home / mcp / kylas crm mcp server lead only

Kylas CRM MCP Server Lead Only

A Python MCP server enabling lead operations for Kylas CRM through standard MCP clients with lead creation, search, and lookups.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "akshaykylas94-mcp": {
      "command": "python",
      "args": [
        "-m",
        "kylas_crm_mcp"
      ],
      "env": {
        "KYLAS_API_KEY": "YOUR_API_KEY",
        "KYLAS_BASE_URL": "https://api.kylas.io/v1"
      }
    }
  }
}

You can run the Kylas CRM MCP Server for lead operations to create, search, and manage leads along with resolving related data such as users, products, and pipelines. This MCP server enables any compatible MCP client to interact with Kylas CRM through a defined set of endpoints, making lead workflows efficient and centralized.

How to use

You will run the MCP server locally or in a container and connect to it with any MCP client (such as Cursor or Claude Desktop). The server exposes functions to create leads, search and filter leads, fetch field instructions, and look up related data like users, products, and pipelines. Use the client to issue calls that correspond to the available tools: get lead field instructions, create a lead with dynamic context fields, search leads by multiple criteria, and resolve owner or created-by users, product IDs, and pipeline stages.

How to install

Prerequisites you need before installing the MCP server:

Python 3.10 or newer

Install the MCP server package in editable mode or fetch it from PyPI:

pip install -e .
# or from PyPI after publishing
pip install kylas-crm-mcp

Additional setup and running

Configure your environment with your Kylas API key and optional base URL. You will need these values when starting the server.

# Example environment setup (values to be replaced by your own)
export KYLAS_API_KEY=YOUR_API_KEY
export KYLAS_BASE_URL=https://api.kylas.io/v1

Start the MCP server

Run the server as a standard MCP stdio server using Python. The server runs and communicates with MCP clients through standard input and output.

python -m kylas_crm_mcp
# or when developing from the repository root
python main.py

Docker (optional)

You can run the MCP server in Docker by setting the API key through an environment variable.

docker build -t kylas-crm-mcp .
docker run -e KYLAS_API_KEY=your_key -i kylas-crm-mcp

Development

If you are actively developing, you can install development dependencies and run tests to validate changes.

pip install -e ".[dev]"
pytest

License

License information is available in the project repository and should be consulted for permissible use and distribution.

Available tools

get_lead_field_instructions

Fetch the lead schema including standard and custom fields, plus available picklist IDs.

create_lead

Create a new lead using dynamic fields sourced from the user context.

search_leads

Filter and search leads using multiple criteria to refine results.

lookup_users

Resolve user names to IDs for fields like owner or created by.

lookup_products

Resolve product names to IDs for associating products with leads.

lookup_pipelines

Resolve pipelines and get their stages for open, closed, or won leads.

get_pipeline_stages

Retrieve the stages within a given pipeline to classify lead progress.

search_idle_leads

Find leads with no activity for a specified number of days.