tcgen-st-test-mcp
Provides offline semantic validation for TcGen Structured Text (ST) review bundles by normalizing ST code, generating STruC++ tests from JSON specs, and executing them via the strucpp CLI.
README
tcgen-st-test-mcp
Offline semantic validation for TcGen Structured Text review bundles.
This MCP server accepts inline TcGen review-ST sources, normalizes the supported
subset into STruC++-compatible ST, builds either JSON-spec tests or TcGen
framework-style tests, and runs them through the strucpp CLI in a temporary
workspace.
Passing results mean only:
Offline semantic test passed for the normalized STruC++ model. Final TwinCAT compilation or target validation may still be required for vendor libraries, task behavior, I/O, ADS, motion, lifecycle methods, and runtime-specific behavior.
Tools
tcgen_st_backend_checktcgen_st_normalizetcgen_st_test_generatetcgen_st_test_run
CLI
tcgen-st-test backend-check
tcgen-st-test normalize request.json
tcgen-st-test generate request.json
tcgen-st-test run request.json
Test Modes
tcgen_st_test_generate and tcgen_st_test_run accept exactly one test
authority:
testSpec: the original JSON step format, converted into STruC++TESTblocks.frameworkTest: TcGen/TwinCAT-style ST tests where the request sources include the CUT plus concreteFB_Test_* EXTENDS FB_TestCaseBaseblocks.
Framework mode uses:
{
"frameworkTest": {
"mode": "tcgen-test-framework",
"testFunctionBlocks": ["FB_Test_LimitCounter"],
"maxScans": 200
}
}
In framework mode the MCP normalizes the CUT and agent-authored test FBs, omits
uploaded framework infrastructure such as FB_TestRunner, I_TestCase,
FB_TestCaseBase, GVL_TestResults, and PROGRAM MAIN, injects a compact
STruC++-compatible framework shim, then runs generated wrapper TEST blocks
against the concrete FB_Test_* instances. A failing framework assertion is
returned as verdict: "failed" with the STruC++ assertion detail in
tests[].message.
Local Development
Use Node.js 22 or later.
npm ci
npm run build
For local development against a sibling STruC++ checkout:
git clone https://github.com/AgileAutomationTechnologies/STruCpp.git C:\Users\fboid\source\python\STruCpp
cd C:\Users\fboid\source\python\STruCpp
git checkout development
$env:STRUCPP_PATH = "C:\Users\fboid\source\python\STruCpp"
$env:STRUCPP_GPP_PATH = "C:\msys64\ucrt64\bin\g++.exe"
STRUCPP_PATH may point to a strucpp executable, dist/node/cli.js, or the
STruC++ repository root. STRUCPP_GPP_PATH is optional for backend checks, but
tcgen_st_test_run needs a working g++ for STruC++ --test execution.
The v0.1 Windows validation target is the AgileAutomationTechnologies STruC++
development branch at commit 0a398a643fad44905d2b786f4229e152cef531bd,
based on STruC++ 0.5.12 plus AAT Windows/compiler-launch fixes.
Verification
npm run verify
npm run verify:native
npm run fixtures
npm run smoke:mcp
npm pack --dry-run
Native verification expects:
$env:STRUCPP_PATH = "C:\Users\fboid\source\python\STruCpp"
$env:STRUCPP_GPP_PATH = "C:\msys64\ucrt64\bin\g++.exe"
Reference STruC++ checks:
cd C:\Users\fboid\source\python\STruCpp
npm run build
npm run typecheck
node dist\node\cli.js --version
node dist\node\cli.js tests\st-validation\function_blocks\fb_accumulator.st --gpp C:\msys64\ucrt64\bin\g++.exe --test tests\st-validation\function_blocks\test_fb_accumulator.st
node dist\node\cli.js tests\st-validation\function_blocks\basic_fb.st --no-default-libs --gpp C:\msys64\ucrt64\bin\g++.exe --test tests\st-validation\function_blocks\test_basic_fb.st
Workspace Retention
Temporary workspaces are deleted by default. keepWorkspace only returns a
workspace path when both are true:
- the request sets
options.keepWorkspace = true; - the local environment sets
TCGEN_ST_ALLOW_KEEP_WORKSPACE=true.
Without that environment flag, keepWorkspace is ignored and a non-blocking
SANDBOX_KEEP_WORKSPACE_DISABLED diagnostic is returned.
Known STruC++ Limitation
The upstream basic_fb sample declares Toggle, while bundled OSCAT libraries
also define TOGGLE. Run that sample with --no-default-libs; use
fb_accumulator as the default-library native smoke until library shadowing is
handled upstream.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.