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/ebmurha/google-tasks-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/ebmurha/google-tasks-mcp/google-tasks-mcp)<a href="https://agentmods.dev/mcp/ebmurha/google-tasks-mcp/google-tasks-mcp"><img src="https://agentmods.dev/badge/mcp/ebmurha/google-tasks-mcp/google-tasks-mcp/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/ebmurha/google-tasks-mcp/google-tasks-mcp"><img src="https://agentmods.dev/badge/mcp/ebmurha/google-tasks-mcp/google-tasks-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
google-tasks-mcp 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 1mo 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
{
"google-tasks-mcp": {
"command": "uvx",
"args": [
"google-tasks-mcp"
],
"env": {
"GOOGLE_CLIENT_ID": "",
"GOOGLE_CLIENT_SECRET": "",
"GOOGLE_REDIRECT_URI": "",
"DB_PATH": "",
"DEFAULT_TASKLIST": ""
}
}
}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.
- 1mo ago First seen · 15 lines scan A d6736451f85a
google-tasks-mcp is an MCP server published in the GitHub repository ebmurha/google-tasks-mcp (2 stars, last pushed 16d ago), licensed Apache-2.0. 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
shotcut-mcp
MCP server "shotcut-mcp" as configured in matrodrigs/shotcut-mcp. Launched with https://github.com/matrodrigs/shotcut-mcp/releases/download/v1.5.6/shotcut-mcp-1.
brvm
MCP server "brvm" as configured in Dilane-Kamga/brvm-mcp-server. Runs locally from the /path/to/brvm-mcp-server Python package.
hitl-finance-mcp
MCP server for market data, macro calendar, SEC filings and risk tooling, with human-approved order execution. Runs locally from the hitl-finance-mcp Python package. Needs 11 environment variables to run.
weeek-mcp-smart
WEEEK tasks by name, not IDs — an MCP server. Runs locally from the weeek-mcp-smart npm package. Needs 5 environment variables to run.
api-mcp
Gateway connector between LLM agents and Sugra API world data through a bundled endpoint catalog and operationid calls. Works with Anthropic Claude, OpenAI GPT, Google Gemini, xAI, and any MCP-enabled IDE. Runs locally from the sugra-api-mcp Python package. Needs 1 environment variable to run.
smartsuite
MCP server "smartsuite" as configured in SmartSuiteFoundry/smartsuite-mcp-server. Launched with smartsuite-mcp. Needs 4 environment variables to run.