MCP server for Hatchet — let AI agents observe and operate your workflows: runs, logs, workers, metrics, plus trigger/cancel/replay. Single-token setup, npx-installable.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add hatchet --env HATCHET_CLIENT_TOKEN='<HATCHET_CLIENT_TOKEN>' -- npx -y hatchet-mcp~/.codex/config.toml
[mcp_servers.hatchet]
command = "npx"
args = ["-y", "hatchet-mcp"]
env = { HATCHET_CLIENT_TOKEN = "<HATCHET_CLIENT_TOKEN>" }
# codex mcp add hatchet --env HATCHET_CLIENT_TOKEN='<HATCHET_CLIENT_TOKEN>' -- npx -y hatchet-mcp~/.cursor/mcp.json
{
"mcpServers": {
"hatchet": {
"command": "npx",
"args": [
"-y",
"hatchet-mcp"
],
"env": {
"HATCHET_CLIENT_TOKEN": "<HATCHET_CLIENT_TOKEN>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"hatchet": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"hatchet-mcp"
],
"env": {
"HATCHET_CLIENT_TOKEN": "<HATCHET_CLIENT_TOKEN>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"hatchet": {
"command": "npx",
"args": [
"-y",
"hatchet-mcp"
],
"env": {
"HATCHET_CLIENT_TOKEN": "<HATCHET_CLIENT_TOKEN>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"hatchet": {
"command": "npx",
"args": [
"-y",
"hatchet-mcp"
],
"env": {
"HATCHET_CLIENT_TOKEN": "<HATCHET_CLIENT_TOKEN>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"hatchet": {
"command": "npx",
"args": [
"-y",
"hatchet-mcp"
],
"env": {
"HATCHET_CLIENT_TOKEN": "<HATCHET_CLIENT_TOKEN>"
}
}
}
}Environment variables
HATCHET_CLIENT_TOKEN
Replace the placeholders with your own credentials and keep them out of version control.