Integrates with Codecov for test coverage reporting and monitoring as part of the project's CI/CD pipeline, though this appears to be a development/testing integration rather than a core MCP server capability.
Hosts the project repository and provides CI/CD workflows for testing and publishing the MCP server, though this appears to be a development infrastructure integration rather than a core MCP server capability.
Built on the ucon dimensional analysis engine for Python, providing unit-aware computation capabilities through Python's scientific computing ecosystem, though this is an implementation detail rather than a service integration.
Hostable interfaces for the ucon dimensional analysis engine.
Documentation · MCP Server Guide · Tool Reference
ucon is a unit-aware computation library for Python. ucon-tools packages it into interfaces that other systems can consume — MCP servers for AI agents, REST APIs for web services, CLIs for humans at a terminal.
Each interface lives under ucon.tools.<interface> and is installable as an optional extra:
Interface | Package | Extra | Status |
MCP server |
|
| Available |
REST API |
|
| Planned |
CLI |
|
| Planned |
Related MCP server: Corrosion Engineering MCP Server
The MCP server gives AI agents (Claude, Cursor, and other MCP clients) dimensionally-verified unit conversion and computation.
Agent: "Convert 5 mcg/kg/min for an 80 kg patient to mL/h. Drug is 400 mg in 250 mL."
decompose → constraint solver places quantities, auto-bridges mcg→mg and min→h
compute → 5 × 80 kg × (60 min/h) × (1 mg/1000 mcg) × (250 mL/400 mg) = 15 mL/h
validate → result dimension matches expected unit ✓pip install ucon-tools[mcp]Requires Python 3.10+.
Claude Desktop / Claude Code — add to your MCP configuration:
{
"mcpServers": {
"ucon": {
"command": "uvx",
"args": ["--from", "ucon-tools[mcp]", "ucon-mcp"]
}
}
}Standalone:
ucon-mcp # stdio transport (default)
ucon-mcp --transport sse # SSE transport for remote clientsCore — conversion and computation:
Tool | Description |
| Convert a value between compatible units |
| Multi-step factor-label calculation with dimensional tracking |
| Build a factor chain from natural-language or structured input |
| Check if two units share the same dimension |
Discovery — explore the unit system:
Tool | Description |
| List available units, optionally filtered by dimension |
| List SI decimal and binary prefixes |
| List available physical dimensions |
| List physical constants (CODATA 2022) |
| List registered domain formulas |
Runtime extension — add units and conversions per session:
Tool | Description |
| Register a custom unit for the session |
| Add a conversion edge (linear or affine) |
| Define a custom physical constant |
| Call a registered dimensionally-typed formula |
| Clear all session-defined units, conversions, and constants |
Kind-of-Quantity (KOQ) — semantic disambiguation:
Tool | Description |
| Register a quantity kind for disambiguation |
| Declare expected quantity kind before computing |
| Validate that a result matches the declared kind |
| List registered quantity kinds |
| Create an extended dimensional basis |
| List session-defined extended bases |
ucon-tools is an interface layer. It does not reimplement dimensional analysis — it delegates to ucon for all unit resolution, conversion, and dimensional algebra. What it adds is interface-specific logic: session state, protocol handling, error suggestions, and agent-oriented features like the decompose constraint solver and KOQ disambiguation.
┌───────────────────────────────────────────────────────┐
│ Clients │
│ MCP (Claude, Cursor) · HTTP · Terminal │
└──────────┬──────────────────┬──────────────┬──────────┘
│ │ │
┌──────────▼───┐ ┌──────────▼───┐ ┌───────▼──────┐
│ ucon.tools │ │ ucon.tools │ │ ucon.tools │
│ .mcp │ │ .rest │ │ .cli │
│ │ │ │ │ │
│ sessions │ │ (planned) │ │ (planned) │
│ decompose │ │ │ │ │
│ KOQ │ │ │ │ │
│ suggestions │ │ │ │ │
└──────┬───────┘ └──────┬───────┘ └──────┬───────┘
│ │ │
└──────────────────┼─────────────────┘
│ Python imports
┌──────────▼──────────┐
│ ucon │
│ │
│ Units, Dimensions │
│ ConversionGraph │
│ Scales, Constants │
└─────────────────────┘UnitSafe is a 500-problem metrological reasoning benchmark for evaluating how well AI models handle unit conversion, dimensional analysis, and kind-of-quantity discrimination. It ships with a runner that can evaluate any model with or without MCP tool augmentation.
pip install ucon-tools[benchmark]
# Bare evaluation (model solves from memory)
python benchmarks/unitsafe/run.py -m claude:claude-haiku-4-5-20251001
# Tool-augmented evaluation (model uses MCP tools)
python benchmarks/unitsafe/run.py -m claude:claude-haiku-4-5-20251001 \
--tools --mcp-url https://mcp.ucon.dev/mcp/<instance>/mcpSee benchmarks/unitsafe/ for the full dataset, runner, and evaluation protocol.
make venv # Create virtual environment
source .ucon-tools-3.12/bin/activate # Activate
make test # Run tests
make test-all # Run across all supported Python versionsmake mcp-server # Foreground (stdio)
make mcp-server-bg # Background
make mcp-server-stop # Stop background serverAGPL-3.0. See LICENSE.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
60+ units, live FX, timezones, and date arithmetic for AI agents.
Precision math engine for AI agents. 203 exact methods. Zero hallucination.
500+ deterministic tools for AI agents: math, conversion, validation, hashing, encoding, date/time.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/the-radiativity-company/ucon-tools'
If you have feedback or need assistance with the MCP directory API, please join our Discord server