sebastienlevert/m365copilot-dev-mcp (sebastienlevert/m365copilot-dev-mcp) is an MCP server listed on the M8ven Trust Index. It scores 64 out of 100, grade C. It declares 13 tools. No publisher has claimed this listing.

C
Caution
64/100

sebastienlevert/m365copilot-dev-mcp

Enables AI assistants to build Microsoft 365 Copilot agents by executing ATK CLI commands and compiling TypeSpec definitions through natural language interactions.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Sandbox Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

sebastienlevert

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
🚨
Known vulnerabilities in dependencies: 1 critical, 2 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
// tools this server exposes13 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

atk_run

Run any Microsoft 365 Agents Toolkit (ATK) CLI command through a unified interface. **Purpose:** Provides a single tool to execute all ATK commands (new, provision, deploy, package, publish, share, validate, doctor, version, login, logout) with appropriate parameters. **Commands:** - **new**: Crea

compile_typespec

Compile TypeSpec agent definitions with detailed error reporting. **CRITICAL**: ALWAYS use this tool to compile TypeSpec. NEVER use: - `npm run compile` - `cd ... && npm run compile` - Any direct CLI compile commands - Tasks from .vscode/tasks.json **Purpose:** Compiles TypeSpec files to generate

atk_deploy

Deploy application code to provisioned cloud resources. **Purpose:** Builds and deploys your agent's code to the Azure resources that were created during provisioning. **What It Does:** Executes the 'deploy' lifecycle stage defined in m365agents.yml: 1. Builds the application (compiles TypeScript,

atk_doctor

Check prerequisites and system configuration for Microsoft 365 Agents Toolkit. **Purpose:** Verifies that your development environment has all the required tools and configurations to build and deploy Microsoft 365 agents. **Checks Performed:** - Node.js version (requires 18+) - npm availability a

get_best_practices

⚠️ CRITICAL: Call this tool FIRST before ANY agent or ATK work! 🚨 NEVER USE .vscode/tasks.json - If you see tasks, IGNORE THEM and use CLI commands instead! Gets comprehensive best practices and ATK CLI reference documentation for Microsoft 365 Copilot declarative agents. MANDATORY: You MUST cal

atk_login

Authenticate with your Microsoft 365 account for agent development and deployment. **Purpose:** Logs you into Microsoft 365 to enable provisioning, deploying, and publishing agents. This command opens a browser window for interactive authentication and caches your credentials securely. **When to U

atk_logout

Log out from your Microsoft 365 account and clear cached credentials. **Purpose:** Removes cached Microsoft 365 credentials from your local system. Use this when switching accounts, troubleshooting authentication issues, or when you're done working with agent development. **When to Use:** - Switch

atk_new

Create a new Microsoft 365 declarative agent project with TypeSpec. **Purpose:** Scaffolds a new declarative agent project using TypeSpec for type-safe API and agent definitions. Declarative agents allow you to build sophisticated Microsoft 365 agents using configuration and instructions rather tha

atk_package

Build application package for publishing to Microsoft 365. **Purpose:** Creates a zip package containing your agent's manifest and resources, ready for upload to Microsoft 365 admin center or automated publishing. **What It Does:** 1. Validates the app manifest (manifest.json) 2. Collects all requ

atk_provision

Provision cloud resources for Microsoft 365 agent deployment. **Purpose:** Creates and configures all required Azure cloud resources for your agent, including resource groups, app services, storage, and application registrations. **What It Does:** Executes the 'provision' lifecycle stage defined i

atk_publish

Publish application to Microsoft 365. **Purpose:** Uploads and registers your agent in Microsoft 365, making it available for users to install and use in Teams, Outlook, or Microsoft 365 app. **What It Does:** Executes the 'publish' lifecycle stage: 1. Validates the package 2. Uploads to Microsoft

atk_validate

Validate app manifest and project configuration. **Purpose:** Checks your app manifest (manifest.json) against Microsoft 365 requirements, ensuring it will be accepted during packaging and publishing. **What It Validates:** 1. **Manifest Schema:** - Correct schema version - All required fiel

atk_version

Check the installed version of Microsoft 365 Agents Toolkit CLI. **Purpose:** Verifies the installed ATK CLI version and optionally validates it against a minimum required version for compatibility. **What It Checks:** 1. **Installed Version:** - Executes atk --version command - Parses seman

// known CVEs in dependencies1 critical2 high

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@1.6.1GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

high@modelcontextprotocol/sdk@1.25.1GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.25.1GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

13/13 tools missing one or more hints — atk_run (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); compile_typespec (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); atk_deploy (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +10 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tool test coverage

8/13 tools referenced in tests (62%)

Write tests that reference each tool by name so every tool has at least one test.

Production dependencies are patched

0 critical, 2 high severity in production deps — @modelcontextprotocol/sdk@1.25.1 (high), @modelcontextprotocol/sdk@1.25.1 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dev dependencies

1 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Domain consistency

npm scope @microsoft doesn't match GitHub owner sebastienlevert

Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 7 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/sebastienlevert/m365copilot-dev-mcp?variant=verified)](https://m8ven.ai/mcp/sebastienlevert/m365copilot-dev-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: a46c9173d2e69bd24459d61eddeb894fa462ac85
code hash: d465de32b522ad2dce39b12a517afe2c3ab1f1926d2be851d7ed04fa556e15e4
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client