microsoft-todo-safe-mcp (Saenai/microsoft-todo-safe-mcp) is an MCP server listed on the M8ven Trust Index. It scores 52 out of 100, grade D. It declares 26 tools. No publisher has claimed this listing.
Enables safe AI-assisted cleanup of Microsoft To Do tasks with backup, preview, confirmation, and audit safeguards.
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
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
Saenai
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
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.
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-statusCheck if you're authenticated with Microsoft Graph API. Shows current token status and expiration time, and indicates if the token needs to be refreshed.
setup_safe_listsCreate or bind the soft-archive lists Archive, Someday, and Needs Review.
export_backupExport all visible Microsoft To Do lists, tasks, and checklist items to a local JSON backup file.
propose_planGenerate a conservative safe task-management plan from a local backup. This never writes to Microsoft To Do.
analyze_todo_systemAnalyze a local Microsoft To Do backup and recommend a high-efficiency list operating system. This never writes to Microsoft To Do.
analyze_low_maintenance_systemAnalyze a local Microsoft To Do backup for low-maintenance cleanup candidates and system pressure. This never writes to Microsoft To Do.
export_completed_archiveExport completed tasks from a local Microsoft To Do backup into Markdown and JSON files for external notes/archive use. This never writes to Microsoft To Do.
validate_planValidate a strict safe task-management JSON plan. This never writes to Microsoft To Do.
preview_planPreview a validated safe task-management JSON plan. This never writes to Microsoft To Do.
apply_planApply a previously previewed safe task-management plan after explicit confirmation. Creates a backup and JSONL audit log before writing.
restore_previewPreview a local backup file for restore planning. This never writes to Microsoft To Do.
get-task-listsGet all Microsoft Todo task lists (the top-level containers that organize your tasks). Shows list names, IDs, and indicates default or shared lists.
get-task-lists-organizedGet all task lists organized into logical folders/categories based on naming patterns, emoji prefixes, and sharing status. Provides a hierarchical view similar to folder organization.
create-task-listCreate a new task list (top-level container) in Microsoft Todo to help organize your tasks into categories or projects.
update-task-listUpdate the name of an existing task list (top-level container) in Microsoft Todo.
delete-task-listDelete a task list (top-level container) from Microsoft Todo. This will remove the list and all tasks within it.
get-tasksGet tasks from a specific Microsoft Todo list. These are the main todo items that can contain checklist items (subtasks).
create-taskCreate a new task in a specific Microsoft Todo list. A task is the main todo item that can have a title, description, due date, and other properties.
update-taskUpdate an existing task in Microsoft Todo. Allows changing any properties of the task including title, due date, importance, etc.
delete-taskDelete a task from a Microsoft Todo list. This will remove the task and all its checklist items (subtasks).
get-checklist-itemsGet checklist items (subtasks) for a specific task. Checklist items are smaller steps or components that belong to a parent task.
create-checklist-itemCreate a new checklist item (subtask) for a task. Checklist items help break down a task into smaller, manageable steps.
update-checklist-itemUpdate an existing checklist item (subtask). Allows changing the text content or completion status of the subtask.
delete-checklist-itemDelete a checklist item (subtask) from a task. This removes just the specific subtask, not the parent task.
archive-completed-tasksMove completed tasks older than a specified number of days from one list to another (archive) list. Useful for cleaning up active lists while preserving historical tasks.
test-graph-api-explorationTest various Graph API queries to discover hidden properties or endpoints for folder/group organization in Microsoft To Do.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
CLIENT_IDCLIENT_SECRETMSTODO_SAFE_DATA_DIRMSTODO_TOKEN_FILEMS_TODO_ACCESS_TOKENMS_TODO_REFRESH_TOKENREDIRECT_URITENANT_IDTool 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
26/26 tools missing one or more hints — auth-status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); setup_safe_lists (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); export_backup (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +23 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 0/26 tools referenced in tests (0%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
1 call in production code run through a shell (src/setup.ts:69)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Secrets not written to files
2 secret values written to files
Avoid persisting secrets to disk. Keep them in memory or your secret manager.
No arbitrary install scripts
Has postinstall/preinstall script — runs arbitrary code on npm install
Remove postinstall/preinstall hooks unless they’re essential.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.21.1 (high), @modelcontextprotocol/sdk@1.21.1 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
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/saenai/microsoft-todo-safe-mcp)?variant=verified from the 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