
noodlelab
io.github.nkalisPublished by GitHub account nkalisv0.8.1Updated Oct 24, 2026
Verifiable science: units, GUM uncertainty, requirements with margins and provenance on every run.
Overview
Local MCP server for verifiable scientific computation: units, GUM uncertainty, and requirement checks with margins and provenance on every run.
- What you can do
- The manifest lists no tools, so capabilities come from the short description only.
- It is presented as a way to make scientific and engineering calculations verifiable.
- It covers physical units, uncertainty evaluation following the GUM approach, and requirements checked with margins.
- Each run is reported with provenance, so results can be traced back to their inputs and assumptions.
- When to use it
- Worth considering when an assistant's numeric or engineering answers need explicit units, stated uncertainty, and a pass/fail check against requirements that can be audited afterwards.
- Requirements
- Runs as a local process on the user's machine, installed from the PyPI package noodlelab and started with uvx, so a Python environment with uv is needed. Desktop only; no authentication, environment variables or headers are declared.
Installation
In SourceWeft
- Open noodlelab 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.
Tools
0Version history
6- v0.8.1LatestOct 6, 2026
- v0.7.1Oct 2, 2026
- v0.7.0Oct 1, 2026
- v0.6.0Oct 1, 2026
- v0.5.0Sep 30, 2026
- v0.2.1Sep 27, 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.