true`；`daemon_started_now` 可 true
扩展 ↔ daemon	daemon 起来后扩展自动挂上（扩展已装好时）	`extension_connected=true`
任务 session / 标签组	Agent `wb_navigate`（`group_title` + 可选 `session`）	可 `wb_list_tabs`
站点登录	用户曾登录 / 本任务遇登录页再请用户	业务页非 login

Agent 强制流程（每次要控浏览器时）

1) wb_status                    # 主动建链入口：会 ensureDaemon
2) 若 ready=true：
     → wb_navigate（首开传 group_title；业务 session 固定）
     → 后续 find/snapshot/click…
3) 若 ready=false 或 extension_connected=false：
     → 先 **Agent 侧重试**（勿立刻甩锅用户）：
         - 再调 1～3 次 wb_status（daemon 刚 start 时扩展可能晚几秒连上）
         - 仍 false：可 shell `kimi-webbridge status` / `kimi-webbridge start` 后复检 status
     → 仅多次失败才问用户：浏览器是否已打开（扩展是否在日常 profile 启用）
4) 禁止：未 wb_status 就假设可用；禁止默认话术「请你去点扩展连接」代替 Agent 建链

实测备忘（2026-08-11）

步骤	结果
仅 MCP 列出 / 未调工具	未视为已连接
`wb_status`	MCP `ensureDaemon`；可 `daemon_started_now=true`；目标 `ready=true`
`ready` 且 `extension_connected`	扩展已装场景下，daemon 起后通常为 true
`wb_navigate` + `group_title` + `session`	打开业务页 / 建立标签组（例：OA 探针成功）
扩展未装或浏览器未开	status 持续 `extension_connected=false` → 再请用户处理

实现锚点（MCP）：ensureDaemon() 在 client.js；wb_status 在 index.js 内先 ensureDaemon 再返回 ready。

`wb_status` 字段

字段	含义
`running`	daemon 是否在跑
`daemon_started_now`	本次 `wb_status` 是否刚拉起 daemon（Agent 建链痕迹）
`extension_connected`	扩展是否已挂到 daemon
`ready`	`running && extension_connected` — 业务门槛
`hint`	Ready 或未连时的提示
`default_session`	默认 session 名
`tool_profile` / `tool_count`	compact vs full

Read the full file on GitHub · 150 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/workflow.md 2.9 KB

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago Changed · +10 lines ff0927f2bf1b
2mo ago First seen · 140 lines · 215 tokens per session scan A 680228065871

Subscribe to this mod's changes

kimi-webbridge is a skill published in the GitHub repository Nimm0ny/kimi-webbridge-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 215 tokens to every session and 2,272 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Browser automation

kimi-webbridge next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
kimi-webbridgeNimm0ny/kimi-webbridge-mcp	Skill	0	2mo ago	MIT	A	215	Claude Code, Codex
interactive-loginyc-software/qm	Skill	16k	today	MIT	A	46	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex
azure-messaging-webpubsub-javamicrosoft/skills	Skill	3.2k	today	MIT	A	43	Claude Code
cua-driverdavidondrej/skills	Skill	4.3k	yesterday	MIT	A	68	Claude Code, Codex
open-design-browsercompozy/compozy	Skill	2.9k	today	MIT	A	56	Claude Code, Codex
southwestborski/travel-hacking-toolkit	Skill	906	yesterday	MIT	A	40	Claude Code

kimi-webbridge