Dataverse Skills

Build, query, and manage Microsoft Dataverse and linked Dynamics 365 Finance and Operations environments through natural language. The plugin teaches AI coding agents to drive the Dataverse MCP server, Dataverse CLI, Python SDK, and PAC CLI — from designing data models and answering CRM questions to deploying Dataverse solutions and Finance and Operations deployable packages.

Browse .github/plugins/dataverse/skills/ for the full source.

Prerequisites

A Microsoft Dataverse environment, available through Power Apps, Dynamics 365, or Power Platform plans, or via the free Power Apps Developer Plan.

Install

Quick install — any agent, incl. JetBrains (npx)

One command installs all Dataverse skills and lets you choose which agent(s) to add them to:

npx skills add microsoft/Dataverse-skills -s "*"

• -s "*" installs every Dataverse skill (skips the per-skill prompt).
• You'll be prompted to pick which agent(s) to install into (Codex, GitHub Copilot, Claude Code, Cursor, …).
• Add -g to install globally so the skills are available in every project on your machine:

npx skills add microsoft/Dataverse-skills -s "*" -g

This is the recommended path for JetBrains IDEs (PyCharm, Rider) via Codex or Claude, and works with any agent that reads local skills. After installing, ask your agent to "Connect to Dataverse" — the dv-connect skill fetches the helper scripts and walks through authentication and MCP registration.

The per-marketplace installs below are alternatives for agents that have a dedicated plugin listing.

GitHub Copilot

/plugin install dataverse@awesome-copilot

Claude Code

/plugin install dataverse@claude-plugins-official

Gemini CLI

Install the extension from the public repository. Gemini CLI selects the generic extension archive attached to the latest GitHub Release:

gemini extensions install https://github.com/microsoft/Dataverse-skills --skip-settings
gemini extensions config dataverse DATAVERSE_URL --scope workspace

Enter the Dataverse environment URL when the configuration command prompts. The value is stored in local Gemini extension settings and is not committed to the repository. Restart Gemini after installation, then verify discovery:

/extensions list
/skills list

gemini mcp list

Update or uninstall the extension with:

gemini extensions update dataverse
gemini extensions uninstall dataverse

The release archive is generated from .github/plugins/dataverse/ when a new plugin version reaches main; the repository does not track a second skills or scripts tree.

Codex

Codex app and ChatGPT

1. Open Plugins.
2. Search for Microsoft Dataverse in the OpenAI plugin directory.
3. Open the dataverse plugin and select Install.

Codex CLI

Install directly from the OpenAI-curated marketplace:

codex plugin add dataverse@openai-curated

Alternatively, run /plugins, search for Microsoft Dataverse, and install dataverse from the openai-curated marketplace.

Cursor

From agent chat

/add-plugin dataverse

From the marketplace UI

1. Open Settings → Plugins in Cursor.
2. Search the Marketplace for Dataverse.
3. Open Microsoft Dataverse and select Add to Cursor.

The listing is published at cursor.com/marketplace/microsoft-dataverse.

Google Antigravity

Install the native plugin directly from its canonical directory in this repository:

agy plugin install https://github.com/microsoft/Dataverse-skills/tree/main/.github/plugins/dataverse

If the Gemini extension is already installed, import the same plugin with agy plugin import gemini instead.

Restart agy, then use /skills to verify discovery. Invoke /dv-connect to select an environment and register the Dataverse MCP server with agy mcp add; verify it with agy mcp list after restarting.

Verify the install

After installation, ask your agent:

"Connect to Dataverse"

The dv-connect skill walks through tool checks, authentication, and MCP registration. When it finishes, you should see a dataverse-<orgname> MCP server (or Gemini's bundled dataverse server), and pac auth list should show your active environment.

Try these prompts

After the connect flow finishes, describe what you want — the plugin picks MCP, the Dataverse CLI, the Python SDK, or PAC CLI for you.

• "Show me my open deals over $100K closing this quarter"
• "Import this CSV into the contacts table"
• "Create a customer feedback table with name, rating, and comment columns"
• "Pull the schema and pack it into a solution"
• "Create a runnable X++ class, compile it, and deploy its Finance and Operations package"
• "Bulk delete activities older than 2024"
• "Add a teammate to the sales team on the dev environment"

Safety & Security

The plugin is designed around a least-privilege model — it cannot exceed the permissions of the authenticated user. Key safeguards:

• MCP authorization — MCP access requires developer auth, tenant admin consent, and per-environment allowlisting; other plugin tools (SDK, PAC CLI) authenticate directly.
• Security role enforcement — every API call is authorized server-side by Dataverse; the plugin cannot bypass or escalate permissions.
• Application-level telemetry only — outbound Dataverse requests may carry application metadata (plugin / version / skill / agent labels) so server-side dashboards can attribute traffic. No prompts, tool arguments, or record data are transmitted.
• Token security — credentials are stored in your OS native credential store or held in memory only; never passed to external services.

For the full safety model — including confirmation flows, logging, irreversible operation handling, and planned improvements — see docs/safety-and-guardrails.md.

Contributing

We welcome contributions — new skills, improvements to existing ones, and bug fixes. See CONTRIBUTING.md for guidelines and local-development instructions.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.

License

This project is licensed under the MIT License.

Code of Conduct

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.