Local-first knowledge graph for token-efficient code review through MCP and CLI
Nothing to run from here
ESP-IDF is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
94/100
trust score
11
downloads a day
local
runs on your machine
108
downloads in 30d
What it does
Build, flash, monitor, and test ESP-IDF projects on real hardware.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user esp-idf-mcp '--' uvx esp-idf-mcp
# 2 — ask your agent for something these tools do
# build_project, flash_project, read_chip_info and 11 more
ESP-IDF costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
MAAll 1 server
Maty4031 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts ESP-IDF as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user esp-idf-mcp '--' uvx esp-idf-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
14 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Build ESP-IDF project via idf.py (same as manual idf.py build). Full output always lands in project_dir/.esp_build.log (rewritten every run).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_dir | string | yes | Absolute path to the ESP-IDF project directory |
| timeout | integer | no | Max seconds for the whole build (default 600). On timeout the process tree is killed and a failure returned. |
Flash the built project with esptool, then open a monitor session on the port (default). Full output always lands in project_dir/.esp_flash.log (rewritten every run).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_dir | string | yes | Absolute path to the ESP-IDF project directory |
| port | string | no | Serial port (e.g. COM13); auto-detected when omitted (only if exactly one non-COM1 port). Monitor sessions on this port are closed before flashing. |
| monitor | boolean | no | Open a monitor session after flashing (default True) |
| wait_after_flash | number | no | Seconds to let the hard-reset boot finish before opening the monitor (default 2.0) |
| timeout | integer | no | Max seconds for the whole flash (default 600). On timeout the process tree is killed and a failure returned. |
Read hardware info from a connected ESP32 board via esptool: chip model, revision, features, crystal freq, MAC address, flash vendor/device/size. The board is briefly put into download mode and hard-reset back to the running app afterwards. Note: PSRAM info is NOT available here (check the boot…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| port | string | no | Serial port (e.g. COM13). Empty = auto-detect (first port, excluding COM1). |
| baud | integer | no | Baud rate for the esptool connection (default 115200). |
Set the ESP-IDF target using idf.py set-target.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_dir | string | yes | Absolute path to the ESP-IDF project directory |
| target | string | yes | Target chip (e.g. esp32, esp32s3, esp32c2, esp32s31) |
Add component dependency to the project's idf_component.yml. The component is downloaded on the next build.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_dir | string | yes | Absolute path to the ESP-IDF project directory |
| dependency | string | yes | Component dependency string (e.g. 'espressif/button^2.5.0', 'elrebo-de/deep_sleep^1.2.1') |
| component | string | no | Name of the component in the project whose manifest gets the dependency (default 'main'). |
| path | string | no | Path to the component directory whose manifest gets the dependency. Takes precedence over component if set (official --path option). |
Remove a dependency (e.g. 'espressif/button') from all manifest files in the project. Component files are pruned on the next build.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_dir | string | yes | Absolute path to the ESP-IDF project directory |
| dependency | string | yes | Component dependency name (e.g. 'espressif/button', 'button') |
List official ESP-IDF examples bundled with the installed IDF (browse before create_project).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | Optional category (e.g. 'get-started', 'wifi', 'peripherals'). Empty = list categories only. |
Create a new ESP-IDF project directory, optionally from an official example bundled with the installed IDF (browse with list_examples).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Absolute path for the new project directory (must not exist or be empty) |
| example | string | no | Optional official example relative to the IDF examples root (e.g. 'get-started/hello_world'). Empty = minimal template project. To pull registry components into the new project, call add_dependency af |
Clean build artifacts using idf.py.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_dir | string | yes | Absolute path to the ESP-IDF project directory |
| full | boolean | no | If True, remove entire build directory (fullclean). If False, incremental clean. |
Open a persistent serial monitor session. Returns immediately (non-blocking).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| port | string | yes | Serial port (e.g. COM14) |
| reset | boolean | no | Hard-reset the board after opening, so the session captures a fresh boot (default True) |
| project_dir | string | no | Project dir for baud auto-detect (sdkconfig); the session full log goes to its .esp_monitor_full.log (rewritten fresh on every session open; standalone opens without a project dir keep no full-log fil |
| idle_release | number | no | Seconds without monitor_read/monitor_send before the session auto-releases the port (default 120). Reopen if a call reports "No session". |
| baud | integer | no | Explicit baud rate (e.g. 74880) - used as-is, the sdkconfig auto-detection is skipped. 0 (default) = auto-detect from the project sdkconfig (fallback 115200). |
Read new serial output of an open session since the last read.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | Session id from monitor_open (e.g. 'COM14@74880') |
| full | boolean | no | Dump everything retained verbatim, cursor-independent (default False = incremental) |
| timestamp | boolean | no | Keep the leading I (12345) ms prefix (default False: stripped) |
| max_lines | integer | no | Cap on returned lines (0 = no cap, the default) |
| match | string | no | Regex filter ('|' separates alternatives, e.g. 'wifi|error') |
Send text to the device's serial input (e.g. shell commands, menu selections).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | Session id from monitor_open |
| data | string | yes | Text to write to the port |
| press_enter | boolean | no | Append CRLF after the data (default True) |
Close a monitor session and release its serial port. Only the given session / port is released — there is no release-all mode.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | Session id from monitor_open (e.g. 'COM14@74880'), or a bare port ('COM14') to close all sessions on that port. |
Run pytest-embedded hardware tests (flash + interact with the real board, assert on serial output).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_dir | string | yes | Absolute path to the ESP-IDF project directory |
| test_path | string | no | Path (relative to project_dir) to the tests dir or a single test file (default 'pytest') |
| target | string | no | Chip target passed as --target (e.g. esp32c2). Empty = use pytest-embedded defaults. |
| port | string | no | Serial port for the device (e.g. COM14). Empty = auto-detect (works when exactly one device is connected). |
| timeout | integer | no | Max seconds for the whole test run (default 300) |
| extra_args | string | no | Extra pytest CLI args, space-separated (e.g. '-k test_wifi --count=1 -vv') |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install ESP-IDF or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 94 / 100
Release 1.1.0 · scanned 28 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score94
Findings1 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest24439392180b292b496acd680daed5b339c3f06277e32f792c924673f5da8c2a
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (14 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| build_project | no tags | |
| flash_project | no tags | |
| read_chip_info | untrusted-input | untrusted-input: keyword "download" |
| set_target | no tags | |
| add_dependency | no tags | |
| remove_dependency | no tags | |
| list_examples | no tags | |
| create_project | no tags | |
| clean_project | no tags | |
| monitor_open | no tags | |
| monitor_read | sensitive-source | sensitive-source: keyword "dump" |
| monitor_send | no tags | |
| monitor_close | no tags | |
| run_pytest | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest24439392180b292b
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.1.0. Pin a release below and the command asks for exactly that one.
1.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish ESP-IDF can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.