Skip to main content
Glama
Sign In
Copper

Copper

by claynicholson
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Read PCB

pcb_read
Read-onlyIdempotent

Read PCB data from a KiCad file or live editor to inspect summaries, footprints, nets, pads, tracks, zones, and drawings, filter by reference or net, and optionally run DRC.

Instructions

Read the PCB. With no arguments: a digest (footprint, track, via and unrouted counts, outline size, layers). what: any of summary | footprints (ref, value, position mm, rotation, side) | nets | pads | tracks (every segment with its uuid; combine with net) | widths (per-net copper summary) | zones | drawings. refs: only these footprints. net: only that net. drc=true also runs KiCad DRC. source='live' reads the board open in the running KiCad editor. Example: pcb_read(what=["footprints"], refs=["U1"]) · pcb_read(what=["nets"], net="GND")

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "pcb_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
drcNoAlso run kicad-cli DRC (slower; default false)
netNoFilter nets/pads/tracks to this net name
refsNo
whatNo
limitNoMax footprints/tracks listed (default 200)
sourceNofile (default) or live IPC board
projectNoproject path (default: active)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint/idempotent/openWorld=false, so the safety profile is covered. The description adds real behavioral context beyond that: drc=true shells out to kicad-cli and is slower, and source='live' depends on a running KiCad editor session — both are non-obvious side conditions. It does not discuss pagination or truncation behavior of the default 200 limit.

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?

Front-loaded with the purpose and the zero-argument default, then a compact parameter-by-parameter legend, then examples. It uses dense fragments rather than prose, and every line carries information an agent needs to choose the right `what` value.

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?

With no output schema, the description carries the return-shape burden and does so for the default digest and for each `what` facet. For a 7-parameter read tool this is close to complete; only the `limit`/`project` parameters and behavior when a filter matches nothing are unaddressed.

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 71%, and the description compensates well for the biggest gap: the `what` enum values are explained individually (e.g. tracks include every segment with its uuid and combine with net; widths is a per-net copper summary), which the schema's bare enum does not convey. It also explains refs and net filtering semantics. `limit` and `project` are left entirely to the schema, keeping this short of a 5.

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 opens with a specific verb+resource ("Read the PCB") and immediately enumerates the returnable facets: digest counts, footprints, nets, pads, tracks, widths, zones, drawings. This lets an agent distinguish it from pcb_edit/pcb_place/pcb_route (mutations) and from sch_read (schematic side) without opening any schema.

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?

It states the default invocation behavior (no arguments → digest) and shows concrete call patterns with filters (refs, net) plus two worked examples. What's missing is an explicit "do not use this to modify" exclusion or a named alternative for schematic data, so it's clear context rather than full when/when-not guidance.

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

Deploy Server

Other Tools