Split.io MCP Server

Connect your account, then chat with AI to run tools.

Split_io provides a feature flagging and experimentation platform, enabling developers to implement and manage feature toggles and conduct A/B testing. Use it for controlled feature rollouts and to gain insights through experiments to enhance application performance and user experience.

Start chatting

Managed

11 tools

Agent guide included

Opens MCPBundles Studio with this server selected. After sign-in, chat and run tools from the same thread.

Browse all tools

AI Skill
SKILL.md

Domain knowledge for Split.io — workflow patterns, data models, and gotchas for your AI agent.

Split.io

Split.io organizes feature flags under Workspaces. Workspaces have Environments; Feature Flags and Segments are workspace-scoped. Traffic Types define targeting.

Data Model

Workspaces — top-level; contain environments, flags, segments.
Environments — dev, staging, prod; flags are evaluated per environment.
Feature Flags — toggles; have rules and rollout.
Segments — user segments for targeting.
Traffic Types — user types (user, account, etc.).
Flag Sets — groupings of flags.
Change Requests — approval workflow for flag changes.
Rollout Statuses — rollout progress.

Gotchas

wsId vs workspaceId: Same value, different parameter names depending on endpoint. Use workspaceId for segments.
Environment required: Target a specific rollout lane (dev/stage/prod) using environment_id from the workspace’s environment catalog.

Tools in this Server (11)

Fetch Environments

Fetch all environments within a specific workspace by using the workspace ID. Ideal for understanding the setup of feature deployments across differen...

Fetch Feature Flags

Get a full list of feature flags available in a particular workspace. Useful for managing and organizing feature toggles. Returns a list with detailed...

Fetch Segments

Fetch all segments within a specified workspace using the workspace ID. Essential for targeting specific user segments when rolling out features. Retu...

Fetch Segments Keys

Retrieve keys associated with a specific segment name and environment. Useful for detailed analysis of segment membership and access. Provides a list ...

Fetch Traffictypes

Get a list of all traffic types available in a specified workspace. This helps in categorizing different streams of traffic uniformly. Returns detaile...

List Changerequests

Retrieve a list of feature flag change requests made within your organization. Use this to monitor and review changes for governance and compliance pu...

List Flagsets

List all flagsets for your account to better organize feature flags into collections. Use this tool to optimize your feature management strategy. Retu...

List Groups

Obtain a list of all user groups in your organization. This is essential for managing permissions and roles related to feature flags. Returns informat...

List Rolloutstatuses

Retrieve the rollout statuses for various feature flags to track their deployment progress. Use this when you need to know the current state of featur...

List Users

List all users in your Split.io account to facilitate user management and collaboration. Ideal for auditing active user accounts and roles. Provides f...

List Workspaces

Retrieve a list of all workspaces available in your Split_io account. Ideal for when you need to manage or integrate multiple project environments or ...

Frequently Asked Questions

What is the Split.io MCP server?

How do I connect Split.io to my AI agent?

Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/split-io. Authentication is handled automatically.

How many tools does Split.io provide?

Split.io provides 11 tools that can be called by AI agents, along with a SKILL.md that gives your AI agent domain knowledge about when and how to use them.

What authentication does Split.io require?

Split.io uses API Key. Split.io requires credentials. Connect via MCPBundles and authentication is handled automatically.

Setup Instructions

Connect Split.io to any MCP client in minutes

MCP URL

https://mcp.mcpbundles.com/bundle/split-io

Claude.ai Cursor VS Code VS Code Insiders Goose LM Studio Cherry Studio ChatGPT

One-click install:

Install on Claude.ai Install for organization (admins)

The link prefills the Add custom connector dialog — you still review the values and click Add, then Connect to complete OAuth.

Or add manually

Open claude.ai → Settings → Connectors.
Click the + button and choose Add custom connector.
Set Name to Split.io and paste the MCP URL into Remote MCP server URL.
Click Add. Split.io will appear under Not connected — select it and click Connect to complete OAuth.