Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

PIO Agent

NPM · PLATFORMIO-MCP

Build, inspect, flash, and monitor PlatformIO firmware projects with policy-controlled tools.

Available components

+6 this week 88 Trust /100

Last scanned (20 hours ago)

Scores higher than 90% of npm servers

Category IoT and Hardware

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 43 of 146 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to jl-codes/platformio-mcp). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 20 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability71
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 7381 tokens (~102/item across 72 items; 72 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management70
  • Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage78
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 33% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 72 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 16 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Oct 26 0
    • Security disclosure: unverified → fail ▼ functional
  • 12 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Oct 26 +3
    • Security disclosure: fail → unverified ▼ functional
  • 3 Oct 26 +9
    • Source repository: unverified → pass ▲ security
    • Stability: unverified → 0.27 ▲ functional
  • 2 Oct 26 −5
    • Provenance: pass → unverified ▼ security
  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 16 Oct 2026 · Analysed npm/platformio-mcp@3.1.0

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo jl-codes/platformio-mcp
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/jl-codes/platformio-mcp/.github/workflows/release.yml@refs/tags/v3.1.0
Rekor log index 2961939495
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:5baf41b91f9cb6bb3b0de16fffa8adf718338361d22695f5688daf4cec2cbbb7df79c453ef0edef1b2628d7dc2173b4a382cf6010f85377f4c2cbae2b

Background: How many MCP packages publish verified provenance →

Dependencies 146 packages
Packages resolved 146
Stale 43
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 72 exposed · ~7,381 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
project_envs ~44

List resolved project environments, inherited board/framework/port settings and configured defaults without running build scripts.

NameTypeReqDescription
approvalIdstring––
projectDirstringyes–

No output schema declared.

No examples provided.

project_metadata ~53

Generate bounded build metadata for selected or all environments. Requires build permission; may execute project scripts or install dependencies.

NameTypeReqDescription
approvalIdstring––
environmentstring––
projectDirstringyes–

No output schema declared.

No examples provided.

query_logs ~114

Scans the latest active background serial trace spool, returning a filtered string block.

NameTypeReqDescription
linesnumber–Fetch this many tail lines from the end of the log (default: 100)
portstring–Specific COM port to query logs for.
projectDirstring–Path to the PlatformIO project directory. Agents SHOULD ALWAYS explicitly provide this to ensure operations execute in the correct workspace, unless explicitly instructed otherwise.
searchPatternstring–Optional Regex pattern to filter the spool for specific keywords.

No output schema declared.

No examples provided.

release_lock ~30

Release the explicit queue lock matching your session ID.

NameTypeReqDescription
sessionIdstringyesYour active Session ID

No output schema declared.

No examples provided.

reset_server_state ~64

Forcefully cleans all server locks and terminates any tracked daemon or compilation PIDs globally or locally.

NameTypeReqDescription
projectDirstring–Path to the PlatformIO project directory. Agents SHOULD ALWAYS explicitly provide this to ensure operations execute in the correct workspace, unless explicitly instructed otherwise.

No output schema declared.

No examples provided.

run_target ~105

Run a named PlatformIO target with effect-based permissions. Serial upload targets coordinate owned monitors and endpoint custody; network/probe destinations require their dedicated workflow.

NameTypeReqDescription
approvalIdstring––
configApprovalIdstring––
environmentstring|null––
projectDirstringyes–
selectionApprovalIdstring––
stopOpenSessionsboolean––
targetstringyes–
uploadPortstring|null––

No output schema declared.

No examples provided.

run_tests ~196

Validates unit tests locally/remote.

NameTypeReqDescription
backgroundboolean–Run testing in background
compileOnlyboolean–Compile tests without uploading or executing them. Enforced by build_only policy.
environmentstring–Specific environment to test
filterstring–Include matching test suites
ignorestring–Exclude matching test suites
projectDirstringyesPath to the PlatformIO project directory. Agents SHOULD ALWAYS explicitly provide this to ensure operations execute in the correct workspace, unless explicitly instructed otherwise.
structuredReportboolean–Include per-case results for foreground runs; cannot be combined with background
uploadPortstring–Explicit test upload port
verboseboolean–Verbose test output
withoutBuildingboolean–Use existing test artifacts; incompatible with compile-only
withoutUploadingboolean–Skip upload; test execution may still access hardware

No output schema declared.

