Skip to main content
Glama
Sign In

Cloudhil

by io.github.Tetef
OverviewDiscussionsAdmin

Flash ELF on a real MCU

flash_elf
Destructive

Flash a pre-built ELF you compiled locally (see AGENTS.md hello/). Pass the binary as elf_base64, or elf_url on https. Do not pass a filesystem path. Requires a Pay With Prompt voucher (merchant cloudhil, 10 credits = 1 flash). Cloudhil verifies it server-side before programming. Returns result.mailbox (NNOK 0x4E4E4F4B) and result.uart. nucleo-n6 and lpc55569-evk require .elf. Oneshot ≤20s then erase. Needs a Cloudhil account (Connect / OAuth).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "board": "<board>",
      "voucher": "<voucher>"
    },
    "name": "flash_elf"
  }
}

Input Schema

NameRequiredDescriptionDefault
boardYesnucleo-n6, disco-h7, nucleo-f4, or lpc55569-evk
elf_urlNohttps URL of the ELF if it is too large for elf_base64
voucherYesPay With Prompt voucher pwpv_… for merchant cloudhil, from https://paywithprompt.com. Not logged.
filenameNoOriginal filename ending in .elf .bin or .hex (default firmware.elf)
elf_base64NoBase64 of the ELF/BIN/HEX you compiled locally (max 2 MiB decoded)
uart_secondsNoObserve 0..20 seconds (default 20)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and readOnlyHint=false; the description goes well beyond that by disclosing the paid voucher flow (merchant cloudhil, 10 credits per flash), server-side verification, the erase-after-oneshot timing (≤20s), the Cloudhil account/OAuth prerequisite, and even the return payload (result.mailbox, result.uart). Those are exactly the consequences an agent needs before invoking a destructive write.

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

Conciseness4/5

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

Front-loaded with the action, and nearly every sentence carries operational information. It is telegraphic and slightly repetitive — the voucher requirement, server-side Cloudhil verification, and the Cloudhil account need are stated in three separate places and could be consolidated.

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

Completeness5/5

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

No output schema exists, yet the description explains the return fields (result.mailbox sentinel, result.uart), the timeout/erase behavior, the payment and authentication prerequisites, and the input format rules. That is enough for an agent to call a destructive hardware-flashing tool correctly.

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 coverage is 100%, so the baseline is 3; the description earns more by adding cross-parameter constraints the schema does not express — the ban on filesystem paths for elf_url, and the rule that two boards require .elf specifically (the schema lists filename as accepting .elf/.bin/.hex).

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?

States a specific verb and resource: 'Flash a pre-built ELF you compiled locally'. It is immediately distinguishable from siblings like list_boards, get_job and send_feedback, and names the prerequisite context (AGENTS.md hello/).

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?

Gives explicit how-to-use guidance ('Pass the binary as elf_base64, or elf_url on https') and an explicit exclusion ('Do not pass a filesystem path'), plus board-specific rules ('nucleo-n6 and lpc55569-evk require .elf'). It does not point to any alternative tool, but no sibling performs flashing, so the gap is minor.

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

All Cloudhil toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources