Skip to main content

bridge-mcp-server

Cross-platform intelligence bridge — correlate Ignition SCADA tags with Studio 5000 PLC logic end-to-end.

License: MIT Python 3.10+ MCP

[!NOTE] This connector is early community tooling from Nodeblue. The complete system is Nexus, our industrial intelligence platform — these repos are just its connector layers.

Nexus reads and reasons over your entire operation: PLC logic, SCADA systems, live controller data, documentation, fault history, and MES/ERP records. It works across vendors — Rockwell, Siemens, Ignition, the CODESYS family, and 500+ more brands through PLCopen. It diagnoses faults on the running line, holds a persistent memory of the operation, and answers in plain English, cited to the source.

The Nodeblue open-source connectors

Connector What it does
studio5000-mcp-server Rockwell/Allen-Bradley Studio 5000 — parse L5X exports: tags, UDTs, routines, AOIs, cross-references
ignition-mcp-server Ignition SCADA — views, scripts, tags, UDTs, alarms, live gateway read/write
bridge-mcp-server (this repo) Correlates Ignition SCADA tags with Studio 5000 PLC logic end-to-end

What This Does

bridge-mcp-server connects ignition-mcp-server and studio5000-mcp-server via the Model Context Protocol. It gives AI agents the ability to:

  • Correlate — build a full tag-by-tag map between an Ignition SCADA project and a Studio 5000 L5X PLC export
  • Trace — follow a single tag end-to-end from Ignition config → OPC item path → L5X tag → every rung of PLC logic that references it
  • Find gaps — identify commissioning mismatches: Ignition OPC tags with no PLC counterpart, and L5X tags with no Ignition reference

It maps Ignition OPC tag paths to L5X tag names using convention-based normalization (with optional explicit mapping file override), then leverages the Studio 5000 cross-reference engine to find every line of PLC logic that references the matched tag.

Why This Exists

Ignition and Studio 5000 are the two most common platforms in North American industrial automation, and they almost always exist together — yet there's no tooling that connects them. Commissioning engineers manually cross-reference tag databases in spreadsheets. This server automates that.

Built and maintained by Nodeblue. These connectors are early community tooling from our work on Nexus, where this capability ships production-grade — alongside cross-vendor correlation, live fault diagnosis, and a persistent memory of the operation.


Installation

Install from source:

git clone https://github.com/Nodeblue-AI/bridge-mcp-server.git
cd bridge-mcp-server
pip install -e .

This also installs ignition-mcp-server and studio5000-mcp-server as dependencies.

Requires Python 3.10+.

Note: pip install bridge-mcp-server from PyPI is coming soon. For now, install from source as shown above.


Quick Start

stdio (local — kiro-cli, Claude Desktop, Claude Code)

bridge-mcp-server

SSE (remote — server on one machine, agent on another)

bridge-mcp-server --transport sse --port 8082

Configuration

kiro-cli

Add to your ~/.kiro/settings.json:

{
  "mcpServers": {
    "bridge": {
      "command": "bridge-mcp-server",
      "args": []
    }
  }
}

Claude Desktop

Add to your Claude Desktop MCP config:

{
  "mcpServers": {
    "bridge": {
      "command": "bridge-mcp-server",
      "args": []
    }
  }
}

SSE (remote)

Start the server on your engineering workstation:

bridge-mcp-server --transport sse --host 0.0.0.0 --port 8082

Connect from any MCP client using the SSE URL: http://<host>:8082/sse


Available Tools

ping

Health check. Returns "pong".

correlate_projects(ignition_path, l5x_path, mapping_file?)

Build a full correlation map between an Ignition project and an L5X PLC project.

correlate_projects("/path/to/ignition-project", "/path/to/plc.l5x")

Returns:

{
  "matched": [
    {
      "ignitionPath": "Conveyors/Line1/Running",
      "opcItemPath": "ns=1;s=[PLC]Motor_1.Running",
      "l5xTag": "Motor_1",
      "l5xMember": "Motor_1.Running",
      "l5xDataType": "Motor_UDT",
      "l5xScope": "controller"
    }
  ],
  "ignitionOnly": [],
  "l5xOnly": [
    {"name": "EmergencyStop", "dataType": "BOOL", "scope": "controller"}
  ],
  "stats": {"matched": 3, "ignitionOnly": 0, "l5xOnly": 5, "totalIgnitionOpc": 3, "totalL5x": 8}
}

trace_tag(ignition_path, l5x_path, tag_name, mapping_file?)

Deep end-to-end trace of a single tag from SCADA to PLC logic.

trace_tag("/path/to/ignition-project", "/path/to/plc.l5x", "Running")

Returns the complete signal chain: Ignition tag config → OPC item path → L5X tag details → every rung/line of PLC logic that references it.

find_unmapped_tags(ignition_path, l5x_path, mapping_file?)

Identify commissioning gaps — tags that exist on one side but not the other.

find_unmapped_tags("/path/to/ignition-project", "/path/to/plc.l5x")

OPC Path Mapping

The bridge uses convention-based mapping by default:

Ignition OPC Item Path L5X Tag Name
ns=1;s=[PLC]Motor_1.Running Motor_1.Running
[PLC]Motor_1.Running Motor_1.Running
[PLC]Program:MainProgram.StartPB Program:MainProgram.StartPB
Motor_1.Running Motor_1.Running (passthrough)

For complex setups (aliased tags, scaled values), provide a JSON mapping file:

{
  "ns=1;s=[PLC]Custom_Alias": "Motor_1.Running",
  "ns=1;s=[PLC]Scaled_Speed": "LineSpeed"
}

Pass it via mapping_file parameter on any tool.


