Physical & geospatialPublic source

SCADA MCP Server

A SCADA / industrial-control platform for ADK-Rust Enterprise energy & utility agents. 27 MCP tools covering sites & assets, tags/points telemetry, real-time readings + a historian, an alarm lifecycle,…

Open the source Read the official guide ↗

What it gives an agent

A purpose-built capability behind one MCP connection.

The server owns its domain logic and publishes a tool contract an MCP client can discover. ADK-Rust can load that contract into an agent, normalize each schema for the chosen model provider, and keep the connection lifecycle outside the agent’s business logic.

Sites & assets — sites by sector (electric/gas/water/renewable); assets with operating state (in_service/out_of_service/locked_out/faulted) and lockout/tagout.

Tags / points — addressable telemetry and control points typed analog/status (read-only) or setpoint/control (writable), with engineering ranges and warn/crit thresholds.

Telemetry & historian — ingest_reading records history and auto-raises/clears threshold alarms; tag_history and tag_trend for analysis.

Alarms — lifecycle of active → acknowledged → cleared, by severity.

Control — issue_command runs the interlock chain and applies the value only on an all-pass; check_interlocks is a read-only dry-run.

Outages — report_outage auto-triages priority (P1 highest); outage_queue is the priority-ordered work queue.

Maintenance — work orders (preventive/corrective/inspection/emergency) with scheduling and assignment.

Architecture

How SCADA MCP Server fits into an agent system.

The model never needs the implementation details or credentials of the system behind the server. It sees reviewed tool definitions. The MCP client handles discovery and calls, while the server keeps ownership of validation, policy, and communication with its domain system.

ADK-Rust agent

Chooses a capability from the reviewed tool catalog.

→

MCP client

Discovers schemas, sends calls, and receives typed content.

→

SCADA MCP Server

Validates the request and owns 27 documented tool contracts.

→

Domain system

Keeps the API, data, credentials, and business rules behind the server.

Connection: stdio · Server framework: ADK MCP SDK + rmcp

SCADA MCP Server architecture diagram from its official repository

Tool catalog

What can an agent ask SCADA MCP Server to do?

Each tool has a stable name, a human-readable purpose, and a JSON input contract discovered during MCP initialization. Risk classes come from the project’s registry manifest when one is available.

27 named tools

create_site

internal write

list_sites

List sites by sector

read only

create_asset

internal write

get_asset

Get an asset (state, lockout)

read only

list_assets

List assets by site/kind/state

read only

set_asset_state

Set asset operating state (affects control interlocks)

external write

set_lockout

Apply/release lockout-tagout (blocks control)

external write

create_tag

Define a tag/point (analog/status/setpoint/control)

internal write

get_tag

Get a tag's value, ranges, thresholds

read only

list_tags

List an asset's tags with live values

read only

ingest_reading

Ingest a telemetry reading (auto alarm eval)

internal write

tag_history

Historian readings for a tag

read only

Governance

Understand the effect of every tool.

A server connection inherits the authority of its credentials and deployment environment. The declarations below come from this project’s README and MCP registry manifest; your application still decides which tools an agent receives and where approval is required.

13 read only11 internal write3 external write

Interlock chain on every command (issue_command), checked in order; the value is applied only if all pass, and a rejected command is recorded but never executed:
Dry-run first — check_interlocks (read-only) lets an agent confirm feasibility before requesting an approval-gated command.
Approval-gated external writes — issue_command, set_lockout, and set_asset_state are external_write + requires_approval in the manifest; risk_level = "critical".
Full audit trail — every command (executed and rejected) and state change is recorded (command_history, audit_log).
Reference engine — this is an in-memory reference implementation. A production deployment must additionally enforce these interlocks at the RTU/PLC/field level and through hardware…

MCP surface

What the current documentation declares.

MCP can carry tools, resources, prompts, structured results, progress, cancellation, and long-running work. This record highlights the modern protocol features explicitly mentioned by this repository.

The current README concentrates on its tool surface. Check the source and release notes before relying on optional MCP capabilities beyond tool discovery and invocation.

ADK MCP SDKrmcpRegistry manifest

Install and connect

Follow the project’s documented starting point.

Install the server in the environment that owns its credentials and domain access. Add it to your MCP host, verify the discovered tools, and narrow the toolset before giving it to a production agent.

Install

cargo install mcp-scada

ADK-Rust connection shape

let toolset = McpToolset::from_stdio(
    "mcp-scada",
    ["mcp-scada"],
).await?;

let agent = LlmAgentBuilder::new("agent")
    .tools(toolset.tools().await?)
    .build()?;

Commands and configuration are extracted from the public README. Confirm prerequisites, environment variables, and release-specific options in the official documentation before deployment.

Official documentation

Continue with the project maintainers’ source of truth.

This page provides an approachable map of the server. The repository remains authoritative for exact schemas, prerequisites, configuration, examples, tests, releases, and security updates.

Overview ↗README.md CHANGELOG ↗CHANGELOG.md Architecture ↗docs/architecture.svg Issues and support ↗github.com issues

Keep exploring