rad quote MCP
Enables creating projects from uploaded files directly from AI assistants. Provides tools for obtaining upload URLs and creating project import jobs from previously uploaded files.
README
rad quote MCP
The rad quote MCP server lets you create projects from uploaded files directly from your AI assistant.
Pick the install path that matches you:
| Your situation | Path |
|---|---|
| I use Claude Desktop and do not want to install Node or open a terminal | Claude Desktop UI — paste https://api.limits.run/mcp?key=<YOUR_API_KEY> into the Custom Connector form |
| I am a developer, I have Node 18+, I use Cursor / Codex / Windsurf / Claude Code | One-command CLI |
| I want a double-click install for Claude Desktop and have Node 18+ on my machine | .mcpb bundle |
One-command CLI
npx @radquote/mcp-setup@alpha install --env=stage
Requires Node 18+. Detects every supported client on your machine and writes the configuration for it. By default it configures all of them; pass --client=<id> to target one, or --pick to choose interactively.
Supported clients: claude-code, claude-desktop, cursor, windsurf, codex.
More detail: packages/setup/README.md.
Manual config snippets
If you prefer to edit configuration files yourself, copy the snippet for your client from examples/. Replace <MCP_URL> with https://api.limits.run/mcp (stage) and <YOUR_API_KEY> with your rad quote workspace API key.
What you get
Three tools appear in your AI assistant:
get_upload_url— obtain a short-lived signed URL for uploading one file.create_project_import_job— create a new project by importing tasks from previously uploaded files; optionally copy rates from an existing project as a read-only template.get_project_import_job— look up the current status of an import job by id. When the job is complete, the response containsproject_idof the newly created project; when it has failed, the response carries a human-readableerror.
And one orchestration prompt:
estimate_project_workflow— a single entry point that walks the agent through the full flow: upload the file, create the import job, poll the job every 15 seconds, and reply with a link to the resulting project (or with the failure reason). Arguments:file(required absolute local path),title,client_title,minimum_budget,source_project_id(all optional).
Workflow: create a project from a file
The estimate_project_workflow prompt packages the full recipe so you do not have to spell out the steps to the agent. Invocation depends on the client:
- Claude Code:
/mcp__radquote-stage__estimate_project_workflow, then fill infileand the optional fields. - Claude Desktop / Cursor / Windsurf: pick
estimate_project_workflowfrom your client's prompts menu and fill the arguments. - Codex: invoke via your normal MCP prompt command.
The workflow requires the agent to PUT the file to a signed URL. That means it works in clients that can run shell commands (Claude Code, Cursor, Codex, Windsurf) but not in Claude Desktop's built-in chat, which cannot perform arbitrary HTTP uploads. In Claude Desktop, upload the file some other way and then invoke
create_project_import_jobwith its public URL directly.
For reference, the PUT step looks like:
curl -X PUT --upload-file ./my-file.xlsx \
-H "Content-Type: application/vnd.openxmlformats-officedocument.spreadsheetml.sheet" \
"<upload_url>"
The response is HTTP 201 with a JSON body containing url — feed that into create_project_import_job.file.
Status
Pre-release. The production endpoint URL and the MCP Registry listing are being finalized. Currently only the stage environment (https://api.limits.run/mcp) is wired up — intended for internal QA and partner integration. Running the CLI with --env=prod prints a clear "not configured" message until production ships.
See docs/stage.md for details on the stage environment.
License
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。