Skip to main content

oee-mcp

CI PyPI License: MIT

An MCP server that exposes oee, the Overall Equipment Effectiveness library for Python, as tools for AI agents: give it machine times and piece counts and it returns OEE, the time waterfall, the six big losses, TEEP, and ready-to-show charts.

Agents asked to compute or report OEE tend to do the arithmetic themselves: a performance figure inverted, schedule loss left out, or - the usual mistake - OEE figures averaged across machines, which is wrong. Generated OEE fails silently. The calculation belongs in a deterministic, versioned, validated library that the agent calls, which leaves the agent to choose the analysis and explain the result.

oee-mcp architecture: an AI agent calls the server's analysis and chart tools, which route to the validated oee core and return structured JSON or a PNG chart

Tools

Analysis tools return the library's payload: the factors, the time waterfall, the six big losses, TEEP, alerts and provenance.

Tool Purpose
compute_oee OEE, OOE and TEEP, the waterfall and the six big losses from times and counts
oee_from_log OEE from an event log of production runs and downtime events
oee_from_factors OEE from availability, performance and quality directly
aggregate_oee roll OEE up across machines or shifts correctly (sums the buckets, never averages)
reliability MTBF, MTTR and inherent availability
rolled_throughput_yield the multi-step quality view (the product of the step yields)
capacity takt time, the required rate, and whether a cycle time keeps up
loss_value the availability, performance and quality losses as lost units and money
describe_inputs the input fields, units and the metric definitions

Chart tools return a PNG image.

Tool Purpose
waterfall_chart the OEE time waterfall
loss_pareto_chart a Pareto of the six big losses
trend_chart OEE and the factors over a sequence of shifts

All tools are read-only.

Installation

Run it with uv (no install needed):

uvx oee-mcp

or install from PyPI:

pip install oee-mcp

Configuration

Add it to your MCP client. For example:

{
  "mcpServers": {
    "oee": {
      "command": "uvx",
      "args": ["oee-mcp"]
    }
  }
}

If you installed with pip, use "command": "oee-mcp" with no args.

Example

compute_oee(machine={
  "planned_production_time": 420, "downtime": 47, "ideal_rate": 60,
  "total_count": 19271, "reject_count": 423, "all_time": 480
})
  -> { "factors": { "availability": 0.888, "performance": 0.861,
                    "quality": 0.978, "oee": 0.748, "teep": 0.654 },
       "summary": "oee - ...\n  OEE 74.8% ..." }

Design

The server is a thin, stateless wrapper. All of the arithmetic lives in the oee library, which computes OEE from the standard definitions and is validated against published worked examples (Vorne, TeepTrak) and the Nakajima world-class benchmark. The server adds the tool schema, read-only annotations and an input-schema helper so an agent can format the input and act on the result.

Related

  • oee: the library this server wraps.

License

MIT. Written and maintained by Atakan Arikan, MSc Student at Tsinghua University and Politecnico di Milano.

Release files for oee-mcp 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for oee-mcp 0.2.0
File Size Uploaded
oee_mcp-0.2.0.tar.gz 10.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for oee-mcp 0.2.0
File Interpreter ABI Platform
oee_mcp-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size:19.8 kB

Release files / oee_mcp-0.2.0.tar.gz

Download URL oee_mcp-0.2.0.tar.gz
Size 10.8 kB
Tags Source
SHA-256 checksum
How to use checksums
0f4d68d78435347c049b94e2e0d32278a6ca437187e6899319cfadeae112abf1
BLAKE2b-256 checksum
How to use checksums
cf8bf533b94cded2c5678050d0fa525acc589ea768b634f3d34d5a477501176a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.12

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jun 16, 2026.

Transparency log

Release files / oee_mcp-0.2.0-py3-none-any.whl

Download URL oee_mcp-0.2.0-py3-none-any.whl
Size 9.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
a34b57b24fece68b83e178bac937716851235422fb15b17a6421d699db666391
BLAKE2b-256 checksum
How to use checksums
b4a71aba598e5887cb5658c8ff6d21a6219f3fd583bbe606fae18578a7c27168
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.12

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jun 16, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.2.0 This release

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page