Skip to content
Back to search

Dataverse-skills

Microsoft Dataverse skills for AI coding agents. Wraps the Dataverse MCP server, Dataverse CLI, Python SDK, and PAC CLI behind specialist skills for building, querying, deploying, and administering Dataverse environments.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/microsoft/Dataverse-skills with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/microsoft/Dataverse-skills'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/microsoft--dataverse-skills/badge.svg)](/listings/microsoft--dataverse-skills)

HTML

<a href="/listings/microsoft--dataverse-skills"><img src="/api/listings/microsoft--dataverse-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

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](https://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.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 16 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  3. "name": "dataverse-skills",
  4. "owner": {
  5. "name": "Microsoft",
  6. "url": "https://www.microsoft.com"
  7. },
  8. "plugins": [
  9. {
  10. "name": "dataverse",
  11. "description": "Microsoft Dataverse plugin for coding agents, covering record CRUD, bulk data operations, advanced queries, schema and metadata, administration, security, environment management, and solution lifecycle through MCP, CLI, and SDK workflows.",
  12. "source": "./.github/plugins/dataverse",
  13. "homepage": "https://github.com/microsoft/Dataverse-skills"
  14. }
  15. ]
  16. }
README.md · README · 205 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Dataverse Skills
  2. [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
  3. Build, query, and manage [Microsoft Dataverse](https://learn.microsoft.com/en-us/power-apps/maker/data-platform/data-platform-intro) 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.
  4. | Skill | What it does |
  5. |---|---|
  6. | **dv-connect** | One-time setup that installs the Dataverse CLI, Python SDK, and PAC CLI; authenticates against your Dataverse environment; and registers the Dataverse MCP server with your agent. |
  7. | **dv-query** | Reads, filters, paginates, and aggregates Dataverse records. Handles natural-language questions like *"show me my open deals"*, multi-page result sets, and pandas DataFrame loading for notebook analysis. |
  8. | **dv-data** | Single-record CRUD plus bulk import — CSV loads, multi-table imports with foreign-key dependencies, upsert by alternate key, and AI-generated sample data. |
  9. | **dv-metadata** | Authors and edits the Dataverse data model: tables, columns, relationships, forms, and views. |
  10. | **dv-solution** | Manages solution lifecycle — create, export, import, promote across environments, and validate deployments. |
  11. | **erp-xpp** | Handles the Finance and Operations X++ lifecycle: model and metadata authoring, matching SDK installation, compile/build, deployable package deployment, database synchronization, and verification of custom services/APIs, runnable X++ classes, and public OData data entities. |
  12. | **erp-sql** | Requests explicitly approved temporary Reader-only SQL access to Finance and Operations unified development environments (UDEs), verifies sqlcmd connectivity, and reads user-selected physical tables with bounded previews and reusable sessions, without exposing the password. |
  13. | **dv-admin** | Environment-level administration: bulk delete, retention/archival, organization settings, OrgDB settings, recycle bin, audit, and the allowlisted PPAC toggles. |
  14. | **dv-security** | Assigns security roles, manages user access, adds application users, configures business units, and handles admin self-elevation. |
  15. | **dv-overview** | Cross-cutting rules and tool routing; loaded before any other skill to direct each request to the right specialist. |
  16. Browse [`.github/plugins/dataverse/skills/`](.github/plugins/dataverse/skills/) for the full source.
  17. ## Prerequisites
  18. A Microsoft Dataverse environment, available through Power Apps, Dynamics 365, or Power Platform plans, or via the free [Power Apps Developer Plan](https://learn.microsoft.com/en-us/power-platform/developer/plan).
  19. ## Install
  20. ### Quick install — any agent, incl. JetBrains (npx)
  21. One command installs **all** Dataverse skills and lets you choose which agent(s) to add them to:
  22. ```bash
  23. npx skills add microsoft/Dataverse-skills -s "*"
  24. ```
  25. - `-s "*"` installs every Dataverse skill (skips the per-skill prompt).
  26. - You'll be prompted to pick which **agent(s)** to install into (Codex, GitHub Copilot, Claude Code, Cursor, …).
  27. - Add `-g` to install **globally** so the skills are available in every project on your machine:
  28. ```bash
  29. npx skills add microsoft/Dataverse-skills -s "*" -g
  30. ```
  31. This works with any agent that reads local skills. JetBrains IDEs also have a native listing -- see [JetBrains IDEs](#jetbrains-ides-pycharm-rider). After installing, ask your agent to **"Connect to Dataverse"** — the `dv-connect` skill fetches the helper scripts and walks through authentication and MCP registration.
  32. The per-marketplace installs below are alternatives for agents that have a dedicated plugin listing.
  33. ### GitHub Copilot
  34. ```bash
  35. /plugin install dataverse@awesome-copilot
  36. ```
  37. ### Claude Code
  38. ```bash
  39. /plugin install dataverse@claude-plugins-official
  40. ```
  41. ### Gemini CLI
  42. Install the extension from the public repository. Gemini CLI selects the
  43. generic extension archive attached to the latest GitHub Release:
