# openLCA MCP Server

Connects AI assistants to an active openLCA session, providing 35 tools for inventory search, system modelling, and LCIA runs.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 6 repo stars
- Author: Below280
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Below280/B280-olca-MCP
- Updated: 2026-09-27
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/openlca-mcp-server

## What it does

This integration bridges your local openLCA desktop software with AI clients using stdio transport. It exposes 35 dedicated tools that inspect inventory datasets, track global parameters, adjust flows, and execute scenario analyses or Monte Carlo simulations. The package works across ecoinvent subsets and FLCAC collections, identifying conventions from flow property metadata.

The server runs as a local Python script powered by `olca-ipc`. It installs straight from PyPI via `b280-olca-mcp` or by cloning the source repository directly.

Communication fails if the openLCA built-in IPC listener on port 8080 is inactive. Any process exchanges, system recipes, and calculated impacts sent to the language model enter your assistant provider's processing pipeline.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add b280-olca-mcp -- uvx b280-olca-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from b280-olca-mcp <command>

### Codex

**Platform CLI**
```bash
codex mcp add openlca-mcp-server -- uvx b280-olca-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from b280-olca-mcp <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "openlca-mcp-server": {
            "command": "uvx",
            "args": [
                "b280-olca-mcp"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from b280-olca-mcp <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "openlca-mcp-server": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "b280-olca-mcp"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from b280-olca-mcp <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add openlca-mcp-server uvx b280-olca-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from b280-olca-mcp <command>

## When to use it
- query processes and flows across ecoinvent and US LCI datasets
- construct new product systems from bill-of-materials prompts
- evaluate impact variations across multiple transport scenarios
- calculate uncertainty distributions using Monte Carlo runs

## Example prompts
- Inspect my openLCA database and report the total count of flows and processes
- Create a model requiring 34 kWh UK electricity and 5 kg sodium hydroxide
- Run scenario comparisons evaluating transport differences between 100 km and 500 km

## Similar
- [carbon-factor-matcher](https://affpapa.org/en/nevibecode/mcp/carbon-factor-matcher.md) — MCP server · 3609 installs
- [nature-figure](https://affpapa.org/en/nevibecode/skills/nature-figure.md) — skill · 20700 installs
- [nature-data](https://affpapa.org/en/nevibecode/skills/nature-data.md) — skill · 16800 installs
- [NOAA Recon MCP Server](https://affpapa.org/en/nevibecode/mcp/noaa-recon-mcp-server.md) — MCP server · ★ 10 repo stars
- [zotero-bridge](https://affpapa.org/en/nevibecode/mcp/zotero-bridge.md) — MCP server · ★ 10 repo stars
- [gdelt-mcp-server](https://affpapa.org/en/nevibecode/mcp/gdelt-mcp-server.md) — MCP server · ★ 10 repo stars

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
