Kylas CRM

io.github.kylastechPublished by GitHub account kylastechv1.0.4Updated Oct 24, 2026

MCP server for Kylas CRM: create, search, and manage leads. Requires KYLAS_API_KEY.

VerifiedSTDIODesktop onlyProductivity & WorkflowBusiness & Commerce

Overview

AI-generated overview

Kylas CRM MCP server that lets an AI assistant create, search and filter CRM leads and look up users, products and pipelines.

What you can do
Create leads with standard and custom fields taken from the conversation context, after reading the lead schema and picklist IDs from the server's field instructions tool. Search and filter leads by multiple criteria, including finding idle leads with no activity for a set number of days. Resolve user names to IDs for owner and creator fields. Resolve product names to IDs. Resolve pipelines and their stages for open, closed and won leads.
When to use it
Useful when you work in Kylas CRM and want an assistant to add leads, run filtered lead searches, or find stale leads without leaving the chat client. It is lead-focused, so it suits sales follow-up and lead hygiene rather than full CRM administration.
Requirements
Runs locally as a Python package (Python 3.10+) over stdio, started by the MCP client or via Docker. Needs a Kylas account and an API key supplied in the KYLAS_API_KEY environment variable. KYLAS_BASE_URL is optional and defaults to the Kylas API endpoint. Network access to the Kylas API is required.
Before you install
The server holds a Kylas API key in KYLAS_API_KEY, which grants access to your CRM data; keep it out of shared configs and logs. Creating leads writes real records into your CRM, so review what the assistant submits. Lead and lookup queries send CRM data to the Kylas API endpoint configured in KYLAS_BASE_URL.

Installation

In SourceWeft

  1. Open Kylas CRM in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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.

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

bash
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:

bash
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

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

Development

bash
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.

Source: README.md at commit fae3d47

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.4LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts