platformio-mcp
Documentation
PlatformIO MCP
PlatformIO MCP is the open-source, agent-first hardware execution layer for embedded development.
It exposes PlatformIO workflows for board discovery, project setup, build, flash, monitor, diagnostics, and task orchestration through:
- an MCP server adapter
- a first-class CLI adapter (`platformio-mcp` / `pio-agent`)
- an optional local dashboard for visibility and control
MCP is one adapter. PlatformIO is the first backend.
Agent-First Capabilities
- Project readiness validation (`agent_validate_project`)
- Rich build diagnostics with structured error taxonomy (`agent_build_diagnose`)
- Board-aware GPIO safety audits (`agent_safe_pin_audit`)
- Flash + monitor + runtime assertions (`agent_flash_monitor_verify`)
- Persistent workflow artifacts in `.pio-mcp-workspace/` (`lastAgentReport.json`, `boardReport.json`)
- Board intelligence reports (`agent_generate_board_report`)
- Policy profile introspection (`get_policy_status`)
All risky operations still honor policy and approval rules.
Quick Start
1. Run the dashboard
npx platformio-mcp dashboard2. Use the CLI
npx platformio-mcp devices
npx platformio-mcp boards --filter esp32
npx platformio-mcp init --board esp32dev --framework arduino --project-dir ./firmware
npx platformio-mcp build --project-dir ./firmware
npx platformio-mcp flash --project-dir ./firmware --port auto
npx platformio-mcp monitor --project-dir ./firmware --port auto --expect BOOT_OK --timeout 30
npx platformio-mcp agent-validate --project-dir ./firmware
npx platformio-mcp agent-build-diagnose --project-dir ./firmware
npx platformio-mcp agent-safe-pin-audit --project-dir ./firmware --board esp32dev
npx platformio-mcp agent-flash-monitor-verify --project-dir ./firmware --expect-all BOOT_OK --reject-patterns "Guru Meditation,Brownout detector,WDT reset" --timeout 45
npx platformio-mcp agent-last-report --project-dir ./firmware
npx platformio-mcp policy-status --project-dir ./firmware
npx platformio-mcp task-statusUse `--json` for machine-readable output:
npx platformio-mcp build --project-dir ./firmware --json3. Install into AI hosts
npx platformio-mcp install --cline
npx platformio-mcp install --claude
npx platformio-mcp install --vscode
npx platformio-mcp install --antigravity
npx platformio-mcp install --codexManual MCP Config
{
"mcpServers": {
"platformio": {
"command": "npx",
"args": ["-y", "platformio-mcp", "--open-dashboard-on-start"]
}
}
}On Windows, use `npx.cmd` if your host requires explicit shim resolution.
Core Capabilities
- Board and device discovery for PlatformIO-supported hardware
- Project initialization and config inspection
- Build, upload, monitor, and background task polling
- Structured diagnostics for build/upload/serial failures
- Safety and policy guardrails (approval gates, audit logs, redaction)
- Dashboard visibility for commands, logs, locks, and safety state
Safety Model
PlatformIO MCP enforces policy decisions across CLI and MCP flows.
- Actions can be `allow`, `deny`, or `requires_approval`
- Risky operations (for example firmware upload/reset paths) require explicit approval
- All actions can be audited
- Secrets are redacted in exposed log streams
Policy profiles can be selected per-project via `.pio-mcp-policy.json`:
{
"profile": "flash_requires_approval"
}Supported profiles:
- `read_only`
- `build_only`
- `flash_requires_approval`
- `lab_admin`
CLI approval workflows:
npx platformio-mcp approvals --status pending --json
npx platformio-mcp approve --json
npx platformio-mcp deny --jsonCodex Usage
Codex-facing docs and prompt cookbook:
Documentation
Getting started:
Guides and references:
- Agent Customization Guide
- MCP Server Command Reference
- Troubleshooting Guide
- Agent-First Embedded Workflow
- Competitive Positioning
- MCP-U Integration Template
- Agent Skills Directory
Specifications:
Development
Prerequisites:
- Node.js >= 18
- PlatformIO Core CLI (install guide)
Local setup:
git clone https://github.com/jl-codes/platformio-mcp.git
cd platformio-mcp
npm install
npm run build
npm run test
npm run smoke-testCI/CD test tiers:
- `npm run test:ci:unit` runs unit/component coverage used in cross-platform CI.
- `npm run test:e2e:ci` runs CI-safe end-to-end tests for agent workflows and CLI wiring.
- `.github/workflows/ci.yml` runs typecheck, tests, and package smoke checks on pull requests/pushes.
- `.github/workflows/hardware-e2e.yml` is a manual self-hosted runner workflow for real hardware MCP E2E (`RUN_MCP_E2E=1`).
Contributing
Contributions are welcome.
- Open an issue for bugs or feature requests
- Submit a pull request with tests when applicable
License
MIT. See LICENSE.
Frequently asked questions
What is platformio-mcp?
platformio-mcp is a Model Context Protocol (MCP) server listed in the TrackMCP directory.
How do I install platformio-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is platformio-mcp open source?
Yes — it is hosted on GitHub at https://github.com/jl-codes/platformio-mcp and has 50 stars.
Related MCP tools
Model Context Protocol Servers
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
MCP server to provide Figma layout information to AI coding agents like Cursor
Open-source backend-as-a-service. Postgres, auth, storage, functions, AI gateway, MCP.
Your memories are in ChatGPT... But nowhere else. Universal Memory MCP makes your memories available to every single LLM. No logins or paywall. One command to set it up.
MCP Server for kubernetes management commands
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP