Adm1 MCP Server

This MCP server enables natural language control of anaerobic digestion modeling through the internationally recognized Anaerobic Digestion Model No.

Local serverstdioPython

What is the Adm1 MCP MCP server?

This MCP server enables natural language control of anaerobic digestion modeling through the internationally recognized Anaerobic Digestion Model No. 1 (ADM1). It bridges Claude or other LLM clients with professional wastewater treatment. The adm1 mcp mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.

Adding it to your client

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Its toolset

Everything the assistant can do here goes through one of these:

  • describe_feedstock — Convert natural language feedstock description to ADM1 state variables
  • describe_kinetics — Generate both state variables AND kinetic parameters from feedstock description
  • set_flow_parameters — Configure influent flow rate and simulation timing parameters
  • set_reactor_parameters — Set reactor-specific parameters (temperature, HRT, integration method)
  • run_simulation_tool — Execute ADM1 simulation with current parameters
  • get_stream_properties — Analyze detailed properties of influent, effluent, or biogas streams
  • get_inhibition_analysis — Process health assessment with inhibition factors and recommendations
  • get_biomass_yields — Calculate process performance metrics and efficiency
  • validate_feedstock_charge_balance — Verify thermodynamic consistency of feedstock definition
  • check_nutrient_balance — Analyze C:N:P ratios for process optimization
  • get_parameter — Retrieve current parameter values from simulation state
  • set_parameter — Modify specific simulation parameters

Configuration

You will need 2 environment variables: MCP_TIMEOUT, GOOGLE_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Python 3.8 or higher - Google API Key (for AI-powered feedstock analysis) - Claude Desktop or other MCP client application - QSDsan (automatically installed with dependencies)

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Adm1 MCP.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the adm1 mcp mcp server does with a few real requests.

When to reach for it

Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Adm1 MCP's toolset — describe_feedstock, describe_kinetics, set_flow_parameters and 11 more — is a fair guide to whether it matches your workflow. It is maintained by puran-water; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Adm1 MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
describe_feedstockConvert natural language feedstock description to ADM1 state variables
describe_kineticsGenerate both state variables AND kinetic parameters from feedstock description
set_flow_parametersConfigure influent flow rate and simulation timing parameters
set_reactor_parametersSet reactor-specific parameters (temperature, HRT, integration method)
run_simulation_toolExecute ADM1 simulation with current parameters
get_stream_propertiesAnalyze detailed properties of influent, effluent, or biogas streams
get_inhibition_analysisProcess health assessment with inhibition factors and recommendations
get_biomass_yieldsCalculate process performance metrics and efficiency
validate_feedstock_charge_balanceVerify thermodynamic consistency of feedstock definition
check_nutrient_balanceAnalyze C:N:P ratios for process optimization
get_parameterRetrieve current parameter values from simulation state
set_parameterModify specific simulation parameters
generate_reportCreate comprehensive professional simulation reports
reset_simulationReset all parameters to default values

How to install the Adm1 MCP MCP server

{
  "mcpServers": {
    "adm1-mcp": {
      "command": "C:\\path\\to\\your\\venv\\Scripts\\python.exe",
      "args": ["C:\\path\\to\\adm1-mcp\\server.py"],
      "env": {
        "MCP_TIMEOUT": "600000"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Python 3.8 or higher - Google API Key (for AI-powered feedstock analysis) - Claude Desktop or other MCP client application - QSDsan (automatically installed with dependencies)
VariableDescriptionRequired
MCP_TIMEOUTConfiguration value read at startup.Optional
GOOGLE_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Adm1 MCP to describe feedstock.
  • Use Adm1 MCP to describe kinetics.
  • Use Adm1 MCP to set flow parameters.

Frequently asked questions

It connects Adm1 MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (describe_feedstock, describe_kinetics, set_flow_parameters, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Adm1 MCP directly.