Teams MCP (Ritchy-EU/teams-mcp) is an MCP server listed on the M8ven Trust Index. It scores 67 out of 100, grade C. It declares 28 tools. No publisher has claimed this listing.

C
Caution
67/100

Teams MCP

Enables AI assistants to interact with Microsoft Teams, users, and organizational data via Microsoft Graph APIs, including sending messages, managing chats and channels, and searching messages.

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

⚡ 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

Ritchy-EU

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
⚠️
Tool descriptions don’t match what handlers do
1 tool describes read intent but its handler mutates — download_message_hosted_content (line 898: hostedContentRegex.exec(bodyContent))
🚨
Known vulnerabilities in dependencies: 1 critical
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 2 credentials: AUTH_TOKEN, AZURE_CLIENT_SECRET
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes28 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.

auth_status

Check the authentication status of the Microsoft Graph connection. Returns whether the user is authenticated and shows their basic profile information.

start_authentication

Start Microsoft Teams authentication via device code flow. Returns a URL and code for the user to complete sign-in in their browser. Use this when auth_status shows not authenticated.

list_chats

List all recent chats (1:1 conversations and group chats) that the current user participates in. Returns chat topics, types, and participant information.

get_chat_messages

Retrieve recent messages from a specific chat conversation. Returns message content, sender information, and timestamps.

send_chat_message

Send a message to a specific chat conversation. Supports text and markdown formatting, mentions, and importance levels.

create_chat

Create a new chat conversation. Can be a 1:1 chat (with one other user) or a group chat (with multiple users). Group chats can optionally have a topic.

update_chat_message

Update (edit) a chat message that was previously sent. Only the message sender can update their own messages. Supports updating content with text or Markdown formatting, mentions, and importance levels.

delete_chat_message

Soft delete a chat message that was previously sent. Only the message sender can delete their own messages. The message will be marked as deleted but can still be seen as '[This message has been deleted]'.

download_chat_attachment

Download files and images from a chat message. Handles both inline images (hosted content) and file attachments (OneDrive/SharePoint references). Use get_chat_messages first to see available attachments.

get_user_manager

Get the manager of a user. Returns the user's direct manager with their profile information. If no userId is provided, returns the current user's manager.

get_direct_reports

Get the direct reports of a user. Returns a list of users who report directly to the specified user. If no userId is provided, returns the current user's direct reports.

get_manager_chain

Get the full chain of managers for a user, from their direct manager up to the top of the organization. Useful for understanding the reporting hierarchy.

search_messages
get_my_mentions

Find recent messages where the current user was @mentioned across all Teams channels and chats.

list_teams

List all Microsoft Teams that the current user is a member of. Returns team names, descriptions, and IDs.

list_channels

List all channels in a specific Microsoft Team. Returns channel names, descriptions, types, and IDs for the specified team.

get_channel_messages

Retrieve recent messages from a specific channel in a Microsoft Team. Returns message content, sender information, and timestamps.

send_channel_message

Send a message to a specific channel in a Microsoft Team. Supports text and markdown formatting, mentions, and importance levels.

get_channel_message_replies

Get all replies to a specific message in a channel. Returns reply content, sender information, and timestamps.

reply_to_channel_message

Reply to a specific message in a channel. Supports text and markdown formatting, mentions, and importance levels.

list_team_members

List all members of a specific Microsoft Team. Returns member names, email addresses, roles, and IDs.

search_users_for_mentions

Search for users to mention in messages. Returns users with their display names, email addresses, and mention IDs.

download_message_hosted_content

Download hosted content (such as images) from a Teams channel message. Returns the content as base64 encoded data along with metadata. Use this to retrieve images or other inline content embedded in messages.

delete_channel_message

Soft delete a message in a channel. Only the message sender can delete their own messages. The message will be marked as deleted.

update_channel_message

Update (edit) a message in a channel that was previously sent. Only the message sender can update their own messages.

get_current_user

Get the current authenticated user's profile information including display name, email, job title, and department.

search_users

Search for users in the organization by name or email address. Returns matching users with their basic profile information.

get_user

Get detailed information about a specific user by their ID or email address. Returns profile information including name, email, job title, and department.

// known CVEs in dependencies1 critical7 medium9 low

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

criticalvitest@4.0.18GHSA-5xrq-8626-4rwp

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

mediumdompurify@3.3.1GHSA-39q2-94rc-95cp

DOMPurify's ADD_TAGS function form bypasses FORBID_TAGS due to short-circuit evaluation

mediumdompurify@3.3.1GHSA-cj63-jhhr-wcxv

DOMPurify USE_PROFILES prototype pollution allows event handlers

mediumdompurify@3.3.1GHSA-cjmm-f4jc-qw8r

DOMPurify ADD_ATTR predicate skips URI validation

mediumdompurify@3.3.1GHSA-cmwh-pvxp-8882

DOMPurify: Permanent `ALLOWED_ATTR` pollution via `setConfig()` bypassing the hook clone-guard (incomplete fix of the 3.4.7 hook-pollution patch)

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
🔐 secretAUTH_TOKEN
configAZURE_CLIENT_ID
🔐 secretAZURE_CLIENT_SECRET
configAZURE_TENANT_ID
configBASE_URL
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
// 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

28/28 tools missing one or more hints — auth_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); start_authentication (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_chats (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +25 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.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — download_message_hosted_content (line 898: hostedContentRegex.exec(bodyContent))

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool inputs are validated

22/28 tool handlers declare input schemas (79%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

27/28 tool handlers wrap calls in try/catch (96%)

Wrap each tool handler body in try/catch and return a structured error response.

Shell command execution

4 child_process calls — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Production dependencies are patched

7 medium severity in production deps

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.

Dependency freshness

1/14 production deps stale: @types/marked@2023-10-03 (2.7y)

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 8 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/ritchy-eu/teams-mcp?variant=verified)](https://m8ven.ai/mcp/ritchy-eu/teams-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: a7cc7b2db50846157dadc5a8c40581555ccb89f4
code hash: d21956997f42cb1af4ba9bf313e8ca99b5dec22dda9fb6aa26ef06c55a38f576
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