
Neo — AI/ML Engineering
io.github.NeoResearchAIPublished by GitHub account NeoResearchAIv0.5.15Updated Oct 30, 2026
AI/ML engineering MCP server for Neo — submit tasks, track execution, and retrieve outputs.
Overview
Neo MCP server that lets an assistant submit AI/ML engineering tasks, track their execution, and retrieve the resulting outputs.
- What you can do
- Submit AI/ML engineering tasks to the Neo backend.
- Track the execution status of submitted tasks.
- Retrieve the outputs produced by finished tasks.
- Write files into a configured project or git root directory.
- When to use it
- Useful when you want an assistant to hand AI/ML engineering work to Neo and follow it through to results, rather than doing everything in the chat session. Suited to desktop clients that can run a local stdio process.
- Requirements
- Runs locally over stdio, installed from PyPI as neo-mcp and launched with uvx, so a Python/uv toolchain is needed. Requires a Neo API secret key in NEO_SECRET_KEY, an absolute project or git root path in NEO_WORKSPACE_DIR, and optionally NEO_ENVIRONMENT set to production (default) or staging. Desktop only; network access to the Neo backend.
Installation
In SourceWeft
- Open Neo — AI/ML Engineering in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
This repository has no README.
Tools
0Version history
1- v0.5.15LatestSep 16, 2026
Score
25% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
- License10 pts
Declare a license in the repository or the registry entry.