Use Cases

Pre-commissioning validation

"Show me every Ignition OPC tag and its matching PLC tag — I need to verify the full correlation before we go live."

Agent calls: correlate_projects("/projects/MyPlant", "/plc/MainPLC.l5x")

Alarm root-cause analysis

"The Conveyors/Line1/Running tag is triggering an alarm in Ignition. What PLC logic drives it?"

Agent calls: trace_tag("/projects/MyPlant", "/plc/MainPLC.l5x", "Running")

Agent: The Ignition tag Conveyors/Line1/Running maps to PLC tag Motor_1.Running
via OPC path ns=1;s=[SampleController]Motor_1.Running.

Motor_1 is a Motor_UDT instance. Motor_1.Running is referenced in:
- MainProgram/MainRoutine rung 1: Motor_Control AOI call
- MainProgram/MainRoutine rung 2: Fault detection branch
- MainProgram/FaultHandler line 1: IF Motor_1.Faulted THEN...

The Motor_Control AOI sets Running from MotorFeedback (rung 4).

Commissioning gap analysis

"Which PLC tags exist in the L5X but aren't wired up in Ignition yet? We need to close gaps before FAT."

Agent calls: find_unmapped_tags("/projects/MyPlant", "/plc/MainPLC.l5x")

Roadmap

v0.4 — Cross-Platform Correlation ✅

  • correlate_projects — full tag-by-tag map between Ignition and L5X
  • trace_tag — end-to-end signal chain from SCADA to PLC logic
  • find_unmapped_tags — commissioning gap detection
  • Convention-based OPC path → L5X tag name normalization
  • Optional JSON mapping file for explicit overrides
  • Correlation index caching per project pair
  • stdio and SSE transport support

Maintenance

  • Mapping file auto-generation from correlation results (contributions welcome)
  • PyPI publication (pip install bridge-mcp-server)
  • Bug fixes and OPC path-convention edge cases from real projects — issues welcome

This connector is feature-complete for its scope: one Ignition project against one L5X export. Development beyond that scope happens in Nexus.


This Connector vs. Nexus

The connector is the access layer. Nexus is the intelligence that sits on top of it — and of every other connector — as one system.

Capability This connector Nexus
Correlate one Ignition project with one L5X export ✅ ✅
Trace a single tag from SCADA to PLC logic ✅ ✅
Commissioning gap detection ✅ ✅
Multi-PLC / whole-plant correlation — ✅
Alarm pipeline → PLC trigger-logic tracing — ✅
Cross-vendor: Siemens, CODESYS family (500+ brands), OPC UA — ✅
Live fault diagnosis on the running line (root-cause, cited) — ✅
Knowledge layer: your manuals, SFS/DOO docs, fault history — searchable, linked to logic — ✅
Persistent memory of the operation across sessions — ✅
Fleet scale: auto-discovery, whole-plant inventory, monitoring, alarming — ✅
Local LLM / air-gapped deployment — ✅

If you're evaluating this connector for more than one PLC, talk to us about Nexus.


Development

git clone https://github.com/Nodeblue-AI/bridge-mcp-server.git
cd bridge-mcp-server
pip install -e .
pip install pytest
pytest tests/ -v

Project Structure

src/bridge_mcp_server/
├── __init__.py       # v0.4.0
├── __main__.py       # CLI entry point (stdio/SSE)
├── server.py         # FastMCP with 4 tools (ping + 3 correlation tools)
└── correlator.py     # OPC path normalizer + correlation engine

tests/
└── test_correlator.py

License

MIT — see LICENSE.


Built by Nodeblue. Early community tooling behind Nexus — the industrial intelligence system that reads your operation and answers, cited to the source.

Metadata

Release files for bridge-mcp-server 0.4.0

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

Source distribution (sdist)

Source distribution for bridge-mcp-server 0.4.0
File Size Uploaded
bridge_mcp_server-0.4.0.tar.gz 11.2 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for bridge-mcp-server 0.4.0
File Interpreter ABI Platform
bridge_mcp_server-0.4.0-py3-none-any.whl Python 3 none any Details

Total release size: 22.1 kB

Release files / bridge_mcp_server-0.4.0.tar.gz

Download URL bridge_mcp_server-0.4.0.tar.gz
Size 11.2 kB
Tags Source
SHA-256 checksum
How to use checksums
a23e960cc349982a3c4bcf7a5a44d0638259df1fdf178de69ee405fd8397d632
BLAKE2b-256 checksum
How to use checksums
240557dc5db350452a33e59293a250d436646c45467789bd61bd35bde7133aee
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.14

Release files / bridge_mcp_server-0.4.0-py3-none-any.whl

Download URL bridge_mcp_server-0.4.0-py3-none-any.whl
Size 10.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
67840c0d74e3f71060cd73405f6c5ffc80ca4ee379567bfcde484d8e3e4f9d8a
BLAKE2b-256 checksum
How to use checksums
6c448633bca6f30fc358444e54d659adf7fe2f7f1f2f2e4da64515b7b8987540
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.14

Release history Release notifications | RSS feed

This release

0.4.0 This release

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