Skip to main content
Glama
0mandrock1

mcp-esp32

by 0mandrock1
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

mcp-esp32

An MCP server that puts an ESP32 / MicroPython board behind tools an agent can call: enumerate ports, flash firmware, run code over the raw REPL, move files, capture serial output.

The problem this repository is actually about: flashing a board takes tens of seconds, boards reset unexpectedly, the serial link drops bytes, and an agent needs to be able to cancel a flash it started. None of that fits the request/response shape most MCP servers use. This repo is a demonstration of the parts of MCP built for exactly that -- progress notifications, cancellation, and structured (not thrown-and-forgotten) error handling -- applied to a device that is genuinely slow, stateful, and failure-prone.

Result: eight tools, a from-scratch raw-REPL client, a flashing orchestrator that reports progress at least every 5% and can be cancelled mid-write with no orphaned process, and a from-scratch fault-injecting simulator so all of that is verifiable without a board attached. 37 tests, all green, no hardware required. See Verification status below for exactly what that does and does not prove.

Why a long-running hardware operation is a harder MCP shape than a REST wrapper

A REST wrapper around esptool is POST /flash and a 200 once it's done (or a client-side timeout if it isn't). That throws away everything that actually matters when the thing on the other end of a serial cable takes 30 seconds to flash and can silently vanish partway through:

  • Progress. A flash with no feedback for 30 seconds is indistinguishable from a hang, to both a human and an agent deciding whether to keep waiting. flash_firmware reports progress via MCP's notifications/progress at least every 5%, not just at the end.

  • Cancellation. An agent that started a flash against the wrong port needs to be able to stop it -- not just stop waiting for it, but actually stop the write and not leave a subprocess or a half-open serial port behind. flash_firmware handles notifications/cancelled by signalling the in-flight write to stop, waiting (inside a shielded scope, so the cleanup itself can't be cancelled) for it to actually stop, and only then letting the cancellation propagate.

  • Timeouts vs. failure. A REST call that times out tells you nothing about whether the device is busy, dead, or reset. Every failure mode here is a distinct, structured exception (DeviceResetError, FlashTimeoutError, ReplDesyncError, ...) with a kind field an agent can branch on, not a generic timeout.

  • Recovery. A dropped byte on a REPL exchange shouldn't corrupt the next one. repl_exec detects a desynchronised raw REPL and resynchronises before the next call, instead of returning garbage or hanging.

  • Statefulness under concurrency. A board has one UART. Two tool calls racing against the same port would interleave bytes and corrupt both, so every tool call is serialised per-port (an asyncio.Lock per port name) -- calls against different ports still run fully in parallel.

Related MCP server: esp-mcp

Tools

Tool

Description

list_ports()

Serial ports with VID/PID and a best-guess chip family, plus the simulator.

board_info(port)

Chip, flash size, MAC, MicroPython version if present.

flash_firmware(port, firmware_path, erase=False, confirm_erase=False)

Progress notifications every ≥5%, cancellable. erase=True requires confirm_erase=True as a separate argument.

repl_exec(port, code, timeout_s=10)

Raw-REPL execution; stdout, stderr, and exception come back as separate fields.

fs_ls(port, path)

Directory listing (name, size, is_dir).

fs_get(port, path, max_bytes)

Read a file (base64), capped and refused up front if it exceeds max_bytes.

fs_put(port, path, content_base64, max_bytes)

Write a file, chunked over several raw-REPL exchanges.

tail_serial(port, seconds)

Bounded (≤30s) raw serial capture, no REPL protocol involved.

Architecture

server.py        MCP tool registration; adapts Context.report_progress and
                  cancellation for flash_firmware. Everything else is a
                  direct pass-through to toolkit.py.
toolkit.py        Backend-agnostic async tool implementations. No mcp.Context
                  here -- every reliability property is tested by calling
                  these functions directly.
backends/base.py  Resolves a port string to a BoardHandle: transport
                  factory, flash-session factory, identify(). Ports named
                  "SIM*" route to the simulator; anything else routes to
                  the serial backend.
raw_repl.py       MicroPython raw-REPL client (transport-agnostic).
fsops.py          ls/get/put built on raw_repl.exec(), chunked, size-capped.
flasher.py        Flash orchestration: progress throttling, cancellation,
                  SimulatorFlashSession (talks to the simulator) and
                  SubprocessFlashSession (drives the real esptool CLI).
sim_flash_protocol.py
                  Wire format for the simulator's flash handshake.
backends/simulator.py
                  A pty-backed fake device: real raw-REPL protocol, real
                  code execution against an in-memory filesystem, and a
                  configurable fault injector.
backends/serial_backend.py
                  Real hardware via pyserial + the esptool CLI. Not
                  exercised by anything in this repository -- see below.

The simulator, and exactly what it reproduces

The simulator (backends/simulator.py) is not a mock of the raw-REPL client -- it's a second, independent implementation of the device side of that protocol, running in a background thread on the other end of a real pty. Code sent to it is genuinely executed (via a sandboxed exec, with fake os/machine/sys/ubinascii modules backing an in-memory filesystem), so raw_repl.py cannot tell it apart from a real board at the protocol level.

Its flash handshake is a separate, deliberately simple framed protocol (sim_flash_protocol.py) -- sync, begin, N acknowledged data blocks, end -- not a reimplementation of esptool's real SLIP/ROM-bootloader wire format. Reproducing that byte-for-byte (chip-specific stub loaders, ROM quirks, SLIP escaping) is a separate project from what this repository demonstrates. What matters for exercising the MCP long-running-operation surface is the shape of a flash: a handshake, many acknowledged writes, an end -- with the same opportunities for a reset, a wedged link, or a cancellation. See Design notes for why this was the simpler option.

A FaultConfig on the simulated board injects, on demand:

  • FlashFault.RESET_MID_FLASH -- the device sends an explicit reset marker after N data blocks and then goes silent, standing in for a brown-out or watchdog reset partway through a write. Tested in test_flasher_simulator.py::test_device_reset_mid_flash_is_a_structured_error_not_a_hang.

  • FlashFault.SILENT_TIMEOUT -- the device stops responding with no reset marker at all, standing in for a wedged link. Tested in test_silent_timeout_surfaces_as_flash_timeout_error.

  • ReplFault.GARBAGE -- one raw-REPL response is replaced with bytes that don't match any expected marker, standing in for a dropped/corrupted byte. Tested in test_raw_repl.py::test_garbage_on_the_line_is_detected_and_resynced_transparently.

  • block_delay_s -- adds latency per flash block, used to make cancellation-mid-flash deterministically testable without a real multi- second flash.

Cancellation itself doesn't need fault injection -- it's tested by cancelling a real (simulated) flash in progress and asserting partial progress was reported and, for the subprocess path, that the child process was actually reaped (test_flasher_subprocess.py::test_cancellation_leaves_no_orphan_process).

Per-port locking is tested by timing two concurrent calls against the same simulated port (they serialise) against two calls on different ports (they don't) -- test_toolkit.py::test_concurrent_calls_on_same_port_are_serialised.

Verification status

Everything in this repository was built and tested against the simulator described above. No physical ESP32 or other hardware was available or used at any point. backends/serial_backend.py (real pyserial + the esptool CLI) is written to the same BoardHandle contract the simulator satisfies and its subprocess-lifecycle logic (progress parsing, cancel-and-reap, reset-string detection) is tested against a stand-in script (tests/fixtures/fake_esptool.py) that mimics esptool's stdout shape -- but the module itself has never been run against a real board or even a real copy of esptool. Treat it as "should work", not "verified".

Installation

python -m venv .venv
.venv/bin/pip install -e ".[dev]"        # simulator only
.venv/bin/pip install -e ".[serial]"     # adds pyserial + esptool for real hardware

Running it

mcp-esp32                 # starts the MCP server on stdio
mcp-esp32 --demo          # narrated walkthrough of every tool against the simulator, no MCP client needed

--demo calls toolkit.py directly (the same functions the tests call) and prints each result, including a deliberate reset-mid-flash fault, so the whole tool surface is visible without wiring up an MCP client.

Testing

pytest

37 tests, no hardware, no network access, no secrets. CI (.github/workflows/ci.yml) runs the suite plus --demo on Python 3.11 and 3.12.

Design notes

Decisions made without a way to check them against real hardware; simpler option chosen in each case.

  • Simulated flash protocol instead of real SLIP/ROM-bootloader bytes. Reimplementing esptool's actual wire protocol (chip-specific stub loaders, ROM quirks) would be a second project and wouldn't change what's being demonstrated -- the MCP-level orchestration around a slow, faulty write. The simulator's protocol has the same shape (sync/begin/data×N/end, acknowledged blocks, an explicit reset signal) and is documented as such in sim_flash_protocol.py.

  • fs_get/fs_put transfer content as hex-encoded lines over repeated raw-REPL exec() calls, not a dedicated binary protocol. MicroPython's raw REPL keeps globals alive across exec() calls (it's a persistent interpreter, not a fresh one per call), so fs_put opens a file handle in one call and writes to it in several more -- this works identically against real hardware and the simulator, and needed no new wire protocol.