No examples provided.

search_libraries ~59

Searches the PlatformIO library registry for available libraries by name, keywords, or description.

NameTypeReqDescription
limitnumber–Maximum number of results (default: 20)
querystringyesSearch query (library name, keyword, or description)

No output schema declared.

No examples provided.

serial_session_list ~25

List this connection's authorized monitor sessions.

NameTypeReqDescription
approval_idstring––

No output schema declared.

No examples provided.

serial_session_read ~87

Read an owned monitor with cursors and bounded Python-compatible regex matching on completed lines. Maximum wait 120 seconds; response and storage byte limits apply.

NameTypeReqDescription
approval_idstring––
cursorinteger––
max_linesinteger––
session_idstringyes–
timeout_snumber––
wait_forstring|null––

No output schema declared.

No examples provided.

serial_session_start ~118

Start an owned serial monitor using explicit arguments, resolved project settings, or an unambiguous device candidate. Opening requires hardware authorization and exclusive device ownership.

NameTypeReqDescription
approval_idstring––
baudinteger|null––
config_approval_idstring––
discovery_approval_idstring––
envstring|null––
max_linesinteger––
portstring|null––
project_dirstring|null––
selection_approval_idstring––

No output schema declared.

No examples provided.

serial_session_stop ~31

Close an owned monitor session, retaining device ownership until closure is confirmed.

NameTypeReqDescription
session_idstringyes–

No output schema declared.

No examples provided.

serial_session_write ~66

Write UTF-8 text to an owned serial session after payload-bound hardware authorization. Limited to 64 KiB including the optional newline.

NameTypeReqDescription
approval_idstring––
newlineboolean––
session_idstringyes–
textstringyes–

No output schema declared.

No examples provided.

size_report ~107

Report GNU symbols and PlatformIO memory accounting for one environment. Metadata and size checks require build permission and may execute project scripts.

NameTypeReqDescription
approvalIdstring––
environmentstringyesExplicit build environment; metadata collection can execute project scripts.
expectedElfSha256string––
filterstring–Case-insensitive bounded regex applied to symbol names or source paths.
projectDirstringyesExplicit PlatformIO project directory.
topinteger––

No output schema declared.

No examples provided.

start_monitor ~105

Manually start or restart the background serial-to-disk spooler for a specific device.

NameTypeReqDescription
baudRatenumber–Optional baud rate. Defaults to 115200.
environmentstring–Optional PlatformIO environment context.
portstring–Optional COM path. Falls back to default.
projectDirstring–Path to the PlatformIO project directory. Agents SHOULD ALWAYS explicitly provide this to ensure operations execute in the correct workspace, unless explicitly instructed otherwise.

No output schema declared.

No examples provided.

stop_monitor ~69

Kills the active background serial listener and unlocks the UART.

NameTypeReqDescription
portstringyesCOM port to stop listening on.
projectDirstring–Path to the PlatformIO project directory. Agents SHOULD ALWAYS explicitly provide this to ensure operations execute in the correct workspace, unless explicitly instructed otherwise.

No output schema declared.

No examples provided.

system_info ~14

Gets sys diagnostic path output.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

uninstall_library ~78

Removes target library.

NameTypeReqDescription
globalboolean–If true, performs the operation globally. Defaults to false.
librarystringyesLibrary name or ID to uninstall
projectDirstring–Path to the PlatformIO project directory. Agents SHOULD ALWAYS explicitly provide this to ensure operations execute in the correct workspace, unless explicitly instructed otherwise.

No output schema declared.

No examples provided.

update_library ~79

Upgrades library versions.

NameTypeReqDescription
globalboolean–If true, performs the operation globally. Defaults to false.
librarystringyesLibrary name or ID to update
projectDirstring–Path to the PlatformIO project directory. Agents SHOULD ALWAYS explicitly provide this to ensure operations execute in the correct workspace, unless explicitly instructed otherwise.

No output schema declared.

No examples provided.

upload_filesystem ~293

Builds and uploads a SPIFFS/LittleFS filesystem image to the connected device. PREFERRED over `pio run --target uploadfs` in a shell — same hardware-lock and port-auto-detect benefits as `upload_firmware`. Supports `start_monitor=true` to re-attach serial after upload.

NameTypeReqDescription
automationKeystring–Stable scheduled-run key. Supplying this activates unattended automation policy.
backgroundboolean–If true, dispatches the compilation to the background and returns immediately to prevent MCP timeouts. You must poll status subsequently.
environmentstring–Optional specific environment from platformio.ini
maxRunDurationSecondsinteger–Required finite execution budget for an unattended write.
portstring–Optional upload port (auto-detected if not specified)
projectDirstringyesPath to the PlatformIO project directory. Agents SHOULD ALWAYS explicitly provide this to ensure operations execute in the correct workspace, unless explicitly instructed otherwise.
sessionIdstring–Agent session ID for pipeline lock validation
start_monitorboolean–If true, automatically starts the background serial monitor after a successful upload, handling OS-level port re-enumeration.
targetBindingobject–Short-lived exact target binding returned by agent_resolve_target.
verboseboolean–If true, returns the complete verbose upload log in the result instead of truncating it

No output schema declared.

No examples provided.

upload_firmware ~311

Uploads compiled firmware to a connected device. PREFERRED over `pio run --target upload` in a shell — this tool routes through the hardware lock to serialize port access, auto-detects the port, and (with `start_monitor=true`) re-attaches the serial monitor after the device re-enumerates. Automatically rebuilds via `build_project` semantics if the cache is cold.

NameTypeReqDescription
automationKeystring–Stable scheduled-run key. Supplying this activates unattended automation policy.
backgroundboolean–If true, dispatches the compilation to the background and returns immediately to prevent MCP timeouts. You must poll status subsequently.
environmentstring–Optional specific environment from platformio.ini
maxRunDurationSecondsinteger–Required finite execution budget for an unattended write.
portstring–Optional upload port (auto-detected if not specified)
projectDirstringyesPath to the PlatformIO project directory. Agents SHOULD ALWAYS explicitly provide this to ensure operations execute in the correct workspace, unless explicitly instructed otherwise.
sessionIdstring–Agent session ID for pipeline lock validation
start_monitorboolean–If true, automatically starts the background serial monitor after a successful upload, handling OS-level port re-enumeration.
targetBindingobject–Short-lived exact target binding returned by agent_resolve_target.
verboseboolean–If true, returns the complete verbose upload log in the result instead of truncating it

No output schema declared.

No examples provided.

upload_ota ~215

Upload ESP32/ESP8266 firmware or filesystem images over ArduinoOTA using a fixed network target, immutable image and private credentials. Build and uploader permissions are separate; transfer success does not verify runtime health.

NameTypeReqDescription
approval_idstring––
authstring|null––
buildboolean––
build_approval_idstring––
command_approval_idstring––
config_approval_idstring––
elf_pathstring––
envstring|null––
expected_image_sha256string––
filesystemboolean––
hoststringyes–
image_approval_idstring––
image_pathstring––
portinteger|null––
project_dirstring|null––
resolve_approval_idstring––
system_approval_idstring––
timeout_snumber––
verify_reachableboolean––

No output schema declared.

No examples provided.

Install

How do I install the PIO Agent MCP server?

PIO Agent runs locally as an npm package, launched with npx -y platformio-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · platformio-mcp

# add to Claude Code
claude mcp add jl-codes-platformio-mcp -- npx -y platformio-mcp
Common questions

What is the PIO Agent MCP server?

PIO Agent is an MCP server listed in the public MCP registry as io.github.jl-codes/platformio-mcp. Build, inspect, flash, and monitor PlatformIO firmware projects with policy-controlled tools. This page covers its npm package (platformio-mcp).

Is the PIO Agent MCP server safe to use?

PIO Agent scores 88 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 16 October 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the PIO Agent MCP server expose?

PIO Agent exposes 72 tools: deps_check, project_envs, project_metadata, coredump, partition_table, and 67 more. Their descriptions and schemas cost roughly 7,381 tokens of context every time the server is loaded.

Is the PIO Agent MCP server still maintained?

PIO Agent is still listed as active in the MCP registry. We last reached this channel on 16 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the PIO Agent MCP server under?

PIO Agent declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.