Connects Claude to your Parsley account to query buyer intent signals, MEDDIC qualification data, and chatbot conversation history. You get eight tools covering everything from hot lead lists and MEDDIC gap analysis to knowledge base suggestions from unanswered questions. The free tier gives you analytics summaries, while paid plans unlock conversation search, enrichment data, and five cross-MCP prompts that can orchestrate between Parsley and your CRM (Attio, HubSpot, Salesforce) to find qualified leads with no follow-up or prep for calls with full context. Useful for morning sales briefings, identifying coaching opportunities, and turning chatbot gaps into content ideas without leaving your AI assistant.
Public tool metadata for what this MCP can expose to an agent.
get_conversationsList recent chatbot conversations with filtering by lead quality, intent signal, and date range.4 paramsList recent chatbot conversations with filtering by lead quality, intent signal, and date range.
daysnumberlimitnumberlead_qualitystringhot · warm · coldintent_signalstringhigh_intent · evaluation · research · supportget_conversation_detailGet full details of a single conversation including MEDDIC signals, engagement metrics, and enrichment data.1 paramsGet full details of a single conversation including MEDDIC signals, engagement metrics, and enrichment data.
conversation_idstringget_hot_leadsGet all hot and warm leads with MEDDIC evidence. The morning briefing tool.2 paramsGet all hot and warm leads with MEDDIC evidence. The morning briefing tool.
daysnumberinclude_warmbooleanget_analytics_summaryDashboard-level overview: views, conversations, lead counts, conversion rate.1 paramsDashboard-level overview: views, conversations, lead counts, conversion rate.
daysnumbersearch_by_intentFind conversations matching specific MEDDIC signals, intent score, or topic.4 paramsFind conversations matching specific MEDDIC signals, intent score, or topic.
daysnumbertopicstringmeddic_signalsarraymin_intent_scorenumberget_knowledge_gapsSurface unanswered questions from chatbot conversations, grouped by topic.3 paramsSurface unanswered questions from chatbot conversations, grouped by topic.
daysnumberlimitnumbertopicstringget_lead_enrichmentGet extracted company, role, timeline, and budget context from conversations.2 paramsGet extracted company, role, timeline, and budget context from conversations.
daysnumberhas_companybooleanget_meddic_summaryAggregate MEDDIC signal distribution across all conversations.1 paramsAggregate MEDDIC signal distribution across all conversations.
daysnumberA 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.
Ask your AI assistant natural questions about your leads:
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.
Generate an API key at parsley.id/hub/api-keys. You need a Parsley account with the chatbot enabled.
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"
}
}
}
}
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"
}
}
}
}
| 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) |
| Tool | Description |
|---|---|
get_analytics_summary | Dashboard overview - profile views, conversations, lead quality breakdown, top topics, conversion rate |
| 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 |
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. |
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.
get_analytics_summary tool onlyUpgrade at parsley.id/pricing.
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
MIT
PARSLEY_API_KEY*secretYour Parsley API key (starts with pk_live_). Generate one at parsley.id/hub/api-keys