  • Base64 in the MCP tool signatures, hex on the wire. fs_get/fs_put take/return content_base64 because raw bytes aren't JSON-safe; internally fsops.py uses ubinascii.hexlify/unhexlify since that's what MicroPython actually has available on-device. MAX_TRANSFER_BYTES (512 KiB) is checked before a transfer starts, not discovered partway through.

  • Ports named SIM* always route to the simulator (backends/base.py), auto-created on first use. No environment variable or config flag needed to use the simulator -- call any tool with a port starting with SIM and it exists.

  • Errors are structured return values, not raised exceptions, for every expected failure mode (reset, timeout, desync, confirmation-required). A tool call that hits one of these returns {"error": {"kind": ..., ...}} rather than an MCP tool error, so an agent can branch on kind without parsing a message string. Actual bugs still raise and surface as normal tool errors.

  • Cancellation cleanup runs inside an anyio.CancelScope(shield=True). Without shielding, the first checkpoint after catching the cancellation would immediately re-raise (cancel scopes are level-triggered), which would skip waiting for the flash thread to actually stop before the request is torn down.

  • esptool is shelled out to as a CLI subprocess, not used as a library. Its Python API is not considered stable across versions; the CLI's stdout format ((NN %) progress lines, specific fatal-error strings) is what every existing esptool-wrapping tool already depends on, and it's the surface tests/fixtures/fake_esptool.py can stand in for without needing esptool internals to match.

Requirements

Python 3.11+. mcp for the server itself; pyserial and esptool are optional (only needed for the serial backend against real hardware) and their absence never breaks import -- see tests/test_optional_deps.py.

Available Tools

8 tools
board_infoB

Chip family, flash size, MAC address, and MicroPython version (if any) for port.

ParametersJSON Schema
NameRequiredDescriptionDefault
portYes

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It lists the output fields but does not disclose whether the operation is read-only, what happens on failure, timeout behavior, or any side effects. The description is purely output-oriented without addressing safety or interaction with the device.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence, front-loaded with the key output categories and clearly referencing the parameter. No wasted words or redundant information, making it highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description partially fulfills the need to explain return values by listing the fields. However, it lacks structure/format details, error handling, and edge cases (e.g., what happens if no board is connected). It is adequate for a simple tool but has clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does so by indicating that 'port' is the target device whose info is retrieved, and it clarifies what data will be returned for that port. This adds meaning beyond the minimal 'Port' title in the schema, though it doesn't provide format or example values.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool's purpose as retrieving board information (chip family, flash size, MAC address, MicroPython version) for a specified port. It is distinct from sibling tools like list_ports, flash_firmware, and fs_* operations, though it lacks an explicit verb like 'get' or 'retrieve'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No usage guidance is provided. The description does not mention when to use this tool versus alternatives, nor any prerequisites such as needing a connected device or a valid port. The only implied context is that it operates on a 'port', but this is also the parameter name and schema title, adding no practical guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

flash_firmwareA

Write firmware_path to port.

Reports progress at least every 5% via MCP progress notifications and can be cancelled mid-flash. erase=True wipes the whole flash first and requires confirm_erase=True as a separate explicit argument.

ParametersJSON Schema
NameRequiredDescriptionDefault
portYes
eraseNo
confirm_eraseNo
firmware_pathYes

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, this description carries the full behavioral disclosure burden. It reveals progress reporting at least every 5%, cancellation support, and the erase flow requiring confirm_erase=True. This provides meaningful context beyond the schema, though it doesn't cover all potential side effects or prerequisites.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, with the primary action in the first and additional behavioral details in the second. Every sentence earns its place with no redundant wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no annotations and no output schema, the description covers the core operation, the safety confirmation, and progress/cancellation behavior. It doesn't mention prerequisites like bootloader mode or return values, but it provides enough context for an agent to invoke the tool correctly in most scenarios.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage, but the description clarifies that firmware_path is written to port, and it explains the dependency between erase and confirm_erase. This compensates well for the bare schema, though it doesn't detail every parameter independently.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description begins with 'Write `firmware_path` to `port`', a specific verb and resource combination that clearly defines the tool's purpose. It naturally distinguishes itself from sibling tools like list_ports, board_info, and fs_* operations by focusing on firmware flashing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The context of writing firmware to a port is clear, and the sibling list shows alternatives, but there is no explicit statement of when to use this tool versus others or when not to use it. The guidance is implied rather than explicit, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

fs_getA

Read a file from the board. Content comes back base64-encoded; refuses files over max_bytes.

