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/evvfebruary/kaiten-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/evvfebruary/kaiten-mcp/kaiten)<a href="https://agentmods.dev/mcp/evvfebruary/kaiten-mcp/kaiten"><img src="https://agentmods.dev/badge/mcp/evvfebruary/kaiten-mcp/kaiten/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/evvfebruary/kaiten-mcp/kaiten"><img src="https://agentmods.dev/badge/mcp/evvfebruary/kaiten-mcp/kaiten.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
kaiten 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
{
"kaiten": {
"command": "uv",
"args": [
"run",
"kaiten-mcp",
"--transport",
"stdio"
],
"env": {
"KAITEN_API_TOKEN": "${KAITEN_API_TOKEN}",
"KAITEN_WORKSPACE_SLUG": "${KAITEN_WORKSPACE_SLUG}"
}
}
}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 · 15 lines scan A a6397e4dd182
kaiten is an MCP server published in the GitHub repository evvfebruary/kaiten-mcp (1 stars, last pushed 1mo 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
astravue-mcp
Manage projects, tasks, time tracking, and team collaboration through natural language. Remote server at api.astravue.com.
amnesic
The MCP server with the most ironic name in the registry — persistent semantic memory for your SQL databases. Runs locally from the amnesic Python package.
kelvia-mcp
Task manager your agent can fully operate: boards, tasks, sprints, roles, worklogs, day planner. Runs locally from the kelvia-mcp npm package. Needs 3 environment variables to run.
laver-mcp
Kanban boards, sprints, tickets and a team wiki, with versioned writes for concurrent agents. Runs locally from the @laver/mcp npm package. Needs 3 environment variables to run.
planka
MCP server for PLANKA kanban boards. Full CRUD for cards, tasks, comments, and labels. Runs locally from the @gogogadgetbytes/planka-mcp npm package. Needs 3 environment variables to run.
veyra-tasks
Task manager with projects, priorities, and status for AI agents. Reads free, writes require Veyra. Runs locally from the veyra-tasks npm package.