PluginBench
MCP Server
Active
MIT

Kylas CRM MCP Server

io.github.kylastech/kylas-crm

Create, search, and manage Kylas CRM leads with AI agents via MCP.

RepositoryRegistry

What is the Kylas CRM MCP server?

The Kylas CRM MCP server enables Claude and Cursor to create, search, and manage leads in Kylas CRM. It provides tools to look up users, products, and pipelines, and to find idle leads based on activity history.

This server integrates Kylas CRM lead operations into your AI workflow. Use it to automate lead creation, search and filter leads by multiple criteria, resolve user and product names to IDs, and identify leads with no recent activity—all from Claude or Cursor without leaving your editor.

How to install Kylas CRM

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • KYLAS_API_KEY
    required
    secret

    Your Kylas API key (required)

  • KYLAS_BASE_URL

    Kylas API base URL (optional, default: https://api.kylas.io/v1)

~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "kylas-crm": {
      "command": "uvx",
      "args": [
        "kylas-crm-mcp-server"
      ],
      "env": {
        "KYLAS_API_KEY": "<YOUR_KYLAS_API_KEY>",
        "KYLAS_BASE_URL": "<YOUR_KYLAS_BASE_URL>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • get_lead_field_instructions — Get lead schema including standard fields, custom fields, and picklist IDs.
  • create_lead — Create a new lead with dynamic fields from user context.
  • search_leads — Search and filter leads by multiple criteria.
  • lookup_users — Resolve user names to IDs for owner, created by, and other user fields.
  • lookup_products — Resolve product names to IDs.
  • lookup_pipelines — Resolve pipeline names and retrieve pipeline information.
  • get_pipeline_stages — Get pipeline stages for open, closed, and won leads.
  • search_idle_leads — Find leads with no activity for a specified number of days.

Use cases

  • Automatically create new leads in Kylas from conversation context or external data sources.
  • Search and filter existing leads by name, email, status, or custom fields to find prospects matching specific criteria.
  • Identify stale leads that haven't been touched in N days to prioritize follow-up activities.
  • Look up user IDs and product IDs to populate lead fields correctly when creating or updating records.
  • Retrieve pipeline and stage information to organize leads by sales process stage.

Kylas CRM MCP server FAQ

What is the Kylas CRM MCP server?

It's an MCP server that connects Claude and Cursor to Kylas CRM, letting you create, search, and manage leads programmatically without leaving your editor.

Is it free to use?

The server itself is free and open-source. You need a Kylas CRM account and API key (Kylas pricing varies by plan).

How do I install it in Cursor or Claude Desktop?

Install via PyPI: `pip install kylas-crm-mcp-server`, then configure your MCP client to run `python -m kylas_crm_mcp` with the KYLAS_API_KEY environment variable set.

What authentication is required?

You must provide a valid Kylas API key via the KYLAS_API_KEY environment variable. Optionally set KYLAS_BASE_URL if using a custom API endpoint.

Can I use this with Docker?

Yes. Build the Docker image with `docker build -t kylas-crm-mcp .` and run it with `docker run -e KYLAS_API_KEY=your_key -i kylas-crm-mcp`.

Does it support all Kylas CRM features?

Currently it focuses on lead operations: creation, search, filtering, and lookups for users, products, and pipelines. Other CRM modules are not yet supported.

README (reference)

Source of truth, from the repository.

Kylas CRM MCP Server (Lead Only)

Model Context Protocol server for Kylas CRM lead operations. Use it from Cursor, Claude Desktop, or any MCP client to create leads, search and filter leads, and look up users, products, and pipelines.

<!-- mcp-name: io.github.kylastech/kylas-crm -->

Features

  • get_lead_field_instructions – Get lead schema (standard + custom fields, picklist IDs)
  • create_lead – Create a lead with dynamic fields from user context
  • search_leads – Search/filter leads by multiple criteria
  • lookup_users – Resolve user names to IDs (for owner, created by, etc.)
  • lookup_products – Resolve product names to IDs
  • lookup_pipelines / get_pipeline_stages – Resolve pipeline and stage for open/closed/won leads
  • search_idle_leads – Find leads with no activity for N days

Requirements

  • Python 3.10+
  • Kylas account and API key

Installation

pip install -e .
# or from PyPI (after publish): pip install kylas-crm-mcp-server

Configuration

Set environment variables (or use a .env file):

VariableRequiredDescription
KYLAS_API_KEYYesYour Kylas API key
KYLAS_BASE_URLNoAPI base URL (default: https://api.kylas.io/v1)

Running the server

The server uses stdio transport (default for MCP). Run:

python -m kylas_crm_mcp
# or: python main.py  (when developing from repo root)

MCP clients (e.g. Cursor) typically start this process and communicate via stdin/stdout.

Docker

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

Development

pip install -e ".[dev]"
pytest

Publishing to the MCP Marketplace

To publish this server to the official MCP Registry (so it appears in Cursor and other MCP clients):

  1. Publish the package to PyPI (the registry verifies ownership via your README).
  2. Install mcp-publisher and run mcp-publisher login github, then mcp-publisher publish.

See PUBLISHING.md for the full step-by-step guide.

License

See repository for license information.

Related MCP servers

TRTrue Memory Fragments logo

True Memory Fragments

Active

Detect stale source context and retain traceable code-chain understanding for AI coding agents.

2
Python
MIT
View repository →
LOLocationLists logo

LocationLists

Active

US business location data: search, sample, count, query rows or buy CSVs (Stripe or x402 USDC).

0
View repository →
NONORMA MCP Server logo

NORMA MCP Server

EU compliance corpus across 8 frameworks (NIS2, DORA, AI Act, ISO 27001 + more) via MCP.

XRXRPL Wallet Risk Score logo

XRPL Wallet Risk Score

XRPL wallet risk scoring. Behavioral tags, sub-scores, graph analysis. Pay per call in XRP.

View repository →
IOio.github.kyrylopr/lenspr logo

io.github.kyrylopr/lenspr

Maintained

Stop vibecoding blind. Code graph so your AI stops breaking things across your codebase.

0
Python
MIT
View repository →
SHshell-use logo

shell-use

Stale

Let agents use the shell like a human.

0
Python
MIT
View repository →