ParametersJSON Schema
NameRequiredDescriptionDefault
pathYes
portYes
max_bytesNo

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses that content is base64-encoded and that files over max_bytes are refused, offering specific behavioral traits beyond just 'read'. However, it omits error handling, path format, and whether any side effects exist.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence—'Read a file from the board'—followed by two crucial behavioral details. Every phrase earns its place, with zero wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The core read operation and encoding are stated, but the tool has no output schema and no annotations, so the description should cover more. It lacks guidance on parameter usage, error scenarios, and its relationship to sibling tools like fs_ls and fs_put, making it minimally viable but with clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for parameter meaning. It only references max_bytes indirectly ('refuses files over max_bytes') and provides no semantics for 'path' or 'port', leaving half the parameters undefined.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses 'Read a file from the board' – a specific verb and resource – which clearly distinguishes it from siblings like fs_ls, fs_put, and repl_exec. It leaves no ambiguity about what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for reading files but does not explicitly state when to use this tool over alternatives or any exclusions. It implies the use case but doesn't discuss not using it for listing (fs_ls) or writing (fs_put).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

fs_lsB

List a directory on the board's filesystem.

ParametersJSON Schema
NameRequiredDescriptionDefault
pathNo/
portYes

TDQS

B3.3/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It merely states the action without mentioning that it's read-only, requires a connection to the board, or describes the return format. It adds little beyond the name, though it does not contradict annotations since none exist.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that immediately communicates the tool's purpose without filler. It is front-loaded and efficient with zero waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple and has no output schema, but the description omits practical details like prerequisites, return value format, and usage context. With no annotations to fill gaps, it's minimally viable but leaves questions for the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, yet the description does not explain the path or port parameters. While param names are intuitive, the description fails to specify acceptable values, defaults, or the role of port, adding no semantic value over the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'List' and resource 'directory on the board's filesystem', clearly distinguishing it from sibling tools like fs_get/fs_put for file transfer and list_ports for port discovery.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance is provided on when to use fs_ls versus alternatives; it relies on the purpose being self-evident. There are no stated exclusions or conditions, making the usage guidance implied rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

fs_putA

Write a base64-encoded payload to a file on the board, chunked over several raw-REPL exchanges.

ParametersJSON Schema
NameRequiredDescriptionDefault
pathYes
portYes
max_bytesNo
content_base64Yes

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden. It discloses that the write is chunked over raw-REPL exchanges, which is a useful behavioral detail. However, it does not mention overwrite behavior, error handling, or prerequisites like board connectivity, leaving gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence, front-loaded with the action verb 'Write', and contains no filler or repetition. Every word adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With four parameters, no output schema, and no annotations, the description captures the core purpose and key behavior (chunking), but it omits important context such as parameter details for port and max_bytes, return behavior, and failure modes. It is adequate but not fully comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain parameters. It indirectly covers content_base64 ('base64-encoded payload') and path ('file'), but port and max_bytes are not explained. The 'chunked' hint only vaguely relates to max_bytes, failing to compensate for the coverage gap on two of four parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Write'), the resource ('a base64-encoded payload to a file on the board'), and the scope ('on the board'). It distinguishes from siblings like fs_get (reads) and fs_ls (lists) by explicitly indicating a write operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: this tool is for writing files to the board. The mention of 'chunked over several raw-REPL exchanges' implies it is suited for large payloads and handles transfer mechanics. However, it does not explicitly mention when not to use it or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_portsA

List serial ports, including the simulator, with a best-guess chip identification.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden for behavioral disclosure. It discloses the heuristic nature of chip identification ('best-guess'), which is a valuable reliability caveat. It does not detail side effects or permissions, but a listing operation is implicitly non-destructive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that states the primary action and key caveat. Every word adds value, with no repetition or irrelevant detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple listing tool with an output schema and no parameters, the description covers the essential purpose and the notable 'best-guess' caveat. It could be slightly more explicit about typical use cases, but it is complete enough for an agent to decide when to invoke this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description does not need to add parameter details, and the schema already reflects this with an empty properties object.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List'), the resource ('serial ports'), and adds specific scope ('including the simulator') and a notable feature ('best-guess chip identification'). This distinguishes it from sibling tools like board_info and flash_firmware, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'including the simulator' provides clear context that this tool is intended for enumerating both physical and simulated port environments. While it does not explicitly mention alternatives, the context is sufficient for selecting this tool over siblings in a development workflow.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

repl_execA

Run code on port over MicroPython's raw REPL; stdout/stderr/exception come back separately.

