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") |
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.