Integrations to the tools you use for humans and agents

Governed tool access for humans and agents

Integrate with your tools so your humans and agents can do real work securely.

  • Connect custom tools and govern with deny/allow lists.
  • API keys never reach your sandboxes.
Environment starting in Ona.

Integrations enable real work

The connective tissue for real agent workflows.

Questions & answers

Are integrations different from API, MCP, CLI?

Integrations are the approved tools and systems agents can use. API, MCP, and CLI are programmatic surfaces for connecting and operating those tools.

Can integrations be scoped?

Yes. Integrations should be attached to the right teams, repositories, workflows, and runtime policies.

Can we connect internal tools?

Yes. The platform is intended to support pre-registered tools, MCP servers, internal APIs, and custom workflow triggers.

Do tool calls bypass review?

No. Tool usage should remain visible through logs, artifacts, workspace state, and human review.

Other platform pieces.

Rest of platform layer.

BYO Agents & Inference

Any agent on your inference stack.

Workflows

Schedule, trigger, and review agent runs.

Environments

Isolated workspaces with repo context.

Self-host Proliferate

Run Proliferate entirely in your VPC

Runtime Security

Control what agents can access and execute.

Governance & budgets

Policies, approvals, usage, and spend.

Security First

Identity, auditability, and deployment boundaries.

API, MCP, CLI

Coming soon

Programmatic access to agent workflows.

Run agents on infrastructure you control.

Start with one team, then standardize agent workflows without giving up control of code, credentials, or inference.