Kylas MCP. Manage your sales pipeline through conversation.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Kylas MCP Server. Manage your entire sales lifecycle inside your AI client. This server connects your CRM data—leads, contacts, and deals—to your agent, letting you track pipeline health, create records, and monitor team performance using natural conversation.
It's built for sales teams that need visibility and action without opening the dedicated CRM dashboard.
What your AI agents can do
Create contact
Adds a new person record to the CRM contact database.
Create lead
Generates a new lead record in the system.
Get lead
Retrieves specific data for a single lead using its ID.
You can list all existing leads, get details on a specific lead, or create new leads and assign them to the pipeline.
The server allows you to list all contacts in the database, create new ones, and view their complete communication history.
Retrieve a list of all deals, or examine the details of specific deals, to monitor their value and stage.
List all scheduled CRM tasks, letting you see what follow-ups or actions are due.
The AI client processes complex requests to show conversion rates and deal velocity across the funnel.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Kylas MCP Server: 7 Tools for Sales Automation
These seven tools let your AI agent interact with your CRM, allowing you to manage leads, contacts, deals, and tasks through natural conversation.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Kylas on Vinkius019dd114create contact
Adds a new person record to the CRM contact database.
019dd114create lead
Generates a new lead record in the system.
019dd114get lead
Retrieves specific data for a single lead using its ID.
019dd114list contacts
Shows a list of all contact records in the CRM.
019dd114list deals
Displays a list of all active deals currently in the pipeline.
019dd114list leads
Shows a list of all leads in the Kylas system.
019dd114list tasks
Retrieves a list of all scheduled CRM tasks.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Kylas, then connect any of our 4,800+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,800+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Kylas. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 7 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Checking your CRM means opening another tab.
Today, to see if a prospect is ready for a proposal, you have to jump into Kylas, navigate to the 'Leads' section, filter by status, and then cross-reference the associated contacts in another tab. If you want to see the whole picture, you’re copying data from five different dashboards into a single spreadsheet.
With the Kylas MCP Server, you just ask your agent: 'Show me the deals closing this week.' It runs the necessary tools and gives you a single, concise report. You get the data instantly, right in the chat.
List_contacts: Pulling full history in seconds.
Before calling a prospect, you usually open the CRM, search by email, and then scroll through pages of notes, emails, and past activities to piece together the person's journey. This takes time and you often miss key details.
Now, your agent uses the `list_contacts` tool. It retrieves the full history and key details immediately. It doesn't just give you a name; it gives you the context of the last activity, which is what matters.
What you can do with this MCP connector
This server lets your AI client run your entire sales process without ever opening the Kylas dashboard. You'll manage leads, track deals, and update contacts just by talking to your agent. You've got access to every core CRM function—listing leads, building contacts, or checking deal values—all from your chat window.
Manage Leads
Your AI client can show you every lead currently in the system using list_leads, and you can pull up all the details for a specific one using get_lead. You can also whip up new prospects and get 'em into the pipeline by running create_lead.
Track Contacts
Want to see who you're talking to? You can pull a full list of every contact in the database with list_contacts. Need to add someone new? Just run create_contact to build a new person record. You can also view that contact's whole history by asking your agent to check their communication records.
View Deal Progress
Check out the whole deal pipeline by calling list_deals to see every active deal. You can also drill down into the specifics of any single deal using the agent when you need to know its current value or stage.
Manage Sales Tasks
You can see what's due next by listing all scheduled CRM tasks with list_tasks, letting you know which follow-ups or actions you gotta take.
Your agent processes complex requests to show conversion rates and deal velocity across the funnel, giving you a full view of your pipeline's health.
019dd114-69bc-710c-b952-65d5527a69d9 
How Kylas MCP Works
- 1 Subscribe to the Kylas server and provide your API Key.
- 2 Your AI client sends a natural language request (e.g., 'Show me all deals in the negotiation stage').
- 3 The server executes the necessary tool call (
list_deals) and returns the structured data to your agent for a conversational answer.
The bottom line is, your AI client talks to the CRM, and the server handles the translation into actions, so you never have to switch apps.
Who Is Kylas MCP For?
This is for sales professionals who spend too much time clicking through dashboards. It’s for the BDR who needs to quickly check a prospect’s history before a call, the Sales Manager who needs to monitor pipeline health without opening the dedicated CRM, or the VP of Sales who just wants a quick status report on team performance.
Checks a prospect’s communication history or lists current leads to prepare talking points before a cold call.
Requests a summary of team performance, checking conversion rates or listing deals in a specific pipeline stage to manage capacity.
Creates a new contact for a client, adds it to the database, and then lists all deals associated with that company.
