Dataverse-skills

mcp
Guvenlik Denetimi
Gecti
Health Gecti
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 79 GitHub stars
Code Gecti
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This tool provides a set of AI agent skills and MCP server configurations for Microsoft Dataverse. It allows AI coding assistants like Claude Code and GitHub Copilot to build, query, and manage Dataverse environments using natural language.

Security Assessment
The tool interacts directly with Microsoft Dataverse APIs to read and write data, requiring authentication and tenant admin consent. It executes shell commands via the underlying Dataverse CLI and PAC CLI tools to manage environments. A light code scan found no dangerous patterns, hardcoded secrets, or excessive permissions. It operates on a strict least-privilege model, meaning it cannot exceed the permissions of the authenticated user and cannot bypass server-side security roles. Overall risk is rated as Low.

Quality Assessment
The project is highly maintained, with repository activity as recent as today. It is backed by a reputable publisher (Microsoft) and has garnered 79 GitHub stars, indicating a healthy level of community trust. The repository is well-documented and safely operates under the standard MIT license.

Verdict
Safe to use.
SUMMARY

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.

README.md

Dataverse Skills

License: MIT

Agent skills and MCP configuration for Microsoft Dataverse — works with Claude Code and GitHub Copilot. These skills teach AI agents how to build and manage Dataverse solutions using natural language.

Browse the .github/plugins/dataverse/skills/ folder for the full catalog.

Prerequisites

  • Microsoft Dataverse environment (included with Power Apps, Dynamics 365, or Power Platform)
  • Python 3.10+ and Node.js 18+

Getting Started

Claude Code

/plugin install dataverse@claude-plugins-official

GitHub Copilot

/plugin install dataverse@awesome-copilot

What's Included

  • 8 skills covering connection setup, metadata authoring, solution management, data writes, queries/analytics, environment admin, security/role management, and tool routing
  • MCP server configuration for Dataverse Web API access
  • Scripts for authentication and MCP client enablement
  • Templates for CLAUDE.md project files

Local Development

Clone the repository first:

git clone https://github.com/microsoft/Dataverse-skills.git

Testing with Claude Code

Test the plugin locally without installing from a marketplace:

# 1. Create and cd into a fresh test folder
mkdir my-test-project
cd my-test-project

# 2. Launch Claude Code with the plugin loaded from your local clone
claude --plugin-dir "<path/to/repo>/.github/plugins/dataverse"

# 3. Start with a natural language prompt, e.g.:
#    "Create a support ticket table with customer and agent lookups"

The --plugin-dir path must be in double quotes if it contains spaces or special characters. Use the absolute path to the plugin directory in your local clone of this repo.

Testing with GitHub Copilot CLI

To register the local plugin marketplace from the cloned repository and install the plugin:

copilot plugin marketplace add <path/to/repo>/Dataverse-skills
copilot plugin install dataverse@dataverse-skills

To reinstall the plugin after pulling or making local changes:

copilot plugin uninstall dataverse@dataverse-skills
copilot plugin install dataverse@dataverse-skills

To install the local version directly without marketplace registration:

copilot plugin install <path/to/repo>/.github/plugins/dataverse

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
  • No plugin telemetry — the plugin does not collect or transmit usage analytics; data flows only to Dataverse within your tenant and to the AI host (Claude or Copilot) as part of normal operation
  • 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.

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.

Yorumlar (0)

Sonuc bulunamadi