Prosp MCP Server
MCP server for Prosp.ai LinkedIn outreach automation. Manage leads, campaigns, messaging, and analytics programmatically.
README
Prosp MCP Server
MCP server for Prosp.ai LinkedIn outreach automation. Manage leads, campaigns, messaging, and analytics programmatically via the Model Context Protocol.
Tools (17)
Leads (8 tools)
| Tool | Description | Type |
|---|---|---|
add_lead |
Add a lead to a contact list and campaign | write |
add_lead_to_list |
Add a lead to a contact list only | write |
add_existing_lead_to_campaign |
Add an existing lead to a campaign | write |
remove_lead_from_campaign |
Remove a lead from a campaign | destructive |
delete_lead |
Permanently delete a lead from workspace | destructive |
get_leads_in_campaign |
Get all leads in a campaign | read-only |
get_lead_stage |
Get current stage of a lead in a campaign | read-only |
check_api_key |
Verify API key and connectivity | read-only |
Campaigns (5 tools)
| Tool | Description | Type |
|---|---|---|
get_all_campaigns |
List all campaigns in workspace | read-only |
get_campaign_status |
Get status of a campaign | read-only |
start_campaign |
Start a campaign | write |
stop_campaign |
Stop a running campaign | destructive |
get_analytics |
Get analytics for campaign or workspace | read-only |
Messaging (3 tools)
| Tool | Description | Type |
|---|---|---|
send_message |
Send a LinkedIn message to a profile | write |
send_voice_message |
Send a LinkedIn voice message | write |
get_conversation |
Get conversation history with a lead | read-only |
System (1 tool)
| Tool | Description | Type |
|---|---|---|
get_server_info |
Server version, config, loaded tools | read-only |
Setup
Environment Variable
export PROSP_API_KEY="your-api-key-here"
Get your API key from Prosp Settings.
Claude Desktop / Claude Code
Add to your MCP config:
{
"mcpServers": {
"prosp": {
"command": "prosp-mcp",
"env": {
"PROSP_API_KEY": "your-api-key-here"
}
}
}
}
Lazy Loading
Load only specific tool categories via TOOL_CATEGORIES:
{
"mcpServers": {
"prosp": {
"command": "prosp-mcp",
"env": {
"PROSP_API_KEY": "your-api-key-here",
"TOOL_CATEGORIES": "leads,campaigns"
}
}
}
}
Available categories: leads, campaigns, messaging
Install
pip install prosp-mcp
Or from source:
git clone https://github.com/AvolveAi/prosp-mcp.git
cd prosp-mcp
pip install -e .
Development
pip install -e ".[dev]"
pytest tests/
API Coverage
Wraps the Prosp API v1 endpoints:
| Endpoint | Tool |
|---|---|
POST /api/v1/leads |
add_lead |
POST /api/v1/leads/list |
add_lead_to_list |
POST /api/v1/leads/campaign |
add_existing_lead_to_campaign |
POST /api/v1/leads/campaign/remove |
remove_lead_from_campaign |
POST /api/v1/leads/delete |
delete_lead |
POST /api/v1/leads/campaign/list |
get_leads_in_campaign |
POST /api/v1/leads/stage |
get_lead_stage |
POST /api/v1/campaigns |
get_all_campaigns |
POST /api/v1/campaigns/status |
get_campaign_status |
POST /api/v1/campaigns/start |
start_campaign |
POST /api/v1/campaigns/stop |
stop_campaign |
POST /api/v1/analytics |
get_analytics |
POST /api/v1/messages/send |
send_message |
POST /api/v1/messages/voice |
send_voice_message |
POST /api/v1/conversations |
get_conversation |
Note: Endpoint paths are inferred from Prosp's API documentation and Zapier/Make.com integration. Some paths may need adjustment once the full OpenAPI spec is available.
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.