  44. ```bash
  45. gemini extensions install https://github.com/microsoft/Dataverse-skills --skip-settings
  46. gemini extensions config dataverse DATAVERSE_URL --scope workspace
  47. ```
  48. Enter the Dataverse environment URL when the configuration command prompts.
  49. The value is stored in local Gemini extension settings and is not committed to
  50. the repository. Restart Gemini after installation, then verify discovery:
  51. ```text
  52. /extensions list
  53. /skills list
  54. ```
  55. ```bash
  56. gemini mcp list
  57. ```
  58. Update or uninstall the extension with:
  59. ```bash
  60. gemini extensions update dataverse
  61. gemini extensions uninstall dataverse
  62. ```
  63. The release archive is generated from `.github/plugins/dataverse/` when a new
  64. plugin version reaches `main`; the repository does not track a second skills or
  65. scripts tree.
  66. ### Codex
  67. **Codex app and ChatGPT**
  68. 1. Open **Plugins**.
  69. 2. Search for **Microsoft Dataverse** in the OpenAI plugin directory.
  70. 3. Open the `dataverse` plugin and select **Install**.
  71. **Codex CLI**
  72. Install directly from the OpenAI-curated marketplace:
  73. ```bash
  74. codex plugin add dataverse@openai-curated
  75. ```
  76. Alternatively, run `/plugins`, search for **Microsoft Dataverse**, and install
  77. `dataverse` from the `openai-curated` marketplace.
  78. ### Cursor
  79. **From agent chat**
  80. ```bash
  81. /add-plugin dataverse
  82. ```
  83. **From the marketplace UI**
  84. 1. Open **Settings → Plugins** in Cursor.
  85. 2. Search the Marketplace for **Dataverse**.
  86. 3. Open **Microsoft Dataverse** and select **Add to Cursor**.
  87. The listing is published at [cursor.com/marketplace/microsoft-dataverse](https://cursor.com/marketplace/microsoft-dataverse).
  88. ### Google Antigravity
  89. Install the native plugin directly from its canonical directory in this repository:
  90. ```bash
  91. agy plugin install https://github.com/microsoft/Dataverse-skills/tree/main/.github/plugins/dataverse
  92. ```
  93. If the Gemini extension is already installed, import the same plugin with
  94. `agy plugin import gemini` instead.
  95. Restart `agy`, then use `/skills` to verify discovery. Invoke `/dv-connect` to
  96. select an environment and register the Dataverse MCP server with `agy mcp add`;
  97. verify it with `agy mcp list` after restarting.
  98. ### JetBrains IDEs (PyCharm, Rider)
  99. Requires JetBrains AI Assistant with Claude Agent or Codex.
  100. 1. Open **Settings | Tools | AI Assistant | Skills**.
  101. 2. Search for **dataverse**.
  102. 3. Select **dataverse** and click **Install**.
  103. Then ask the agent to **"Connect to Dataverse"** to install the full `dv-*` skill set and set up authentication and MCP. The listing is published at [JetBrains/skills](https://github.com/JetBrains/skills/tree/main/dataverse).
  104. ## Verify the install
  105. After installation, ask your agent:
  106. > "Connect to Dataverse"
  107. 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.
  108. ## Try these prompts
  109. After the connect flow finishes, describe what you want — the plugin picks MCP, the Dataverse CLI, the Python SDK, or PAC CLI for you.
  110. - *"Show me my open deals over $100K closing this quarter"*
  111. - *"Import this CSV into the contacts table"*
  112. - *"Create a customer feedback table with name, rating, and comment columns"*
  113. - *"Pull the schema and pack it into a solution"*
  114. - *"Create a runnable X++ class, compile it, and deploy its Finance and Operations package"*
  115. - *"Get temporary Reader access and connect sqlcmd to my Finance and Operations developer database"*
  116. - *"Bulk delete activities older than 2024"*
  117. - *"Add a teammate to the sales team on the dev environment"*
  118. ## Safety & Security
  119. The plugin is designed around a least-privilege model — it cannot exceed the permissions of the authenticated user. Key safeguards:
  120. - **MCP authorization** — MCP access requires developer auth, tenant admin consent, and per-environment allowlisting; other plugin tools (SDK, PAC CLI) authenticate directly.
  121. - **Security role enforcement** — every API call is authorized server-side by Dataverse; the plugin cannot bypass or escalate permissions.
  122. - **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.
  123. - **Token security** — credentials are stored in your OS native credential store or held in memory only; never passed to external services.
  124. For the full safety model — including confirmation flows, logging, irreversible operation handling, and planned improvements — see [docs/safety-and-guardrails.md](docs/safety-and-guardrails.md).
  125. ## Contributing
  126. We welcome contributions — new skills, improvements to existing ones, and bug fixes. See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines and local-development instructions.
  127. ## Trademarks
  128. This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft
  129. trademarks or logos is subject to and must follow
  130. [Microsoft's Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks/usage/general).
  131. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship.
  132. Any use of third-party trademarks or logos are subject to those third-party's policies.
  133. ## License
  134. This project is licensed under the [MIT License](LICENSE).
  135. ## Code of Conduct
  136. This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
  137. For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.