OmniBrowse-Agent

OmniBrowse-Agent

A browser research MCP server that emphasizes evidence-centric workflows, secure browser automation, and deterministic data extraction, with structured responses and artifact-based screenshots.

Category
Visit Server

README

OmniBrowse-Agent

OmniBrowse-Agent 是一个以证据为核心的浏览器研究 Agent。项目计划将 MCP 浏览器服务、 有界编排、确定性数据提取、可追溯事实和报告生成组合起来,并要求报告中的重要结论 能够引用已经登记的原始证据。

当前状态

仓库目前已经完成阶段 0 工程基线:

  • Python 3.11/3.12 工程包和依赖定义;
  • 应用、浏览器、模型能力别名、预算和数据保留策略的类型化环境配置;
  • 带有限上下文字段的结构化 JSON 或控制台日志;
  • pytest、Ruff 配置和多 Python 版本 GitHub Actions CI;
  • 带稳定错误码的 Browser MCP 结构化响应;
  • 使用本地 artifact 引用返回截图,不在工具响应中传输 base64;
  • 阻止私网、回环、链路本地和云元数据地址的本地安全出口代理。

Browser MCP 仍然保留了一些计划在阶段 1 实现的能力,包括多会话隔离、页面版本、 确定性提取工具和更完整的 artifact 生命周期管理。设计书中这些后续契约不能视为 已经实现或已经稳定。

本地开发

py -3.11 -m venv .venv
.venv\Scripts\Activate.ps1
python -m pip install -e ".[dev]"
python -m playwright install chromium
Copy-Item .env.example .env
ruff check .
pytest

配置项使用 .env.example 中记录的环境变量前缀。密钥等敏感配置应写入已被忽略的 .env 文件,禁止提交到仓库。

通过 stdio 启动已经安装的 Browser MCP 服务:

omnibrowse-browser-mcp

服务启动时不会立即启动 Chromium,只有浏览器工具被调用时才会创建浏览器实例。

开发路线图

  • 阶段 1: Browser MCP 会话隔离、页面版本、确定性提取、更完整的 artifact 生命周期 管理和稳定等待策略。
  • 阶段 2: 有界 LangGraph 编排、SQLite 事实/证据/成本账本、断点恢复和带引用报告生成。
  • 阶段 3: 按需启用的本地视觉兜底,以及 Benchmark 和成本回归测试。
  • 阶段 4: 最小可用界面、Human-in-the-Loop 流程,以及可选的检索和可观测性增强。

项目架构基线见 docs/PROJECT_DESIGN.md,开发协作规范见 AGENTS.md。

安全与成本原则

本地规则、DOM 和网络数据的优先级高于模型调用。CAPTCHA、登录、支付、提交、删除和 发布等操作必须由人工处理或确认。网页内容始终是不可信数据,不能覆盖工具权限、 安全策略或任务预算。

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured