Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/dcarrascosa/ms-todo-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/dcarrascosa/ms-todo-mcp/ms-todo)<a href="https://agentmods.dev/mcp/dcarrascosa/ms-todo-mcp/ms-todo"><img src="https://agentmods.dev/badge/mcp/dcarrascosa/ms-todo-mcp/ms-todo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/dcarrascosa/ms-todo-mcp/ms-todo"><img src="https://agentmods.dev/badge/mcp/dcarrascosa/ms-todo-mcp/ms-todo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ms-todo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"ms-todo": {
"command": "python",
"args": [
"-m",
"ms_todo_mcp"
],
"env": {
"MS_TODO_CLIENT_ID": "REPLACE_WITH_APPLICATION_CLIENT_ID",
"MS_TODO_TENANT_ID": "REPLACE_WITH_DIRECTORY_TENANT_ID",
"MS_TODO_TIMEZONE": "Europe/Madrid"
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 14 lines scan A a807a2248dba
ms-todo is an MCP server published in the GitHub repository dcarrascosa/ms-todo-mcp (0 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
ms-calendar-mcp
Microsoft Calendar (Outlook Calendar) MCP server for managing events via Microsoft Graph. Runs locally from the ms-calendar-mcp npm package. Needs 1 environment variable to run.
mcp-google-tasks
MCP server for the Google Tasks API — manage task lists, create and organize tasks with due dates, notes and subtasks, track completion and sync changes. For Claude, Cursor, Codex and other AI clients. Runs locally from the mcp-google-tasks npm package.
generator-agent
MCP server "generator-agent" as configured in Azure/azure-sdk-for-net. Launched with dotnet run --project sdk/tools/Azure.GeneratorAgent/src/Azure.GeneratorAgent.csp.
amazing-marvin-complete-mcp
MCP server for Amazing Marvin with complete public-API coverage (34 tools). Runs locally from the amazing-marvin-complete-mcp Python package. Needs 3 environment variables to run.
megaplan
MCP server for Megaplan — tasks, deals, project management (Russia). Runs locally from the @theyahia/megaplan-mcp npm package. Needs 2 environment variables to run.
jira-product-discovery-mcp
MCP server for Jira Cloud REST APIs, native Jira Product Discovery Insights, and supporting attachments. Runs locally from the @enterpret/jira-product-discovery-mcp npm package.