Skip to main content
Glama

ppsspp_screenshot

Capture a PNG screenshot of the PSP framebuffer. Select 'render' for native resolution (safe) or 'output' for the final display (may crash on some games).

Instructions

PURPOSE: Capture the current PSP framebuffer as a PNG-encoded screenshot. USAGE: For visual inspection or sequence documentation. Default 'render' source reads the active GPU render target — safer, native 480x272, what the PSP CPU asked the GPU to draw. Opt-in 'output' source reads PPSSPP's final composited output (post scaling/shaders) but can crash PPSSPP on games whose output framebuffer state confuses GPU_GetOutputFramebuffer (a real upstream bug — an assert that should be a graceful failure). Prefer 'render' unless you specifically need the post-processed image. BEHAVIOR: Transparently pauses the CPU (cpu.stepping), captures, then resumes — both PPSSPP buffer events require stepping. If the emulator was already paused, leaves it paused. Returns an error if no game is loaded. The 'output' source CAN crash PPSSPP on certain games; if it does, MCP auto-reconnects to the relaunched PPSSPP cleanly. RETURNS: Text confirmation + inline PNG image block.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sourceNoWhich GPU buffer to capture. 'render' (default) reads the current render target via gpu.buffer.renderColor — native PSP 480x272, safer on homebrew/edge-case games. 'output' reads the final composited framebuffer via gpu.buffer.screenshot — post-processed (matches what's on screen) but can crash PPSSPP on games where GPU_GetOutputFramebuffer trips its null-buf assertion.
Behavior5/5

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

The description discloses key behaviors: pauses CPU during capture, resumes unless already paused, returns error if no game loaded, and that the 'output' source can crash PPSSPP but MCP auto-reconnects. Since no annotations are provided, the description carries the full burden and meets it fully.

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 structured with clear sections (PURPOSE, USAGE, BEHAVIOR, RETURNS) and front-loads the purpose. Every sentence adds unique value without redundancy. Length is appropriate for a one-parameter tool.

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?

Given no output schema, the description specifies the return format (text confirmation + inline PNG). It covers all aspects: purpose, source options, side effects, error cases, and post-capture behavior. Sufficient for an agent to select and invoke correctly.

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

Parameters5/5

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

The input schema provides 100% coverage with enum values, but the description adds significant value: explains the technical difference (GPU render target vs composited output), notes native resolution for render, and gives crash context for output. This exceeds schema detail.

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 tool captures a PNG screenshot of the PSP framebuffer, with specific verb 'capture' and resource 'framebuffer'. It distinguishes between 'render' and 'output' sources, and differs from sibling tools (no other screenshot tool) by focusing solely on visual capture.

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

Usage Guidelines5/5

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

The description provides explicit guidance: 'Prefer 'render' unless you specifically need the post-processed image.' It warns against using 'output' on certain games due to crash risk, and explains the default behavior. There are no alternative screenshot tools among siblings, so it fully addresses when to use this tool.

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

Install Server

Other Tools

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/dmang-dev/mcp-ppsspp'

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