Neo — AI/ML Engineering runs on your own machine — the client starts it, so there is no endpoint to ping. 178 installs a week from pypi.
AI/ML engineering MCP server for Neo — submit tasks, track execution, and retrieve outputs.
The linked repository no longer exists on GitHub — it was deleted or made private.
This one has been quiet for a while
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
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 MCPServer -e 'NEO_SECRET_KEY=<NEO_SECRET_KEY>' -e 'NEO_WORKSPACE_DIR=<NEO_WORKSPACE_DIR>' -- uvx neo-mcp{
"mcpServers": {
"MCPServer": {
"command": "uvx",
"args": [
"neo-mcp"
],
"env": {
"NEO_SECRET_KEY": "<NEO_SECRET_KEY>",
"NEO_WORKSPACE_DIR": "<NEO_WORKSPACE_DIR>"
}
}
}
}[mcp_servers.MCPServer]
command = "uvx"
args = ["neo-mcp"]
env = { NEO_SECRET_KEY = "<NEO_SECRET_KEY>", NEO_WORKSPACE_DIR = "<NEO_WORKSPACE_DIR>" }{
"mcpServers": {
"MCPServer": {
"command": "uvx",
"args": [
"neo-mcp"
],
"env": {
"NEO_SECRET_KEY": "<NEO_SECRET_KEY>",
"NEO_WORKSPACE_DIR": "<NEO_WORKSPACE_DIR>"
}
}
}
}{
"servers": {
"MCPServer": {
"type": "stdio",
"command": "uvx",
"args": [
"neo-mcp"
],
"env": {
"NEO_SECRET_KEY": "<NEO_SECRET_KEY>",
"NEO_WORKSPACE_DIR": "<NEO_WORKSPACE_DIR>"
}
}
}
}Put your own values in place of
<NEO_SECRET_KEY> (Your Neo API secret key (starts with sk-v1-). Get one at https://heyneo.com), <NEO_WORKSPACE_DIR> (Absolute path to your project/git root where Neo writes files. Required for Postman and recommended for all clients).
The author’s registry entry marks them as required.
Optional settings from the registry entry, left out of the block above:
NEO_ENVIRONMENT (Neo backend environment: 'production' (default) or 'staging').
Alternatives to Neo — AI/ML Engineering
same job, measured the same wayAI/ML engineering MCP server for Neo — submit tasks, track execution, and retrieve outputs.
MCP server for AI-enhanced prompt engineering and request conversion.
MCP server for AI agents to report infrastructure needs they encounter during task execution
MCP server for data engineering: validation, transformation, visualization, and APIs.
MCP server for ModusOp — projects, tasks, time tracking, and retainers for AI assistants.
VePrompts MCP server for 800+ MCP servers, prompt libraries, and AI engineering.
MCP server for the Frida reverse engineering toolkit.
One MCP server for web search, page extraction, and cited research.
Neo — AI/ML Engineering — questions
Answers built from our own checks of this server.