What Changes When You Connect
- Monitor your entire deal pipeline instantly. Instead of clicking through 15 stages, ask the agent to
list_dealsand see total value, deal count, and stage breakdowns in one prompt. - Keep your data current without opening the CRM. Use
create_contactorcreate_leadto log new information—like a website lead or a meeting follow-up—directly from your chat window. - Know exactly who you're talking to.
list_contactspulls up a person's full history, including past activities and communications, so you never miss context. - Track team performance metrics on the fly. Ask the agent to summarize pipeline conversion rates or check team deal counts without needing a dedicated dashboard view.
- Manage follow-ups effortlessly. Use
list_tasksto see all scheduled follow-ups, ensuring no prospect falls through the cracks because you forgot to open the CRM.
Real-World Use Cases
The End-of-Day Pipeline Review
The Sales Manager needs to know if the team hit its quarterly target. They ask the agent to 'Show the pipeline and deals closing this week.' The server runs complex logic, aggregating data from list_deals and list_leads, and gives a clear, actionable report on win rates and deal totals.
The Prospecting Follow-Up
A BDR finds a new company website. They ask the agent to 'Create a new lead for NovaTech and list all contacts at acmecorp.com.' The agent runs create_lead and then list_contacts, solving the need for immediate, contextual data gathering.
The Deal Qualification Check
An Account Executive is about to propose a deal. They ask the agent to 'What is the full history for John Smith at Acme Corp?' The agent uses list_contacts and get_lead to pull up all past interactions and deals, ensuring the proposal is highly personalized.
The Quick Data Entry
You just got a name and email from a networking event. Instead of opening Kylas, you tell your agent: 'Create a contact for Jane Doe.' The agent executes create_contact instantly, logging the data without context switching.
The Tradeoffs
Trying to list everything manually
Manually navigating to the Leads tab, then the Contacts tab, and then opening the Deals dashboard just to get a high-level view of the week's activity.
→ Just ask your agent: 'Show the sales pipeline and deals closing this week.' The agent runs the necessary tools and compiles all the data into one report.
Assuming leads and contacts are the same
Trying to use list_leads to find a person's full communication history, which is a contact function, resulting in incomplete data.
→
Use list_leads for prospect status and list_contacts for historical records. If you need both, tell your agent to combine the reports.
Forgetting to assign a deal stage
Creating a deal record but failing to specify its current stage or expected value, making it useless for forecasting.
→ Always ensure your prompt includes the necessary context, like 'Create a deal for $50K in the Proposal stage.' This helps the agent use the tools correctly.
When It Fits, When It Doesn't
Use this if you need to interact with your CRM data—creating, reading, or listing leads, contacts, or deals—without leaving your current chat interface. The server handles the full lifecycle, from create_lead to list_tasks.
Don't use this if you need to perform deep data analysis that requires custom BI tools or if you need to update complex data fields that aren't exposed by the simple tools. If you only need to view raw, exportable data, a direct API connection might be better. This is for operational workflow support, not deep data science.
Common Questions About Kylas MCP
How do I use the `create_lead` tool in the Kylas MCP Server? +
You tell your agent to create the lead and provide the necessary details in the prompt. The agent handles the JSON structure required by the tool, so you just write naturally. It logs the new lead in the system.
Can I get a list of all contacts using the `list_contacts` tool? +
Yes. The list_contacts tool pulls up every contact in the CRM. You can then ask follow-up questions about that list, like 'Show me all contacts at TechCo.'
What is the difference between `list_leads` and `list_contacts`? +
The list_leads tool shows your raw list of prospects and their current status. list_contacts focuses on the individuals, showing their activity history and communication records.
How do I check deals using the `list_deals` tool? +
The list_deals tool fetches all active deals. You can filter this list by stage, value, or closing date, giving you a real-time view of the pipeline.
Can I list tasks using the `list_tasks` tool? +
Yes, list_tasks pulls all scheduled CRM tasks. This helps you manage follow-ups and make sure no action item gets missed before a meeting.
How do I use the `get_lead` tool to find a specific lead's details? +
You pass the lead ID to get_lead. This retrieves all specific details for that single lead, including status and assigned owner. It's faster than listing all leads when you know the ID you need.
What data can I process using `create_contact`? +
You provide the contact's necessary information, like name, company, and title. The tool handles the creation and ensures it's logged correctly in the CRM database.
Is there a way to list deals that are currently in the 'Proposal' stage using `list_deals`? +
You specify the desired pipeline stage when calling list_deals. This filters the results to show only deals currently at that exact stage, helping you focus your efforts.
Can I manage leads and track deals? +
Yes. List, create, and update leads with status tracking. Browse deals across pipeline stages with deal values and probability.
Can I monitor pipeline conversion rates? +
Yes. Track pipeline metrics including deal counts per stage, conversion rates, average deal size, and velocity.
What API endpoint does Kylas use? +
Bearer authentication against api.kylas.io/v1.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.