Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add bulaofen0036-coder/TIA_Portal_Openness_MCP --skill skillgit clone --depth 1 https://github.com/bulaofen0036-coder/TIA_Portal_Openness_MCPWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bulaofen0036-coder/tia_portal_openness_mcp/skill)<a href="https://agentmods.dev/skills/bulaofen0036-coder/tia_portal_openness_mcp/skill"><img src="https://agentmods.dev/badge/skills/bulaofen0036-coder/tia_portal_openness_mcp/skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bulaofen0036-coder/tia_portal_openness_mcp/skill"><img src="https://agentmods.dev/badge/skills/bulaofen0036-coder/tia_portal_openness_mcp/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 152 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00103 | $0.17726 |
| Opus 5 | $0.00051 | $0.08863 |
| Sonnet 5 | $0.00021 | $0.03545 |
| Haiku 4.5 | $0.00010 | $0.01773 |
Grade A, and why
tiaportal-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 1,142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TIA Portal MCP — Single Skill
This is the operating skill for TIA Portal MCP automation. The
companion plugin lives at tools/tiaportal-mcp/. It exposes on the order of
~201 MCP tools (lite profile ~43; exact runtime set: call tools/list on the running server) covering
project, hardware, PLC, HMI, and online operations.
0. Always start here
1. Call Bootstrap ← returns env, project state, next step
2. Follow RecommendedNextTool ← e.g. Connect, AttachToOpenProject
3. Call GetProjectTree ← resolve real paths (PLC_1, HMI_RT_1)
4. Read-before-write loop ← inspect, smallest change, compile, save
交付包内最短路径（仅读包内文件时）
根目录 README.md（三步上手）→ scripts/Validate-Bundle.ps1（脱机校验）→ 用 cursor-mcp.example.json 把 command 指到包内 TiaMcpServer.exe → 执行顺序见 docs/full-project-generation-runbook.md 与 templates/project-blueprints/full_plc_hmi_project.json。
Never guess paths. Never invent SCL/LAD XML. If a tool exists for the task, use
it; otherwise inspect with DescribeObject/DescribeService first, then call
InvokeObject/InvokeService.
0.1 弱模型 / 新手：你一辈子只需要这 15 个工具（其余的先忽略）
This server exposes ~190 tools. You do NOT need most of them. A small or non-expert model should pick only from this whitelist and ignore everything else unless one of these tools' output explicitly tells you to call another:
| 想做的事 | 用这个，别的别碰 |
|---|---|
| 开局/看环境 | Bootstrap → 然后照它返回的 recommendedNextTool 做 |
| 连接 TIA | Connect（新工程）或 AttachToOpenProject（已打开的工程） |
| 看工程里有什么 | GetProjectTree（拿真实 softwarePath，如 PLC_1），细看用 GetSoftwareTree / GetBlocks |
| 做一个完整项目 | ScaffoldProject（一次调用搞定 PLC+HMI，见 §0.5） |
| 加一段 PLC 逻辑/变量/DB/UDT | PlcBuildAndImport（先 dryRun=true，见 §6.2/§10） |
| 复杂 SCL（带 FOR/CASE/表达式） | ImportPlcExternalSource → GenerateBlocksFromExternalSource（§14） |
| 编译验证 | CompileAndDiagnosePlc（必须 errorCount=0） |
| 存盘/收尾 | SaveProject → Disconnect |
| 环境报错/装不上 | Doctor — 一次性体检(TIA装没装/Openness组/连接状态)，每项给出修复办法；fix=true(默认)会自动把你加进 Openness 组(可能弹 UAC) |
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- lad-cookbook/MCPVerify_FB_LAD_v3.s7dcl 1.9 KB
- lad-cookbook/MCPVerify_FB_LAD_v3.s7res 431 B
- lad-cookbook/MCPVerify_FB_LAD_v3.xml 11 KB
- lad-cookbook/MCPVerify_FC_LAD_v2.xml 22 KB
- lad-cookbook/MCPVerify_FC_LAD_v3.xml 4.2 KB
- lad-cookbook/MCPVerify_FC_LAD.s7dcl 2.7 KB
- lad-cookbook/MCPVerify_FC_LAD.s7res 800 B
- lad-cookbook/MCPVerify_FC_LAD.xml 21 KB
- lad-cookbook/MCPVerify_Mixed_LADSCL.s7dcl 1.7 KB
- lad-cookbook/MCPVerify_Mixed_LADSCL.s7res 72 B
- scl-cookbook/MCPVerify_FC_SCL_v2.scl 680 B
- scl-cookbook/MCPVerify_FC_SCL_v3.scl 598 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 1,142 lines · 103 tokens per session scan A 37939ce7d752
tiaportal-mcp is a skill published in the GitHub repository bulaofen0036-coder/TIA_Portal_Openness_MCP (229 stars, last pushed 7d ago), licensed MIT. It adds 103 tokens to every session and 17,726 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gx3-existing-project-audit
Analyze an existing Mitsubishi GX Works3 .gx3 project with gx3-cli when the user asks what a ladder does, why a device turns on, or whether a project has risks.
tia.init
Initialize or update the current project's AGENTS.md with the TIA harness operating guide. USE WHEN the user asks to "init / bootstrap / set up the TIA harness", "add the harness guidance to AGENTS.md", or "update the TIA harness section / refresh the harness guide in this project". Idempotent: injects the guide…
cpu.select
Recommend a Siemens S7-1500/S7-1200 CPU family + variant + order number (MLFB) from an engineering need (I/O count, scan/performance, memory, communication ports, safety, redundancy, motion). USE when the user asks "which CPU / PLC should I use", gives selection criteria instead of a model, or needs a typeIdentifier…
spec.validate
Validate a TIA project-spec against the JSON Schema AND the deterministic cross-field engineering rules (same-subnet, unique names, OrderNumber: /V format, module limits, language-by-family, and the G5 safety rule). USE when the user provides or edits a project-spec, asks to "validate / check / lint my spec", or…
tia.handoff
Prepare a human-approval envelope for a GATED operation — download / CPU-STOP (G3), go-online (G4), network scan (G7), master-secret/UMAC (G6), safety/F (G5). USE WHEN the user wants to "download / deploy / go online / commission", or after tia.verify is clean and the next step touches the physical controller, the…
tia.review
Audit an EXISTING / open TIA project against the engineering baseline (optimized block access, 100% symbolic addressing, FB + instance-DB, everything typed via UDT, correct language per task, versioned library TYPEs, uniform PLCopen naming) and the verification-ladder posture. USE when the user asks to "review / audit…