{
  "markdown": "# PLCs.ai MCP Server\n\nConnect Claude, Cursor, Codex, or any MCP-compatible agent to your PLC projects.\n\n[PLCs.ai](https://www.plcs.ai) is the AI platform purpose-built for PLC engineers: upload an Allen-Bradley (Studio 5000), Siemens (TIA Portal) or CODESYS V3 project and understand, troubleshoot, document, and safely generate code for it in plain English. This MCP server gives any AI agent governed access to that same capability — your projects, live tag values, and analyses — with per-tool permission scopes.\n\n**Remote server:** `https://mcp.plcs.ai/mcp` (Streamable HTTP · OAuth or API key)\n**Full documentation:** https://www.plcs.ai/developer/mcp\n\n## Quick start\n\n### Claude Code\n\n```bash\nclaude mcp add --transport http plcs-ai https://mcp.plcs.ai/mcp\n```\n\nThen run `/mcp` and choose **Authenticate** to sign in with your PLCs.ai account. (Or pass an API key: `--header \"Authorization: Bearer plck_live_…\"`.)\n\n### Claude Desktop\n\nSettings → Connectors → Add custom connector → URL `https://mcp.plcs.ai/mcp` → Connect and sign in. For API-key or on-prem setups, use the [`mcp-remote`](https://www.npmjs.com/package/mcp-remote) bridge:\n\n```json\n{\n  \"mcpServers\": {\n    \"plcs-ai\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"mcp-remote\", \"https://mcp.plcs.ai/mcp\",\n               \"--header\", \"Authorization: Bearer plck_live_…\"]\n    }\n  }\n}\n```\n\n### Cursor / Codex / other MCP clients\n\nSee per-client guides: https://www.plcs.ai/developer/mcp — covers Cursor, Codex, and any client that speaks remote MCP or can run `mcp-remote`.\n\n## What the agent can do\n\n17 tools, permission-scoped per API key or OAuth grant:\n\n| Area | Tools |\n|---|---|\n| Discover | `plcs_health`, `plcs_list_projects`, `plcs_get_project`, `plcs_get_project_source` |\n| Ask | `plcs_ask_project` — a cited answer from the PLCs.ai assistant, not raw source to reason over |\n| Live plant data | `plcs_get_live_values`, `plcs_get_tag_history`, `plcs_request_live_tags` |\n| Analyze | `plcs_get_project_analysis` (dead code, race conditions, missing handshakes, interlock audits, cycle-time bottlenecks, signal tracing) |\n| Propose | `plcs_propose_code` — a plan you approve, then a **reviewable proposal**; nothing is saved without review |\n| Version & export | `plcs_save_version`, `plcs_stage_upload`, `plcs_export_plc`, `plcs_export_pdf`, `plcs_get_export`, `plcs_download_export` |\n| Embed | `plcs_mint_embed_token` — short-lived, read-only, project-scoped iframe tokens |\n\nThe agent reasons over projects your organization **already owns**. Onboarding a\nmachine is a deliberate act in the app or through a version-source connector, so\nthere is no create-a-project tool — an agent can read, ask, propose and save\nversions, but never add a project.\n\n## Example prompts\n\n- \"List my PLC projects and check which ones have live data connected.\"\n- \"Why won't Conveyor 3 restart after a stop? Trace the interlocks.\"\n- \"Read the latest analysis on the Palletizer project and summarize what's safe to remove.\"\n- \"What did tag `Motor1_Enable` do in the last hour?\"\n- \"Draft a fix for the missing handshake between Conv001 and Rob010 — proposal only.\"\n\n## Safety model\n\n- Every tool call is authenticated and scoped to your organization; the credential *is* the tenant.\n- Proposing code is two steps — a plan you approve, then the change — and it returns a proposal either way; persisting a new version is a separate, separately-scoped action.\n- Customer data is never used to train AI models. [Data handling →](https://www.plcs.ai/data)\n\n## Requirements\n\n- A PLCs.ai account ([start a free trial](https://www.plcs.ai)) or API key\n- For the `mcp-remote` bridge: Node 18+\n\n---\n\n© PLCs.ai · [Terms](https://www.plcs.ai/terms) · [Privacy](https://www.plcs.ai/privacy) · Questions: sales@plcs.ai\n",
  "bytes": 3764,
  "sha": "07bbec623babe0d2574ef16eae441e2eb5b5a9ee800f693450c3afeaf3360321",
  "repo_slug": "plcsai/plcs-ai-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_plcs_plcs_ai_9d8cedeb/readme"
}