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/smaurier/gtasks-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/smaurier/gtasks-mcp/gtasks-mcp)<a href="https://agentmods.dev/mcp/smaurier/gtasks-mcp/gtasks-mcp"><img src="https://agentmods.dev/badge/mcp/smaurier/gtasks-mcp/gtasks-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/smaurier/gtasks-mcp/gtasks-mcp"><img src="https://agentmods.dev/badge/mcp/smaurier/gtasks-mcp/gtasks-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
gtasks-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 8d 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
{ "gtasks-mcp": { "command": "npx", "args": [ "-y", "gtasks-mcp" ] } }
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.
- 8d ago First seen · 9 lines scan A e84391b4d651
gtasks-mcp is an MCP server published in the GitHub repository smaurier/gtasks-mcp (0 stars, last pushed 7d 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
cortex-gateway
MCP server "cortex-gateway" as configured in wellknownmcp/cortex-gateway. Runs in Docker (ghcr.io/wellknownmcp/cortex-gateway:v0.2.0). Needs 4 environment variables to run.
manifold
MCP server "manifold" as configured in nonchan7720/manifold. Runs in Docker (ghcr.io/nonchan7720/manifold:v1.9.0). Needs 2 environment variables to run.
mcp
Citable retrieval across papers, books, patents, Wikipedia, and live social sources. Remote server at mcp.spacefrontiers.org.
power-automate-mcp
MCP server "power-automate-mcp" as configured in karenrebecag/PowerAutomateMCP. Runs locally from the power-automate-mcp npm package.
mcp-server-auth-template
MCP server "mcp-server-auth-template" as configured in brunovicco/mcp-server-auth-template. Runs in Docker (ghcr.io/brunovicco/mcp-server-auth-template:v0.6.2). Needs 10 environment variables to run.
aipod
A framework for packaging the models provided by the AI. Runs locally from the aipod Python package.