Shinobi runs on your own machine — the client starts it, so there is no endpoint to ping. 40 installs a week from npm. Last commit 4 Jul 2026.
Task spine + searched dead ends + approvals for AI coding agents. One brain, every device.
What the code does
We read the source, 1 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const child = spawn(execPath, [cliPath, 'dispatch', ...dispatchArgs], {
{ key: 'SHINOBI_TELEGRAM_CHAT_ID', label: 'Telegram chat ID', description: 'Numeric chat ID the bot should send digests to. Get it by sending /start to your bot and reading https://api.telegram.org/bot<TOKEN>/getUpdates.', group: 'digest' },
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add shinobi -- npx -y @shinobiapps/shinobi{
"mcpServers": {
"shinobi": {
"args": [
"-y",
"@shinobiapps/shinobi"
],
"command": "npx"
}
}
}[mcp_servers.shinobi]
command = "npx"
args = ["-y", "@shinobiapps/shinobi"]{
"mcpServers": {
"shinobi": {
"args": [
"-y",
"@shinobiapps/shinobi"
],
"command": "npx"
}
}
}{
"mcpServers": {
"shinobi": {
"args": [
"-y",
"@shinobiapps/shinobi"
],
"command": "npx"
}
}
}Alternatives to Shinobi
same job, measured the same wayShared task layer for AI coding agents. One MCP surface: task_search, task_get, task_mutate.
One shared brain for your AI coding agents: team memory, agent Q&A, tasks, and file claims.
Deterministic local cross-service API-chain discovery for AI coding agents.
Prepaid virtual cards for AI agents: one-time cards, spend caps, human approvals.
Memory for coding agents: the decisions, the dead ends, and where the last session stopped.
On-device, self-organizing memory for AI coding agents — recalls the right facts into each prompt.
Searchable football data provider docs for AI coding agents.
Human-in-the-loop for AI coding agents — ask questions, get approvals via Slack.
Shinobi — questions
Answers built from our own checks of this server.