microsoft-365-copilot

v0.5.8

Microsoft 365 Copilot extensibility & administration team — agents (copilot-extensibility-architect, declarative-agent-engineer, graph-connector-engineer, api-plugin-engineer, agents-sdk-engineer, copilot-admin-governance) covering declarative agents (pinned manifest schema + the 50/25/4096/45s hard-limit wall), custom-engine agents on the M365 Agents SDK/Toolkit, Copilot (Graph) connectors (synced vs federated/MCP, semantic labels, ACL trimming), API plugins (OpenAPI + Entra/OAuth2), the app-package publish lifecycle, and M365 Agent Registry + Purview DLP-for-Copilot governance. citation-grounded knowledge bank (two Mermaid decision trees), skills, templates, an advisory hook (house opinions). Disjoint from power-platform's Copilot Studio low-code coverage (cross-linked). Seams: Copilot Studio → power-platform; CEA engine → claude-app-engineering; Entra/hosting → azure-cloud; security → ravenclaude-core. Requires ravenclaude-core@>=0.7.0.

Claude Code5 Skills1 MCP serverStreamable HTTP

By Matt CorbettLicense: MIT7 GitHub starsUpdated last week

Directory evidence

Runtimes: Claude Code
Parsed components: 6 skill or MCP entries
Source updated: Sep 15, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install microsoft-365-copilot for Claude Code

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install microsoft-365-copilot@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/mcorbett51090/RavenClaude

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/microsoft-365-copilot/.

Plugin files

plugins/microsoft-365-copilot/

├── .claude-plugin/plugin.json
├── skills/api-plugin-openapi-hygiene/SKILL.md
├── skills/copilot-agent-eval-harness/SKILL.md
├── skills/copilot-connector-schema-design/SKILL.md
├── skills/declarative-agent-manifest-authoring/SKILL.md
├── skills/oversharing-remediation-playbook/SKILL.md
└── .mcp.json

Included Skills5

api-plugin-openapi-hygieneskills/api-plugin-openapi-hygiene/SKILL.md

Make a REST API safe and correct to expose as a Microsoft 365 Copilot API plugin — lay out the four files (app manifest + plugin manifest + OpenAPI + adaptive cards), verify the plugin-manifest↔OpenAPI `operationId` mapping both ways, respect the OpenAPI-for-Copilot subset, write model-readable operation descriptions, budget responses to ~66% of the 25-item/~4096-token wall, and wire Entra OAuth2/API-key auth (with the GCC-High caveat). Use when building or reviewing a Copilot API plugin.

copilot-agent-eval-harnessskills/copilot-agent-eval-harness/SKILL.md

Build the golden-prompt regression set + pre-publish evaluation gate for a Microsoft 365 Copilot agent — author representative + adversarial prompts, check grounding accuracy and citation correctness, stress the declarative-agent hard limits (50/25/4096/45s, no-loop), and gate publish on the results. Use before declaring any declarative or custom-engine agent done, and on every manifest/grounding change.

copilot-connector-schema-designskills/copilot-connector-schema-design/SKILL.md

Design a Microsoft 365 Copilot (Graph) connector schema — choose synced vs federated (MCP), declare property attributes (searchable/queryable/retrievable), apply the mandatory semantic-label map (title/url/createdBy/...), ingest ACLs for per-user trimming, and plan crawl/refresh + semantic-index latency. Use when building a Copilot connector to ground Copilot on a line-of-business store.

declarative-agent-manifest-authoringskills/declarative-agent-manifest-authoring/SKILL.md

Author and review a Microsoft 365 Copilot declarative-agent manifest — pin the schema version (v1.8), keep instructions within the ~8,000-char budget, declare only the needed capabilities, write scope-demonstrating conversation starters, wire API actions, and pass manifest + Responsible-AI validation against the 50/25/4096/45s hard-limit wall. Use when building or reviewing a declarative agent.

oversharing-remediation-playbookskills/oversharing-remediation-playbook/SKILL.md

Remediate Microsoft 365 oversharing BEFORE enabling Copilot — assess the blast radius, then run the sequence (RCD/RSS reach-reduction → Purview sensitivity labels + DLP-for-Copilot → site/permission cleanup → enable), framing RSS/RCD as reach-reduction and NOT a security boundary, with owners, verification, comms, and rollback. Use when planning a Copilot rollout over a tenant with uncertain permissions.

MCP servers1

microsoft-learnStreamable HTTP

url: https://learn.microsoft.com/api/mcp

Plugin manifests1

plugins/microsoft-365-copilot/.claude-plugin/plugin.json

{
  "name": "microsoft-365-copilot",
  "version": "0.5.8",
  "description": "Microsoft 365 Copilot extensibility & administration team — agents (copilot-extensibility-architect, declarative-agent-engineer, graph-connector-engineer, api-plugin-engineer, agents-sdk-engineer, copilot-admin-governance) covering declarative agents (pinned manifest schema + the 50/25/4096/45s hard-limit wall), custom-engine agents on the M365 Agents SDK/Toolkit, Copilot (Graph) connectors (synced vs federated/MCP, semantic labels, ACL trimming), API plugins (OpenAPI + Entra/OAuth2), the app-package publish lifecycle, and M365 Agent Registry + Purview DLP-for-Copilot governance. citation-grounded knowledge bank (two Mermaid decision trees), skills, templates, an advisory hook (house opinions). Disjoint from power-platform's Copilot Studio low-code coverage (cross-linked). Seams: Copilot Studio → power-platform; CEA engine → claude-app-engineering; Entra/hosting → azure-cloud; security → ravenclaude-core. Requires ravenclaude-core@>=0.7.0.",
  "author": {
    "name": "Matt Corbett"
  },
  "homepage": "https://github.com/mcorbett51090/RavenClaude",
  "license": "MIT",
  "keywords": [
    "microsoft-365-copilot",
    "copilot-extensibility",
    "declarative-agent",
    "custom-engine-agent",
    "copilot-connector",
    "graph-connector",
    "api-plugin",
    "agents-sdk",
    "agents-toolkit",
    "purview-dlp",
    "agent-registry",
    "data-residency",
    "openapi",
    "m365"
  ],
  "requires": {
    "plugins": [
      "ravenclaude-core@>=0.7.0"
    ]
  },
  "mcpServers": {
    "microsoft-learn": {
      "type": "http",
      "url": "https://learn.microsoft.com/api/mcp"
    }
  },
  "x-mcpAttribution": {
    "microsoft-learn": {
      "party": "third-party",
      "source": "https://github.com/MicrosoftDocs/mcp",
      "license": "MIT",
      "notice": "NOTICE.md"
    }
  }
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[microsoft-365-copilot on Agent Plugins Marketplace](https://pluginsmp.com/plugins/microsoft-365-copilot)