An MCP (Model Context Protocol) server that connects AI assistants to a running openLCA instance. Developed and tested with Claude Desktop; compatible with any MCP client that supports stdio transport. Built by Below280, the UK partner for openLCA.
The server exposes 35 tools covering the full LCA workflow: exploring databases, building and editing models, running calculations (scenarios, sensitivity, Monte Carlo, contribution analysis), auditing and validating models, and extracting data quality assessments. All calculation patterns are tested against production ecoinvent databases.
Connect AI assistants to openLCA. 35 tools for database search, model building, and LCIA.
2026-11-08
ดาว
—
เครื่องมือ
—
อัปไทม์
—
The server works with both ecoinvent-family databases (ecoinvent, EN15804GD, HiQLCD, BAFU) and FLCAC-family databases (LCA Commons, US LCI, USEEIO). It asks which family you are using, or auto-detects from the flow property names.
On Windows, if Claude Desktop cannot find Python, use the full path to your Python executable.
Restart Claude Desktop after saving.
Cursor
Go to Settings > Tools & MCP > Add MCP Server. Choose stdio transport, set the command to python and the argument to -m b280_olca_mcp (PyPI) or the path to b280_olca_mcp/server.py (GitHub clone). Cursor picks up config changes without restarting.
VS Code
Add the server to .vscode/mcp.json in your workspace or user settings:
Note: VS Code uses servers as the root key, not mcpServers. If using GitHub Copilot, switch Copilot Chat to Agent mode.
ChatGPT
ChatGPT cannot directly launch a local stdio server. OpenAI provides the Secure MCP Tunnel, which bridges ChatGPT to a local MCP server without exposing anything publicly. The architecture is:
The tunnel launches the B280 server (python -m b280_olca_mcp) on your machine. No changes to the B280 server are needed; it remains stdio throughout. No additional search or fetch tools are required for ChatGPT custom MCP servers.
B280's existing tool annotations (read-only, destructive, idempotent) are used by ChatGPT when deciding whether to auto-approve or prompt for confirmation.
For the full setup guide, including installation, configuration, troubleshooting and security considerations, see docs/chatgpt.md.
ChatGPT support is currently experimental. A remote Streamable HTTP transport option may be added in future for users who prefer not to run the local tunnel.
Other MCP clients
Any client that spawns a local Python process over stdin/stdout should work. With PyPI: python -m b280_olca_mcp. With GitHub clone: python path/to/b280_olca_mcp/server.py.
Beta software. This server is under active development. Test it on a copy of your database before connecting a production database. Report issues on GitHub or at [email protected].
Start it
Open your database in openLCA
Start the IPC server (Tools > Developer Tools > IPC Server > green play button, port 8080)
Restart your MCP client (or reconnect)
Ask something like 'what can you do?' or 'what's in my openLCA database?'
After creating or modifying anything, press the Refresh button in openLCA's toolbar to see changes in the GUI.
Data security
The MCP server runs locally and communicates with openLCA on localhost. The AI client (Claude Desktop or equivalent) sends tool results to its provider's servers for processing. This means process names, exchange data, parameter values, and impact results from your database will be in the conversation.
Do not connect a confidential client database through a personal or free-tier AI account. Use a business or enterprise account with appropriate data retention controls, and check your provider's data processing terms before connecting any database containing sensitive information.
Tools
Explore (11 tools)
Tool
Purpose
database_info
Counts of systems, processes, flows, methods, parameters. Auto-detects database family
set_database_family
Set ecoinvent or FLCAC naming conventions
list_systems
List/search product systems
list_methods
List/search impact assessment methods
search_processes
Find processes by name, location, or category
search_flows
Find flows by name and/or category folder
process_details
Full process info: exchanges, parameters, providers
system_parameters
List parameters for a product system
global_parameters
Look up database-level parameters
find_unit
Look up units and their flow properties
chemical_synonyms
PubChem synonym search to find database matches
Build (8 tools)
Tool
Purpose
create_global_parameter
Create or update a database-level parameter, as a value or a formula
create_flow
Create product, waste, or elementary flows
edit_flow
Add or update flow properties, or change the reference property
create_bridge
Create a bridge flow + process in one call
create_process
Build a process with exchanges, parameters, and providers
edit_process
Edit an existing process: add/update/remove exchanges and parameters
create_system
Create a product system from a process
delete_entity
Delete a process, flow, or product system (requires user confirmation; refuses to delete a flow that is still in use)
Audit (6 tools)
Tool
Purpose
extract_model
Pull everything from a model folder for inspection
audit_model
Structural checks: missing qrefs, zero amounts, unit mismatches
validate_system
Mirrors openLCA's Validate button: linking, parameters, test calculation
get_system_links
Show which providers are linked for each exchange
data_quality
Extract pedigree matrices and uncertainty from a process
find_flow_usage
Find the processes and impact categories that use a flow
Calculate (9 tools)
Tool
Purpose
calculate
Baseline impact assessment
contribution_analysis
Process-level contribution breakdown per impact category
upstream_tree
Multi-level contribution tree for one category, with pedigree scores on every branch
monte_carlo
Uncertainty simulation with statistics
inventory_flows
Raw elementary flow results (LCI level)
scenarios
Scenario calculations from conversational parameter values
scenarios_csv
Scenario calculations from a CSV file
sensitivity
Parameter sensitivity analysis
sensitivity_csv
Sensitivity analysis from a CSV file
Meta (1 tool)
Tool
Purpose
help
Show capabilities grouped by workflow, with optional topic filter
Tool annotations
Every tool carries MCP tool annotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) so clients can decide whether to auto-approve or prompt for confirmation. Explore and Calculate tools are read-only. Build tools signal that they modify the database. delete_entity is marked destructive. CSV tools are marked as writing files to disk. chemical_synonyms is marked as reaching an external service (PubChem).
Resources
The server exposes four MCP resources that AI clients can read on demand:
Resource
URI
Purpose
Database info
lca://database/info
Live database overview
Assistant instructions
lca://knowledge/instructions
Operational rules, workflows, and conventions
IPC protocol reference
lca://knowledge/ipc-protocol
Complete JSON-RPC spec for all 60 IPC methods
openLCA resources
lca://knowledge/openlca-resources
Links to databases, docs, forums, and training
The IPC protocol reference enables AI clients to help users connect to openLCA from any programming language by generating client code from the protocol specification.
EPD model building
The server includes a guided workflow for building EN15804 EPD models from LCI data. The AI maps LCI items to lifecycle modules (A1-D), creates the folder structure, bridge processes, module processes, and product systems. Ask 'build an EPD from this LCI' to start.
Standalone scripts
For repeated analyses, the server recommends standalone Python scripts that run without AI tokens. After a scenario or sensitivity calculation, it offers to generate the CSV file needed to run the equivalent script from the openLCA-IPC-tools-python repository.
Built by Below280 Limited, a UK LCA, EPD and CBAM consultancy and official UK partner for openLCA. The calculation patterns in this server are derived from production scripts used in EPD and LCA consulting work, tested against ecoinvent 3.10/3.11/3.12, EN15804GD, and US Federal LCA Commons (FLCAC) databases.