Gives Claude access to Microsoft 365 mail, calendar, files, and Teams chat with per-user identity via On-Behalf-Of flow. Supports reading and drafting content, but sending is deliberately disabled.
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
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
usedrobot
Source: Glama
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
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
M365_ALLOWED_REDIRECT_URISoptional Comma-separated exact /authorize redirect_uri allowlist. Defaults to https://claude.ai/api/mcp/auth_callback; set this only if a different client connects.M365_CORS_ORIGINoptional CORS origin allowed to call this server, default https://claude.aiM365_DEFAULT_TZoptional IANA zone, default America/New_YorkM365_EVENTS_LIBRARY_PATHoptional SharePoint library the default file-search scope narrows to; unset searches the whole tenantM365_EXTRA_INSTRUCTIONSoptional House-style notes appended to the server instructions (tone, signatures, place names)M365_GRAPH_TIMEOUT_MSoptional Microsoft Graph request timeout in milliseconds, default 30000M365_ORG_NAMEoptional Your organization's name, used in the server instructionsM365_READ_ONLYoptional true disables every write toolM365_REDACT_PIIoptional true scrubs tokens, secrets, and email addresses from logsM365_TRUST_PROXYPORTTool 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 — search_email (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_email (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_calendar (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.
Tool test coverage
Only 0/13 tools referenced in tests (0%)
Write tests that reference each tool by name so every tool has at least one test.
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.
[](https://m8ven.ai/mcp/usedrobot-m365-mcp-m630co)?variant=verified to the badge URL.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