ParametersJSON Schema
NameRequiredDescriptionDefault
codeYes
portYes
timeout_sNo

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of behavioral disclosure. It discloses that stdout/stderr/exception are returned separately, which is a useful behavioral trait. However, it does not mention potential side effects of arbitrary code execution, prerequisites like device connection, or error handling, leaving gaps for an agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is concise, front-loaded, and contains no filler. Every part—action, target, mechanism, and output result—is packed meaningfully, earning a high rating.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has moderate complexity with three parameters, no output schema, and no annotations. The description covers the core purpose and output separation, but it leaves out important details such as how to identify the port (though sibling list_ports exists), timeout behavior, and connection prerequisites. It is adequate but could be more complete by referencing sibling tools or clarifying expected behaviors.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It gives meaning to 'code' and 'port' by stating 'Run `code` on `port`', but adds no detail about valid formats or constraints. The 'timeout_s' parameter is not mentioned at all, and the description does not sufficiently explain parameter values beyond restating names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Run') and resource ('`code` on `port`'), and specifies the mechanism ('over MicroPython's raw REPL'). This clearly distinguishes it from sibling tools like list_ports and fs_ls, which handle ports and filesystem operations rather than code execution.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool: when you need to execute Python code on a MicroPython device via raw REPL. It does not explicitly list alternatives or exclusion cases, but the context is sufficiently distinct from sibling tools that an agent can infer appropriate usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

tail_serialA

Capture raw serial output for up to 30 seconds without going through the REPL protocol.

ParametersJSON Schema
NameRequiredDescriptionDefault
portYes
secondsNo

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses a 30-second time limit and the fact that it bypasses the REPL protocol, offering some behavioral context. Yet it does not state whether the operation is read-only, how output is delivered, or any side effects, leaving gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that front-loads the core action and key constraints. Every word contributes meaning with no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with two parameters and no output schema, the description adequately covers the purpose and key constraint. It could mention the output format or prerequisites, but overall it is complete enough for a straightforward capture tool within a device tool suite.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It adds meaning to 'seconds' by mentioning 'up to 30 seconds', but does not clarify the 'port' parameter beyond its self-explanatory name. It does not mention the default value for seconds, which the schema provides, so coverage remains partial.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Capture' and clearly identifies the resource as 'raw serial output', distinguishing it from REPL-based operations. The phrase 'without going through the REPL protocol' explicitly differentiates it from the sibling tool repl_exec.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this tool is for capturing raw serial data when REPL protocol is not desired, providing clear context. However, it does not explicitly name alternatives or explain when not to use it, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 8 tool updatesv0.1.0
    • First observedboard_info
    • First observedflash_firmware
    • First observedfs_get
    • First observedfs_ls
    • First observedfs_put
    • First observedlist_ports
    • First observedrepl_exec
    • First observedtail_serial
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.8/5.0
Disambiguation5/5

Each tool has a clear, distinct purpose: port discovery, board info, flashing, REPL execution, filesystem operations, and serial monitoring. There is no overlap between them, and even related tools like fs_ls/fs_get/fs_put are differentiated by operation type.

Naming Consistency3/5

Naming patterns are mixed: some are verb_noun (list_ports, flash_firmware, tail_serial), some are prefix-based (fs_ls, fs_get, fs_put), and repl_exec inverts the usual order. While readable, the lack of a single consistent convention makes the API slightly less predictable.

Tool Count5/5

With exactly 8 tools, the server is well-scoped for its purpose of managing ESP32 boards. Each tool covers a distinct aspect of the workflow (discovery, flashing, code execution, filesystem, serial) without bloat or trivial tools.

Completeness4/5

The toolset covers the core lifecycle: identify port, get board info, flash firmware, execute code, and manage files. The only notable gap is lack of a delete/rename filesystem operation, but this is a minor omission that doesn't compromise the primary workflows.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • esp-mcp

    horw
    F
    license
    Not graded
    quality
    F
    maintenance
    An MCP server for managing ESP-IDF workflows, enabling LLMs to build, flash, and test firmware for ESP32 and related microcontrollers. It provides tools for project creation, target configuration, and serial port management to simplify embedded development.
    156
    -

  • Python REPL MCP Server

    piplin-es
    A
    license
    Not graded
    quality
    D
    maintenance
    Provides a persistent Python REPL session as a tool for executing code, managing files, installing packages, and initializing projects via the MCP protocol.
    1
    MIT

  • mcp-micropython-bridge

    SWITCHSCIENCE
    F
    license
    Not graded
    quality
    D
    maintenance
    MCP server for controlling MicroPython devices (ESP32, RP2040, etc.) via USB Serial or WebREPL, enabling code execution, file operations, and device management from MCP clients.
    8
    -

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/0mandrock1/mcp-esp32'

If you have feedback or need assistance with the MCP directory API, please join our Discord server