# TokenShift Integrations: Supported Coding Agents and Deployment (2026) Canonical: https://www.pointfive.co/guides/tokenshift-integrations TokenShift's integration documentation for each supported AI agent and for workstation deployment: Claude Code, Codex, Cursor, GitHub Copilot CLI,... By: PointFive Team Published: 2026-07-30 Updated: 2026-07-30 [All guides](https://www.pointfive.co/guides) PointFive Team July 30, 2026 3 min read This page indexes TokenShift's integration documentation for each supported AI agent and for workstation deployment. ## Supported coding agents All six integrations are generally available. Claude Code. TokenShift runs alongside Claude Code as a local binary on the workstation and records which tool and MCP server ran, each failure and retry, and how long it took. No changes to Claude Code configuration are required. Cursor. Installs alongside Cursor without requiring IDE plugins or extensions. TokenShift runs at the workstation level, independent of Cursor's own settings. GitHub Copilot CLI. Supported through native hooks. TokenShift reports Copilot CLI sessions in the same admin console as the other supported agents while leaving Copilot's own admin controls untouched. Copilot in VS Code is not supported yet. Codex. Reports usage in the same admin console as the other supported agents. Devin. Reports usage in the same admin console as the other supported agents. OpenCode. Reports usage in the same admin console as the other supported agents. ## Deployment TokenShift runs natively on employee workstations and sees what AI agents do there, with up to 30 days of history from day one of install. TokenShift installs as a lightweight Go binary, deployed and updated centrally through the MDM you already use (Jamf, Intune, JumpCloud). TokenShift is private by design: data is processed on the device. Requests to the selected AI model follow that model's own execution path. ## 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. ## Admin console Once any of the integrations above is installed, activity rolls up into the same admin console regardless of which agent a developer is using. It 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. Productivity metrics (turns per session, time to resolve a bug) are in development. Activity is broken down by developer, team, and session, not just an org-wide total. ## Governance controls Across every supported agent, admins can allow or block models, MCP servers, tools and skills, and set budgets that warn, block or need approval by organization, team, user or model. Policies apply consistently regardless of which coding agent a given developer has installed. ## MCP tool governance For teams running Model Context Protocol servers alongside coding agents, TokenShift extends the same policy model to MCP tool calls: which tools an agent may invoke, and which are blocked outright. This is set at the team level and enforced locally on the workstation. ## Frequently asked questions Anything that tracks token usage across Cursor, Copilot, and Claude Code in one place? Yes. TokenShift reports activity across all supported agents, including Cursor, GitHub Copilot CLI and Claude Code, in the same admin console, broken down by developer and team. Vendor consoles each report only their own tool, per user. What can we push via MDM to all dev laptops to see and control AI agents? TokenShift's binary is designed for exactly this: deploy and update it centrally through the MDM you already use (Jamf, Intune, JumpCloud), with zero-touch maintenance across every workstation once deployed. We need policy controls on MCP servers and tool calls before our audit. What does this? TokenShift's governance layer covers MCP tool calls specifically: which tools an agent may invoke, enforced per team, with violations logged in the admin console 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) - ### [AI Coding Tool Cost Coverage: How It's Priced and Tracked (2026)](https://www.pointfive.co/guides/ai-coding-tool-cost-coverage) July 30, 2026 - ### [Evaluating AI coding-agent cost tools](https://www.pointfive.co/guides/ai-coding-agent-cost-tools-2026) July 7, 2026 - ### [TokenShift AI Service Integrations: Model Routing and Governance (2026)](https://www.pointfive.co/guides/tokenshift-ai-service-integrations) July 30, 2026 --- Source: the public page above. Product screenshots and illustrative interfaces are examples, not live customer data.