DiffBeam MCP Server
Enables AI agents and engineering tools to validate and simulate Gaussian beam optical systems, search component catalogs, and create immutable design links for optical design workflows.
README
DiffBeam by Gaussian Beam
DiffBeam is a deterministic Gaussian beam optics service for AI agents and engineering tools. It validates and solves multi-element optical systems, searches local component catalogs, creates immutable design links, and publishes capability-bound live previews to the Gaussian Beam planner.
DiffBeam does not host or proxy a language model. Bring any compatible AI client.
Remote MCP server
- Endpoint:
https://api.gaussian-beam.com/mcp/ - Registry name:
com.gaussian-beam/diffbeam - Human-readable documentation: https://gaussian-beam.com/mcp/
- Machine-readable manifest: https://gaussian-beam.com/.well-known/mcp/server.json
- Contracts: https://gaussian-beam.com/mcp/contracts/
MCP clients can connect directly with Streamable HTTP. Public tools include validation, deterministic simulation, fiber and lens search, schema discovery, and immutable design-link creation. Workspace tools require a temporary capability created by the user in the planner.
No-install Direct Agent Bridge
An internet-capable AI that can send HTTPS POST requests does not need native MCP installation. The planner's Connect your AI dialog creates a workspace-specific endpoint, temporary scoped credential, and ready-to-copy prompt. The normal flow is:
get_workspacepreview_workspace_design- explain the calculated preview
- apply only after user authorization
Read the Direct Agent Bridge guide. Never put a workspace credential in a URL, public page, model configuration, log, or repository.
Public MCP tools
validate_optical_systemsimulate_optical_systemsearch_fiberssearch_fiber_collimatorssearch_lensesget_optical_system_schemacreate_design_link
Capability-bound workspace tools:
get_workspacepreview_workspace_designapply_workspace_designlist_workspace_revisionsrestore_workspace_revision
Worked optical-design guides
- 4F Gaussian beam expander
- Fiber collimation from mode-field diameter
- Gaussian waist placement
- Practical focal-length selection
- MCP examples
Repository scope
This public repository contains discovery metadata and integration documentation. It deliberately contains no production credentials, private workspace data, telemetry, or deployment configuration. The documents and examples are licensed under Apache-2.0.
Security issues should be reported privately as described in SECURITY.md.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。