Parsley MCP Server
Enables AI assistants to access buyer intent signals, MEDDIC qualification data, and lead intelligence from Parsley accounts for lead qualification and follow-up.
README
Parsley MCP Server
A Model Context Protocol server that exposes buyer intent signals, MEDDIC qualification data, and lead intelligence from your Parsley account to AI assistants like Claude Desktop and Cursor.
What it does
Ask your AI assistant natural questions about your leads:
- "Which leads went hot this week?"
- "Show me the MEDDIC gaps for recent conversations"
- "Any high-intent visitors that nobody's followed up on?"
- "What are people asking that my chatbot can't answer?"
If you also have a CRM MCP connected (Attio, HubSpot, Salesforce, etc.), Claude can cross-reference automatically - finding hot leads with no CRM follow-up, prepping you for calls with full context from both systems.
Setup
1. Get your API key
Generate an API key at parsley.id/hub/api-keys. You need a Parsley account with the chatbot enabled.
2. Configure Claude Desktop
Add to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"parsley": {
"command": "npx",
"args": ["-y", "@tryparsley/mcp-server"],
"env": {
"PARSLEY_API_KEY": "pk_live_your_key_here"
}
}
}
}
3. Configure Cursor
Add to your Cursor MCP settings (.cursor/mcp.json):
{
"mcpServers": {
"parsley": {
"command": "npx",
"args": ["-y", "@tryparsley/mcp-server"],
"env": {
"PARSLEY_API_KEY": "pk_live_your_key_here"
}
}
}
}
Environment variables
| Variable | Required | Description |
|---|---|---|
PARSLEY_API_KEY |
Yes | Your Parsley API key (pk_live_...) |
PARSLEY_BASE_URL |
No | API base URL (defaults to https://www.parsley.id) |
Tools (8)
Free tier
| Tool | Description |
|---|---|
get_analytics_summary |
Dashboard overview - profile views, conversations, lead quality breakdown, top topics, conversion rate |
Business tier
| Tool | Description |
|---|---|
get_conversations |
List recent conversations with filtering by lead quality, intent signal, date range |
get_conversation_detail |
Full conversation detail - MEDDIC signals with evidence quotes, engagement, enrichment |
get_hot_leads |
Hot and warm leads with MEDDIC evidence - the morning briefing tool |
search_by_intent |
Find conversations by MEDDIC signals, intent score, or topic |
get_knowledge_gaps |
Unanswered chatbot questions grouped by topic and frequency |
get_lead_enrichment |
Extracted company, role, timeline, and budget context from conversations |
get_meddic_summary |
Aggregate MEDDIC signal distribution - per-signal counts, top combinations |
Prompts (5)
Predefined workflow templates that appear in Claude's prompt picker.
| Prompt | Cross-MCP | Description |
|---|---|---|
morning_briefing |
Yes | Hot leads summary with follow-up priorities. Cross-references CRM if connected. |
stale_leads_check |
Yes | Qualified leads with no recent CRM activity. Requires a CRM MCP. |
coaching_gaps |
No | MEDDIC gaps with suggested follow-up questions for each lead. |
content_opportunities |
No | Knowledge gaps turned into blog post, chatbot doc, and FAQ suggestions. |
deal_prep |
Optional | Pre-call briefing on a company/person. Pulls CRM context if available. |
Cross-MCP workflows
Prompts marked "Cross-MCP" work with any CRM that has an MCP server. Connect both Parsley and your CRM's MCP to Claude, and the prompts will orchestrate across both automatically. No extra configuration needed.
Tested with: Attio, HubSpot, Salesforce, Copper, Pipedrive.
Tier gating
- Free plan:
get_analytics_summarytool only - Business plan: All 8 tools + all 5 prompts
Upgrade at parsley.id/pricing.
Development
git clone https://github.com/peterjduffy/parsley-mcp.git
cd parsley-mcp
npm install
npm run build
PARSLEY_API_KEY=pk_live_xxx node dist/index.js
License
MIT
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.
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.
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.
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.