TopicForge

The safety-first read-only MCP for ROS2 robotics: graph introspection, bag analysis, and multi-vendor OMG DDS-RTPS observability. TopicForge lets AI agents inspect your ROS2 graph, recorded bag files, and the raw DDS layer beneath ROS, without ever publishing back to the bus. Eleven typed read-only tools (5 ROS2 graph + 3 DDS + 3 observability/bag) share a single Pydantic envelope so an LLM caller reads one schema across the whole stack. It joins a domain through one OSS Python participant (Eclipse CycloneDDS or eProsima Fast DDS) and reads the builtin discovery topics the OMG protocol standardizes, so it observes every conformant vendor on the wire (RTI Connext, OpenDDS, CoreDX, Dust DDS in Rust) with no proprietary binding. See docs/dds-interop-matrix.md for the canonical multi-vendor positioning and the OMG May 2025 interop reference.

TopicForge is a production-minded MCP (Model Context Protocol) server that lets AI agents (such as Claude) inspect ROS2 topics, analyze ROS bag files, and (since v0.2.0) observe the raw DDS layer through a clean, structured tool interface. It is read-only by architecture, not by configuration: there is no write path to misconfigure, no permission system to audit, no liability conversation to have. The MCP client can see the robot stack; it cannot touch it.

This stance matters because the ROS-MCP space is no longer empty: general-purpose ROS-MCP servers exist that let an LLM publish topics, call services, and command robots. That shape is fine for demos; it is untenable for production fleets, defense systems, automotive AUTOSAR Adaptive surfaces, or anything safety-certified. TopicForge is the read-only alternative for those audiences, plus the robotics developers, ML/CV engineers, and teams that want their AI tooling to understand their robotics stack without commanding it.

Why it exists

LLM agents are good at reasoning over text, but ROS2 introspection lives in a CLI + DDS world they cannot directly reach. Without grounding, an LLM will hallucinate topic names, message types, and bag contents. TopicForge bridges that gap with a small, well-typed set of MCP tools, all read-only, all returning frozen Pydantic schemas that a downstream agent can parse without ambiguity:

Outputs are structured, JSON-serializable, and stable across runtime modes - they look the same whether the server is talking to a real robot or to its built-in mock fixtures. Every response carries a mode_effective field ("live" or "mock") so a downstream LLM can tell a real graph from the demo fixtures without re-reading health_check.

30-second demo without ROS2

The mock adapter ships deterministic fixtures for a small differential robot (LIDAR + RGB camera). You do not need ROS2 installed to try the full tool surface - a clean Python 3.11 venv is enough.

pip install topicforge
TOPICFORGE_MODE=mock python -m topicforge
# Windows PowerShell: $env:TOPICFORGE_MODE="mock"; python -m topicforge

Point any MCP client (Claude Desktop, see below) at this server and ask it to list the topics or analyze /tmp/demo.mcap - every tool returns realistic, typed payloads.

Quickstart

pip install topicforge
python -m topicforge --help
TOPICFORGE_MODE=mock python -m topicforge

Architecture

+----------------------+
|   MCP client (LLM)   |
+----------+-----------+
           |  (stdio, MCP protocol)
           v
+----------+-----------+
|  topicforge.server   |   FastMCP entrypoint, lifecycle, tool registration
+----------+-----------+
           |
           v
+----------+-----------+
|  topicforge.tools    |   Thin handlers - validate, delegate, serialize
+----------+-----------+
           |
           v
+----------+-----------+
| topicforge.services  |   Inspector / Health - orchestration & validation
+----------+-----------+
           |
           v
+----------+-----------+
| topicforge.adapters  |   ros2_live  - subprocess wrappers over `ros2` CLI
|                      |   ros2_mock  - deterministic fixtures
+----------------------+

Layers are strictly separated:

• server/ wires the whole graph and exposes build_app(settings).
• tools/ registers MCP tools on FastMCP. Handlers never call ROS directly.
• services/ validate inputs and orchestrate calls.
• adapters/ are the only code that knows how to talk to a specific backend. New backends (e.g. an rclpy-based adapter) plug in by implementing the RosAdapter protocol.
• models/ holds Pydantic schemas - the contract with MCP clients.
• config/ resolves runtime settings from the environment.

Runtime modes

Mode is selected via the TOPICFORGE_MODE environment variable.

Install from source

Requires Python 3.11+.

git clone https://github.com/yaniswav/TopicForge.git
cd TopicForge
python -m venv .venv
source .venv/bin/activate          # Linux / macOS
# .venv\Scripts\Activate.ps1       # Windows PowerShell
pip install -e ".[dev]"

Or, if you have make:

make dev

Run

Mock mode (no ROS2 required)

TOPICFORGE_MODE=mock python -m topicforge

Or:

make run-mock

Live mode (requires ROS2)

Source your ROS2 distribution first, then:

source /opt/ros/humble/setup.bash
TOPICFORGE_MODE=live python -m topicforge

TopicForge invokes the ros2 CLI under the hood, so it does not require rclpy to be importable. This keeps the live adapter portable across ROS2 distros.

Multi-vendor DDS support (v0.3.0+)

Beyond ROS2 graph introspection, TopicForge observes the raw DDS bus directly via one of two OSS Python adapters (Eclipse CycloneDDS or eProsima Fast DDS) each joining as a read-only DDS-RTPS participant. By the OMG-DDS-RTPS protocol guarantee, both adapters see every conformant participant on the domain (RTI Connext, OpenDDS, CoreDX, Dust DDS in Rust, InterCOM, etc.) regardless of host language. See docs/dds-interop-matrix.md for the canonical multi-vendor positioning and the OMG May 2025 interop reference.

Useful for non-ROS DDS stacks (defense, aerospace, automotive AUTOSAR Adaptive, industrial integration) and for diagnosing why a ROS2 subscriber isn't receiving when the graph says it should. Same safety-first contract : read-only by architecture. The MiddlewareAdapter protocol does not expose a write method on any backend.

Install one or both OSS backends. The v0.4.0 auto-detect framework picks whichever you actually installed:

# Single vendor: install only what you need
pip install topicforge[dds-cyclone]   # Eclipse CycloneDDS only
pip install topicforge[dds-fast]      # eProsima Fast DDS only
pip install topicforge[dds]           # both OSS backends (union)

Then select a backend (or let auto-detect pick):

TOPICFORGE_MODE=live TOPICFORGE_DDS_BACKEND=cyclone python -m topicforge
# or:
TOPICFORGE_MODE=live TOPICFORGE_DDS_BACKEND=fast python -m topicforge
# or, auto-select across the 8-vendor priority chain:
#   RTI > OpenSplice > CoreDX > InterCOM (Pro tier, if installed)
#   > OpenDDS > Fast > Cyclone > Dust > Mock (OSS fallback)
TOPICFORGE_MODE=live TOPICFORGE_DDS_BACKEND=auto python -m topicforge

What the OSS install covers. Cyclone and Fast DDS are the two working backends; OpenDDS and Dust are stubs whose upstream Python bindings do not exist yet, and their install extras fail today. That is not a limitation on what you can observe: because discovery runs over the OMG-standardized wire protocol, a Cyclone participant already sees RTI Connext, OpenDDS, CoreDX and Fast endpoints on the same domain. You do not need a commercial adapter to observe a commercial bus.

A native RTI Connext adapter exists for the cases where the standard route is not enough (secure domains needing vendor credentials, shared-memory-only deployments, vendor-specific extensions). It requires the RTI Python binding and an RTI license you already hold. See docs/pro.md for commercial support and integration.