Authenticate explicitly.
Use authorized tokens or the supported OAuth flow. Confirm the user, workspace, and scopes before accessing company context.
Developers
Give your AI tools company context.
Connect applications and AI clients to Heidi through the API and MCP. Build with shared knowledge, scoped access, and the controls of your workspace.
One context layer. Many ways to work.
Retrieve company knowledge, ask questions, and connect supported tools using the documented API and MCP interfaces. Choose the authentication path supported by your client and grant the access it needs.
Heidi supports an OAuth consent flow for compatible MCP clients, alongside token-based integrations. Workspace policy and connected capabilities still determine what is available.
Build your connection
A connection carries responsibility.
Inspect available capabilities.
Read the API reference and discover the MCP tool surface for your integration. Access depends on scope, permissions, and configuration.
Evaluate the result.
Keep source evidence with answers and distinguish accepted work from completed execution. Review consequential actions through the configured approval path.
Build the next version of your company
Start with one outcome.
Think company-wide.
Bring a workflow that crosses departments. Let’s map the knowledge, controls, and evidence a meaningful rollout needs.
Discuss your rollout