AI/ML engineering MCP server for Neo — submit tasks, track execution, and retrieve outputs.
AI/ML engineering MCP server for Neo — submit tasks, track execution, and retrieve outputs. That is what the neo — ai/ml engineering mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
Neo is built for AI engineering, not general code chat, so it goes deeper on ML, LLM, and data workflows than a typical coding agent.
Installation goes through your MCP client rather than a global install: point it at neo-mcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
The server publishes 13 tools. What each one is for:
neo_submit_task — Submit an AI/ML task. Returns thread_id immediatelyneo_list_tasks — List running and recent tasks. Reconnects pollers automaticallyneo_task_status — Check status: RUNNING / COMPLETED / WAITING_FOR_FEEDBACK / PAUSED / TERMINATEDneo_get_messages — Read full task output when COMPLETED. Capped at ~20 000 tokensneo_send_feedback — Reply when Neo asks a question (WAITING_FOR_FEEDBACK)neo_pause_task — Pause a running taskneo_resume_task — Resume a paused taskneo_stop_task — Stop and clean up a task permanentlyneo_list_integrations — List stored third-party API keys (names only, never the value)neo_add_integration — Register a GitHub PAT, HuggingFace token, Anthropic key, or OpenRouter key for Neo tasksneo_test_integration — Call the provider's API to confirm a stored key is still validneo_remove_integration — Delete a stored key from this machineConfiguration is passed through the environment: NEO_SECRET_KEY, YOUR_KEY, NEO_DEPLOYMENT_ID. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of planning and project tracking servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Neo — AI/ML Engineering's toolset — neo_submit_task, neo_list_tasks, neo_task_status and 10 more — is a fair guide to whether it matches your workflow. It is maintained by NeoAIResearch; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| neo_submit_task | Submit an AI/ML task. Returns thread_id immediately. |
| neo_list_tasks | List running and recent tasks. Reconnects pollers automatically. |
| neo_task_status | Check status: RUNNING / COMPLETED / WAITING_FOR_FEEDBACK / PAUSED / TERMINATED. |
| neo_get_messages | Read full task output when COMPLETED. Capped at ~20 000 tokens. |
| neo_send_feedback | Reply when Neo asks a question (WAITING_FOR_FEEDBACK). |
| neo_pause_task | Pause a running task. |
| neo_resume_task | Resume a paused task. |
| neo_stop_task | Stop and clean up a task permanently. |
| neo_list_integrations | List stored third-party API keys (names only, never the value). |
| neo_add_integration | Register a GitHub PAT, HuggingFace token, Anthropic key, or OpenRouter key for Neo tasks. |
| neo_test_integration | Call the provider's API to confirm a stored key is still valid. |
| neo_remove_integration | Delete a stored key from this machine. |
| Cursor | Restart Cursor after editing the file directly. Changes via the GUI apply immediately. |
{
"mcpServers": {
"neo": {
"command": "uvx",
"args": ["neo-mcp"],
"env": {
"NEO_SECRET_KEY": "your-value",
"YOUR_KEY": "your-value",
"NEO_DEPLOYMENT_ID": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| NEO_SECRET_KEY | Credential the server authenticates with. | Yes |
| YOUR_KEY | Credential the server authenticates with. | Yes |
| NEO_DEPLOYMENT_ID | Configuration value read at startup. | Optional |
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.