Skip to main content
Glama
discohead

textual-mcp-server

by discohead

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
textual_launchC

Launch a Textual app headlessly for QA interaction.

textual_stopB

Stop a running Textual app session.

textual_pressC

Simulate key presses in a running Textual app.

textual_clickA

Click a widget by CSS selector in a running Textual app.

textual_type_textC

Type text into the focused input widget.

textual_hoverC

Hover the mouse over a widget by CSS selector.

textual_snapshotB

Snapshot current app state — widget tree with refs, focus, bindings, errors.

textual_screenshotB

Capture a visual screenshot of the running app (text or SVG).

textual_queryB

Query widgets matching a CSS selector with their properties.

textual_get_screen_stackC

Get the current screen stack with modal indicators.

textual_wait_forC

Wait for a condition: idle, animation, workers, or widget.

textual_check_errorsC

Check for collected errors and app exceptions.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.5/5.0

Scored across 12 tools

Disambiguation5/5

Each tool targets a distinct action: launching, clicking, hovering, typing, pressing keys, querying widgets, taking screenshots, capturing state, waiting for conditions, checking errors, and stopping the app. No two tools overlap in purpose.

Naming Consistency5/5

All tools follow a consistent 'textual_' prefix followed by a descriptive verb in snake_case (e.g., textual_click, textual_query). No deviations in naming convention.

Tool Count5/5

With 12 tools, the server covers all essential interactions for headless QA of Textual apps: launching, UI manipulation, state inspection, and error checking. The count is well-scoped without unnecessary redundancy.

Completeness4/5

The tool set covers core workflows (launch, interact, query, debug, stop). Minor gaps like drag-and-drop or scroll are absent but not critical for typical testing scenarios.

Maintenance

ActivityInactive
ResponsivenessNo issues