Jiminny MCP Server
Enables access to Jiminny sales call transcripts, AI-generated summaries, and action items directly within Cursor. Users can list recent conversations, retrieve speaker-labeled transcripts, and search for specific meeting topics using natural language.
README
Jiminny MCP Server for Cursor
Access your Jiminny sales call transcripts, summaries, and action items directly from Cursor.
What You Can Do
Ask Cursor things like:
- "List my recent Jiminny conversations"
- "Get the transcript for the call with Luc Bernard"
- "Summarize last week's SoV growth meeting"
- "Find calls where pricing was discussed"
Setup (3 minutes)
1. Clone this repo
git clone https://github.com/fzheng0222/jiminny-mcp.git
2. Open in Cursor and ask it to set up
Open the cloned folder in Cursor, then in chat type:
"Help me set up this MCP server"
Cursor will automatically:
- Install dependencies
- Walk you through getting your Jiminny token (with step-by-step instructions)
- Configure everything for you
3. Restart Cursor
Press Cmd+Shift+P → type "Reload Window" → hit Enter.
That's it! Open a new chat and try: "List my recent Jiminny conversations"
Token Expired?
If you see a 401 error, your token needs refreshing. Just ask Cursor:
"Update my Jiminny token"
It will walk you through getting a new one.
Built-in Prompts (for Sales Leaders)
These are pre-built workflows — just type the prompt name in Cursor chat:
| Prompt | What to ask Cursor |
|---|---|
| Deal Brief | "Use the deal_brief prompt for Illuvium" |
| Weekly Digest | "Use the weekly_sales_digest prompt" |
| Feature Demand | "Use the feature_demand prompt" |
- Deal Brief — Get a full brief on any deal: status, stakeholders, risks, next steps
- Weekly Digest — Monday morning summary of all calls, action items, and deals needing attention
- Feature Demand — What product features are prospects asking for most across recent calls
Available Tools
| Tool | What it does |
|---|---|
jiminny_list_conversations |
Lists recorded calls (paginated, newest first) |
jiminny_get_transcript |
Full transcript with speaker labels and timestamps |
jiminny_get_summary |
AI-generated summary, action items, and key points |
Troubleshooting
| Problem | Fix |
|---|---|
| "JIMINNY_TOKEN is not set" | Ask Cursor: "help me set up this MCP server" |
| 401 error | Token expired — ask Cursor: "update my Jiminny token" |
| 403 error | You don't have access to that conversation in Jiminny |
| Tools not showing | Restart Cursor (Cmd+Shift+P → "Reload Window") |
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。