units-static
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@units-staticconvert 5 miles to kilometers"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
units-static
High-quality unit conversion MCP server with fixed conversion tables (no
network I/O). Companion dogfood to meteo-static:
this repo is the good MCP baseline — tools are designed so schema-clarity
judges should score well (clear names, deep descriptions, strict enums, typed
output schemas).
Tools
Tool | Description |
| List supported unit ids (optionally filter by dimension) |
| Convert length between SI / imperial units |
| Convert mass / weight |
| Convert °C / °F / K (rejects below absolute zero) |
| Convert liquid volume (US + imperial + SI) |
| Compare two quantities in the same dimension |
Related MCP server: gnomon-mcp
Design goals (judge-friendly)
Names: lowercase, descriptive, verb-led (
convert_*,list_*,compare_*)Descriptions: when to call the tool, what it does, what not to use it for
Inputs: closed enums / constrained fields with per-parameter descriptions
Outputs: Pydantic models → MCP
outputSchemaobjects (no bare arrays)Deterministic: static factor tables; safe for CI evals
Running
STDIO (default)
pip install -r requirements.txt
python src/server.pyStreamable HTTP
pip install -r requirements.txt
python src/server.py --transport http --port 8000Export tools/list (local)
pip install -r requirements.txt
python scripts/export_tools_list.py --output ci/tools-list.jsonGitHub Actions
Shared Actions from plugin-federation/actions:
Job | Purpose |
| Export |
| OIDC → catalog, schema verify, selection-surface embeddings, LLM-as-judge (fail-on-judge-fail) |
| Functional evals ( |
Nexus pipeline setup
Variable / secret | Purpose |
| e.g. |
| Must match Nexus GitHub audience |
| Target tenant UUID |
| New stable tool source UUID for this server |
| Judge model + functional evals |
| Embeddings ( |
Embeddings use name + description + input schema (tool-embedding-report/v1).
Embed failures do not fail judges. Similarity reports are derived by Nexus from
a registered semantic-analysis profile whose profileVersion and model match
text-embedding-3-small (1536 dimensions unless shortened). CI cannot create
that profile.
Also register this repository in the tenant OIDC trust policy (same pattern as
meteo-static) and create a dedicated tool source for units-static.
Status
Working — stdio + streamable HTTP
Tools — six conversion tools with structured I/O
CI — Plugin Federation Actions with hard fail gates
This server cannot be deployed
Maintenance
Related MCP Connectors
Remote MCP server for deterministic educational practice-assessment score conversions.
Read-only developer, date, finance, and text utilities. Authless remote MCP server by Clean.tools.
Read-only MCP server for The Quiet Protocol's engines, benchmarks, proof, and business data.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA comprehensive suite of four MCP servers providing real-time stock market data, currency conversion between 160+ currencies, world timezone conversion, and unit conversion across 10 measurement categories. Features beautiful web interfaces and ChatGPT integration capabilities.-
- AlicenseAqualityCmaintenanceA small MCP server for the boring-but-essential utilities every model needs: dates, calendars, arithmetic, unit conversion. Use it so your assistant stops "next-token guessing" math and date math.425 PyPI1MIT
- AlicenseCqualityDmaintenanceA comprehensive MCP server that turns any AI assistant into a powerful mathematical computation engine, providing 52 advanced functions, 158 unit conversions, financial calculations, and secure AST-based evaluation.1816MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP server providing deterministic base conversions (binary, hex, octal, decimal, base64) for AI agents, eliminating hallucination risks in low-level data processing.6 npm3-