units-static
A deterministic unit conversion MCP server with fixed tables, offering tools to convert length, mass, temperature, and volume, list units, and compare quantities. Designed for judge-friendly schema clarity and no network I/O.
README
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_units |
List supported unit ids (optionally filter by dimension) |
convert_length |
Convert length between SI / imperial units |
convert_mass |
Convert mass / weight |
convert_temperature |
Convert °C / °F / K (rejects below absolute zero) |
convert_volume |
Convert liquid volume (US + imperial + SI) |
compare_quantities |
Compare two quantities in the same dimension |
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.py
Streamable HTTP
pip install -r requirements.txt
python src/server.py --transport http --port 8000
Export tools/list (local)
pip install -r requirements.txt
python scripts/export_tools_list.py --output ci/tools-list.json
GitHub Actions
Shared Actions from plugin-federation/actions:
| Job | Purpose |
|---|---|
tools-list-validate |
Export tools/list + structural validation |
nexus-catalog |
OIDC → catalog + embeddings + LLM-as-judge (fail-on-judge-fail) |
evals |
Functional evals (evals/evaluations.xml, 100% threshold) |
Nexus pipeline setup
| Variable / secret | Purpose |
|---|---|
NEXUS_URL |
e.g. https://api.nonprod.plugin-federation.com |
NEXUS_OIDC_AUDIENCE |
Must match Nexus GitHub audience |
TENANT_ID |
Target tenant UUID |
MCP_SOURCE_ID |
New stable tool source UUID for this server |
XAI_API_KEY |
Judge model + functional evals |
OPENAI_API_KEY |
Embeddings (text-embedding-3-small) |
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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.