acpi-mcp

Overview Schema Source Related Servers Discussions Admin

acpi_load

Load ACPI tables from a live QEMU guest through its gdbstub or from raw table dumps, and register the snapshot under a name for later inspection.

Instructions

Load a set of ACPI tables and register it under name.

Pass exactly one source:

port: a live VM's gdbstub (QEMU -s is port 1234). Tables are read from guest PHYSICAL memory, so this works even after the guest enables paging. QEMU allows one debugger at a time - disconnect gdbstub-mcp first. QEMU pauses the guest while attached; resume=True detaches afterwards (the guest runs on, even one started with -S), resume=False leaves it paused. If QEMU was started with -S the firmware hasn't built the tables yet: set boot_wait_s=5: it runs the guest until the tables exist, then stops.
path: a directory of raw tables - /sys/firmware/acpi/tables on Linux (needs root), or the output of acpidump -b (any OS). Tables are a snapshot; load again to re-read.

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": {
      "name": "<name>"
    },
    "name": "acpi_load"
  }
}

Input Schema

Name	Required	Default
`host`	No	127.0.0.1
`name`	Yes
`path`	No
`port`	No
`resume`	No
`boot_wait_s`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 10, 2026

TDQS

A4.5/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so: reads are from guest PHYSICAL memory, QEMU pauses the guest while attached, resume=True detaches (guest runs even if started with -S) while resume=False leaves it paused, boot_wait_s handles -S firmware timing, root is needed for the sysfs path, and the loaded set is a snapshot. These are exactly the non-obvious side effects an agent needs before invoking.

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?

The core action is front-loaded in one sentence and the source options are cleanly bulleted, so the agent can scan for the decision it needs. Some clauses are dense and nested (the resume parenthetical, the -S explanation), but no sentence is 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 six-parameter tool with hidden side effects and no annotations, the description covers nearly everything: source selection, pausing behavior, boot timing, permissions, and snapshot semantics. An output schema exists so return values need not be described, leaving only `host` unspecified.

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 0%, so the description must compensate; it explains port, path, resume, boot_wait_s, and what `name` registers, along with the mutual-exclusivity of port/path. The only unaddressed parameter is `host` (default 127.0.0.1), which is left entirely to the schema title.

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?

'Load a set of ACPI tables and register it under `name`' gives a specific verb (load), a specific resource (ACPI tables), and the side effect (registration under a name). This is clearly distinct from sibling tools like acpi_dump/acpi_tables that read or list rather than register a loaded set.

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 states a hard selection rule ('Pass exactly one source') and explains when each source applies: live VM via gdbstub vs. a table directory from /sys/firmware/acpi/tables or acpidump -b output. It also gives conditional guidance for resume and boot_wait_s, but it does not route the agent among sibling tools beyond the note to disconnect gdbstub-mcp first.

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

Deploy Server