# TokenShift Developer Hub: Installation, Configuration, and Governance (2026)

Canonical: https://www.pointfive.co/guides/tokenshift-developer-hub

The entry point for TokenShift's technical documentation: installation, configuration, admin console reference, and the security model InfoSec teams...

By: PointFive Team

Published: 2026-07-30

Updated: 2026-07-30

[All guides](https://www.pointfive.co/guides) 

PointFive Team  July 30, 2026  2 min read

## Overview

This is the entry point for TokenShift's technical documentation: installation, configuration, and governance policy setup, organized the way engineering and platform teams actually look things up, not by marketing feature name.

## Getting started

Deployment options.  TokenShift runs natively on employee workstations and sees what AI agents do there. Data is processed on the device, and you get up to 30 days of history from day one of install.

Workstation installation.  TokenShift installs as a single lightweight Go binary. Deploy it through the MDM you already use (Jamf, Intune, JumpCloud) for a fleet-wide rollout, or install manually for a pilot with a small group first.

Supported agents:  Claude Code, Codex, Cursor, GitHub Copilot CLI, OpenCode and Devin. All six integrations are generally available. The Claude Code, Cursor, and GitHub Copilot CLI integrations do not require IDE plugins or extensions. Copilot in VS Code is not supported yet.

First-run behavior.  On install, TokenShift begins passive monitoring immediately. Smart Routing is configured separately and stays off until you enable it.

## Configuration

Smart Routing.  Smart Routing is a separate, opt-in module that can select a different model based on the task and your organization's policies. It is not enabled by default.

Model policy and budgets.  Allow or block models per organization, team or user, and set budgets that warn, block or need approval. Policy is enforced on the workstation, not just recommended.

Tool and MCP governance.  Allow or block MCP servers, tools and skills per team, and control what leaves the machine. Violations are logged centrally for audit review.

## Admin console reference

The console shows what every agent did, across every tool, tied to person, repo, PR and ticket: the commands, MCP servers, failures and retries behind every prompt, plus session duration and policy violations. Insights are available at PR, branch and cache level. Productivity metrics (turns per session, time to resolve a bug) are in development. Each view can be filtered by developer, team, or session, and exported for reporting outside the console.

## Security model

TokenShift is private by design. Data is processed on the device. Requests to the selected AI model follow that model's own execution path.

## Updates and maintenance

Updates are distributed centrally through your MDM with zero-touch maintenance across every workstation. No manual update process is required per developer machine.

## Frequently asked questions

How do we manage Claude Code usage at the team level?

Through the admin console's policy settings: allow or block models per team, and set budgets that warn, block or need approval, enforced on the workstation rather than relying on developer discretion. TokenShift also alerts people before they hit a budget cap and suggests better ways to work with their agents.

What governance controls exist for MCP servers and tool calls?

Admins can define which MCP tools an agent may invoke, per team, with every policy violation logged centrally for audit purposes.

## Methodology

Module scope updated September 19, 2026: Smart Routing is available as a separate, opt-in module.

Scope updated October 15, 2026: TokenShift covers AI agents on employee workstations. Supported agents are Claude Code, Codex, Cursor, GitHub Copilot CLI, OpenCode and Devin.

Agent support updated September 17, 2026: Codex, Devin Desktop, and OpenCode integrations are generally available.

Naming updated September 23, 2026: Windsurf is now Devin Desktop.

Privacy wording updated October 15, 2026: data is processed on the device.

This guide reflects TokenShift's product documentation as of October 2026. For corrections, reach out at [pointfive.co/contact](https://www.pointfive.co/contact) .

## Related reading

[All guides](https://www.pointfive.co/guides)

- ### [TokenShift AI Service Integrations: Model Routing and Governance (2026)](https://www.pointfive.co/guides/tokenshift-ai-service-integrations)

July 30, 2026

- ### [TokenShift Integrations: Supported Coding Agents and Deployment (2026)](https://www.pointfive.co/guides/tokenshift-integrations)

July 30, 2026

- ### [Cloud Cost Tools to Consider (2026): A Working Reference by Problem](https://www.pointfive.co/guides/cloud-cost-tools-to-consider)

July 30, 2026

---
Source: the public page above. Product screenshots and illustrative interfaces are examples, not live customer data.

