Skip to main content
Glama
Sign In
bambu-printer-mcp

bambu-printer-mcp

by DMontgomery40
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

camera_snapshot

Destructive

Capture a single JPEG frame from a Bambu Lab printer chamber camera, returning base64 data or saving it to disk for live monitoring and snapshot-based checks.

Instructions

Capture a single JPEG frame from the printer's chamber camera. A1/P1 use TCP-on-6000; X1/P2S/H2/X2D use RTSP via ffmpeg. Returns JPEG as base64; pass save_path to also write the bytes to disk.

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": "camera_snapshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostNoHostname or IP of the printer (default: value from env)
save_pathNoOptional absolute path to write the JPEG to disk. If omitted, only the base64 payload is returned.
timeout_msNoMax ms to wait for a live frame (default 8000). A1/P1 cameras first replay a buffered frame, which is skipped, so a live frame takes about 3 s, longer on cold start.
bambu_modelNoPrinter model. Used to route to the correct protocol or fail fast on unsupported models. Defaults to BAMBU_MODEL.
bambu_tokenNoAccess token (default: value from env)
ffmpeg_pathNoOverride path to the ffmpeg binary used by the RTSP path. Defaults to FFMPEG_PATH or ffmpeg via $PATH. Per-call overrides require MCP_ALLOW_EXECUTABLE_ARG=1. Required only for the RTSP transport (X1, P2S, H2 series, X2D).
bambu_serialNoSerial number (default: value from env)
experimentalNoDeprecated and ignored. Earlier this flag let callers probe H2 series via the A1/P1 TCP-on-6000 path; live testing on an H2S confirmed H2 uses RTSP instead, so the flag has no effect now.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.37
    • changedInput schema / properties / timeout_ms / description
      Previous value: -"Max ms to wait for a full frame (default 8000). Camera may take a few seconds on cold start."New value: +"Max ms to wait for a live frame (default 8000). A1/P1 cameras first replay a buffered frame, which is skipped, so a live frame takes about 3 s, longer on cold start."
  2. Changed1 schema field changedv1.1.14
    • changedInput schema / properties / ffmpeg_path / description
      Previous value: -"Override path to the ffmpeg binary used by the RTSP path. Defaults to ffmpeg via $PATH. Required only for the RTSP transport (X1, P2S, H2 series)."New value: +"Override path to the ffmpeg binary used by the RTSP path. Defaults to FFMPEG_PATH or ffmpeg via $PATH. Per-call overrides require MCP_ALLOW_EXECUTABLE_ARG=1. Required only for the RTSP transport (X1, P2S, H2 series, X2D)."
  3. First observedv1.1.1

TDQS

A3.6/5.0
Behavior4/5

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

Annotations declare destructiveHint=true and readOnlyHint=false, which the description usefully explains via the optional on-disk write to save_path. Beyond annotations it discloses per-model transport behavior (TCP-on-6000 vs RTSP/ffmpeg), the buffered-frame skip on A1/P1, and the MCP_ALLOW_EXECUTABLE_ARG=1 gate, though it says nothing about failure modes for unsupported models or rate/latency limits beyond the default timeout.

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?

Three sentences, no filler, and the core action is front-loaded ahead of transport and return-value detail. Each clause carries distinct information an agent would otherwise have to discover by trial.

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 an 8-parameter tool with no output schema it covers the essentials: where the image comes from, what comes back, and how to also persist it. The main missing piece is differentiation from camera_frame and a note on what happens when bambu_model routes to an unsupported device.

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 coverage is 100%, so every parameter already carries its own detailed description, including the ffmpeg_path execution gate and timeout rationale. The description's only added parameter meaning is the return-shape choice between base64 and disk write, which is largely a restatement, so the baseline of 3 applies.

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 opens with a specific verb and resource: 'Capture a single JPEG frame from the printer's chamber camera,' and adds protocol-routing detail per model. It stops short of a 5 because it never tells the agent how this differs from the sibling tool camera_frame, which by name reads as the same operation.

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?

There is no explicit statement of when to use this instead of camera_stream_start, camera_frame, or camera_stream_stop, even though all four touch the same camera. The only conditional guidance is protocol routing by model, which the tool resolves internally rather than being a usage decision the agent must make.

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