Overview

The Zylo MCP Server connects your AI assistant of choice directly to your Zylo data, so your team can query your SaaS portfolio, generate insights, and get answers in plain language—right inside the tools you already use. Instead of exporting your data and waiting on a BI analyst to build a report, you can just ask.

MCP (Model Context Protocol) is an open standard that lets AI assistants connect to external tools and data sources. Think of it as a universal adapter: instead of Zylo building a custom integration for every AI tool on the market, we expose our data through a single MCP server that any MCP-capable assistant—Claude, ChatGPT, Gemini, or others—can connect to. Setting up MCP for your organization means anyone on your team can connect their assistant to this same server when you configure access below.

After connecting, your Zylo users can ask your AI assistant things like:

"Show me all applications and their annual costs."
"What's my total SaaS spend by department?"
"Which contracts are expiring in the next 90 days?"
"Create a $150,000 annual budget for Salesforce."

Your assistant doesn't just hand back raw data—it can analyze it, summarize it, and help you build reports, all in the same conversation.

What you get

Enabling MCP for your organization unlocks:

A natural language interface for your SaaS portfolio—no query language to learn
Real-time access to your live Zylo data, not a stale export
Complex, multi-resource queries (applications, contracts, spend, and more) in a single question
Granular permissions, so OAuth access matches each user's Zylo permissions and API key access is limited to the key's configured scopes
Secure, encrypted communication between your assistant and Zylo, authenticated end to end

How it works

Your AI assistant authenticates with the Zylo MCP server using either OAuth 2.0 with PKCE or an API key—you'll choose one during setup.
When your Zylo users ask a question, the assistant selects the right Zylo tool for the job (see the Tools Reference) and sends the request over Streamable HTTP transport.
Zylo executes that operation against the Enterprise API, scoped to the Zylo user permissions or the API key used in the query.
Zylo returns the result as JSON or as a stream of Server-Sent Events (SSE).
Your assistant turns that result into a natural-language answer.

A note on model choice: MCP is only as reliable as the AI model interpreting your data. Lower-tier or smaller models can be more prone to hallucination, such as inventing numbers or misreading results, so we recommend using a capable, well-supported model for anything you intend to act on.

What's in this developer guide

Setting up MCP for your organization takes just a few steps. This developer guide walks you through choosing an authentication method, configuring the client you use (Claude, ChatGPT, VS Code, and more), and running your first queries. If you run into issues along the way, jump to Common Troubleshooting Tips at the end.

Want to read more about the Zylo MCP Server to understand what MCP is, ways your Zylo users can effectively use it, and more before you set it up? Check out these additional Zylo resources:

Step 1: Choose an authentication method

The Zylo MCP server supports two authentication methods: OAuth 2.0 with PKCE, and API tokens. For help in determining the best method for your use case, contact your Zylo admin or IT team.

Method A: OAuth 2.0 with PKCE

This method uses your Zylo user account.
A Zylo admin will have to ensure that your user account has the MCP role and any relevant permissions via the User Management tab.
Configure your client with the Zylo MCP Server URL (https://api.zylo.com/mcp), and when starting the first conversation, your client will open a browser window for you to sign into Zylo and authorize the MCP connection.
Access tokens are short-lived (5mins) and refresh automatically.

Method B: API Key

This method uses an Enterprise API key.
A Zylo admin will have to ensure that the key has been granted any relevant scopes via the Company Tokens tab.
The complete API key combines the token_id and token_secret with a colon separator (token_id:token_secret). Note that lost token secrets cannot be recovered, so be sure to record it when creating the API key.
API keys require manual configuration and rotation.

Step 2: Client Configuration

Be sure to consult the official documentation for your client. The guides below may be helpful in configuring some of the more popular clients, but information from official documentation supersedes these guides.

Anthropic Claude

The Zylo MCP server is available as a community connector in Claude marketplace: https://claude.ai/directory/connectors/3a0d2d6f-9c40-4fe3-b2c0-1d91218ede9c

A Claude admin can enable the Zylo MCP connector for their organization by using the above link, or by navigating to Organization Settings -> Connectors -> Add -> All Available, then searching for Zylo.

Once enabled, users can find it in Claude Desktop by navigating to Settings -> Connectors, or in Claude Code via the /mcp command.

OpenAI ChatGPT

MCP Setup Guide for ChatGPT

VS Code

Depending on the authentication method being used, add one of the below configs to .vscode/mcp.json.

For OAuth:

Note that VS Code will handle the OAuth PKCE flow automatically — a browser window will open for you to sign in on first use.

{
  "servers": {
    "zylo": {
      "type": "http",
      "url": "https://api.zylo.com/mcp"
    }
  }
}

For API Key:

As best practice, we recommend storing your API key in a secure vault and calling it via an environmental variable rather than configuring it in plaintext as shown in the example below. For assistance with those configurations, contact your IT or InfoSec admin.

{
  "servers": {
    "zylo": {
      "type": "http",
      "url": "https://api.zylo.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_TOKEN_ID:YOUR_TOKEN_SECRET"
      }
    }
  }
}

Common Troubleshooting Tips

Authentication Failed

Common Cause: Invalid or missing API key
Common Solution: Verify your API key format ({token_id}:{token_secret}), and have a Zylo admin check to make sure the key hasn't been revoked in the Zylo admin panel

Permission Denied

Common Cause: The API key doesn't have permission for the requested operation
Common Solution: Ensure you're using the correct key (if there are multiple), and have a Zylo admin check the key's permissions in the Zylo admin panel

Connection Timeout

Common Cause: Network connectivity issues or server unavailable
Common Solution: Verify the MCP server URL is correct, verify that your network is stable, and check status.zylo.com for temporary outage

Query Timeout

Common Cause: Your query is taking too long (>30 seconds).
Common Solutions:
- Add more specific filters (date ranges, status, etc.)
- Reduce the number of fields requested
- Query smaller date ranges
- Break complex queries into smaller ones

Not Found

Common Cause: The resource you're trying to update doesn't exist.
Common Solutions:
- Verify the resource ID is correct
- Query for the resource first to confirm it exists
- Check if the resource was deleted

AI Assistant Not Using Tools

Common Cause: MCP configuration issue
Common Solution: Restart your AI assistant application, verify MCP configuration file syntax, check MCP server logs for errors, and ensure API key is properly formatted

Zylo MCP - Overview & Getting Started