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/asachs01/float-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/asachs01/float-mcp/task-master-ai)<a href="https://agentmods.dev/mcp/asachs01/float-mcp/task-master-ai"><img src="https://agentmods.dev/badge/mcp/asachs01/float-mcp/task-master-ai/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/asachs01/float-mcp/task-master-ai"><img src="https://agentmods.dev/badge/mcp/asachs01/float-mcp/task-master-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
task-master-ai 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.
This is a copy
92% identical to task-master-ai — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"task-master-ai": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"--package=task-master-ai",
"task-master-ai"
],
"env": {
"ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
"PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
"OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
"GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
"XAI_API_KEY": "YOUR_XAI_KEY_HERE",
"OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
"MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
"AZURE_OPENAI_API_KEY": "YOUR_AZURE_KEY_HERE",
"OLLAMA_API_KEY": "YOUR_OLLAMA_API_KEY_HERE"
}
}
}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 · 22 lines scan A df11bb11b19d
task-master-ai is an MCP server published in the GitHub repository asachs01/float-mcp (2 stars, last pushed 8mo 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. It is 92% identical to task-master-ai, differing in 1 line, and is treated as a copy.
Other mcp servers, from other repositories
openproject-mcp-server
MCP server for OpenProject: 89 tools for work packages, attachments, git activity, time tracking, meetings and reporting over the API v3. Runs locally from the openproject-mcp-server Python package. Needs 5 environment variables to run.
taiga-mcp-server
MCP server connecting Claude, Cursor, Windsurf, and other AI assistants to Taiga (Cloud and self-hosted) — projects, epics, user stories, tasks, issues, sprints, wiki, and more. Runs locally from the @madebyclowd/taiga-mcp-server npm package.
mcp-redmine-rest
Model Context Protocol server that connects Claude, or any other MCP client, to a Redmine instance via its REST API. Runs locally from the mcp-redmine-rest Python package.
jira-mcp
Jira MCP for controlling Jira through Jira Command Line. Runs locally from the jira-tools-mcp Python package. Needs 2 environment variables to run.
asana-project-ops
Highly efficient and robust MCP server for Asana project management with advanced batch operations, direct section assignment, and enterprise-grade reliability. Runs locally from the @n0zer0d4y/asana-project-ops npm package.
huly-mcp
Complete MCP server for Huly project management with 209 tools across 23 categories. Supports custom task types, project-scoped status workflows, and read-side Process plugin tools. Runs locally from the @dugynoo/huly-mcp npm package. Needs 5 environment variables to run.