See how ekai worksBook a demo
SolutionsBuild, enable and migrate, on one data foundation.
Go deeper
The problemModeling methodWorkflowsWhy ekai
ProductFrom raw tables to trusted answersHow ekai worksDiscovery, semantics and ontologyAI agent accuracyThe same verified answer in every agentGovernance and securityOwned, verified and versioned
IntegrationsThe warehouses and agents ekai connectsekai MCP
SnowflakeDatabricksBigQueryRedshiftPostgreSQLAzure SynapseClickHouseDuckDB
CustomersReal results, in the customer's own words.

One verified set of definitions.

LeadersOwn the layer AI reads fromChief Information OfficersChief Data OfficersChief AI Officers
TeamsAsk, build and verifyAnalytics and BI leadersAnalytics engineersApplied AI engineersForward deployed engineersPrincipal AI leadersData product ownersEnterprise data architects
SolutionsBuild, enable, migrateHow ekai helps, step by step
ekai raises $1.7MBacked by Misneach and C10 Labs. Yahoo Finance ↗

Cambridge, MA.

ekaiWho we areAbout ekaiTeamOur valuesCustomersSecurityPrivacy policy
ResourcesRead and askLearnNews and blogsReadiness checkDocsFAQContact us
Home / ekai MCP

ekai MCP is one interface into the enterprise ecosystem.

Bring governed semantic models into the AI apps your teams already use, and bring the sources your experts already write in back into ekai, through MCP, the open standard for connecting AI agents to tools and data.

Book a demoSee which connectors are live

How does ekai MCP work? It runs in both directions.

As a server, ekai serves its governed semantic models to AI apps. As a client, ekai reads from the MCP sources your teams already use.

MCP server

Bring ekai into your AI app

Give Claude, ChatGPT, VS Code and Cursor the same governed semantic models your experts authored. Add the MCP server URL from Connected Apps on your ekai home page, then switch MCP on for each model you want to share. Apps get read-only access as the person who connected them, only on the models shared with that person, and the workspace owner can turn MCP off.

MCP client

Bring your sources into ekai

Connect MCP sources such as Google Drive, Notion and Atlassian to ekai. Use Add connector, which is available on each model and data connection.

Connect your AI app.

Pick your app to see the steps. The configuration itself is published when ekai MCP is released.

  1. Copy the MCP server URL from Connected Apps on your ekai home page.

  2. Add it to Claude, then sign in.

  3. Switch MCP on for each model, in the MCP column of your Semantics list.

MCP server URL for Claude

The URL appears here at release

Google Drive, Notion and Atlassian connectors are live. More connectors are on the way.

Google Drive

Document stores

Live

Notion

Knowledge tools

Live

Atlassian

Knowledge tools

Live

Agents ekai serves today

Live

ekai already publishes governed semantic models to these agents. MCP adds every other MCP-enabled app.

Snowflake CoWorkDatabricks GenieBigQuery data agents

Coming soon

On the way
Conversational BI agents
Wren AI
Document stores
SharePointOneDriveBox
Enterprise applications
SalesforceNetSuiteCoupaSAPWorkdayServiceNowHubSpot
Knowledge tools
ClickUpSAP LeanIX
Data catalogs
OpenMetadataDataHubAtlanCollibraAlationMicrosoft Purview
Exchange

Pull existing definitions in from a data catalog and push ekai output back.

Common questions

Last updated October 28, 2026

What is MCP?

The Model Context Protocol (MCP) is the open standard for connecting AI agents to tools and data. ekai uses it in both directions: as a server for AI apps and as a client for your sources.

Which AI apps work with ekai MCP?

Claude, ChatGPT, VS Code and Cursor, once the MCP server is released. You add the MCP server URL from Connected Apps on your ekai home page, then switch MCP on for each model. As connectors, Google Drive, Notion and Atlassian are live, and more connectors are on the way.

Is my data safe when I use ekai MCP?

MCP is off until a workspace owner turns it on, and each model is shared only when its owner switches MCP on, and only with people who already have access to it. Apps sign in as a person through OAuth, so there are no shared API keys. Their access is read-only: every query must be a single read-only SELECT. Query results go to the app you connected, with personal-data columns masked. Sessions expire after an hour, and you can disconnect any app from Connected Apps, or revoke all connections at once in Settings.

When can I use it?

The Google Drive, Notion and Atlassian connectors are live today. The MCP server is coming soon. Book a demo and we will walk you through both with your own stack.