Skip to main content
Glama

read_screen

Reads the current 5250 screen content to retrieve visible text, cursor position, input fields, and screen dimensions.

Instructions

Read the current 5250 screen content.

Returns structured data with:

  • screen: list of text rows (the visible display)

  • cursor: current cursor position {row, col} (1-based)

  • fields: list of input fields with position, length, value, and type

  • dimensions: screen size {rows, cols}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The read_screen MCP tool handler registered via @mcp.tool() decorator. Calls get_screen_data() on the session's ScreenBuffer.
    @mcp.tool()
    async def read_screen() -> dict:
        """Read the current 5250 screen content.
    
        Returns structured data with:
        - screen: list of text rows (the visible display)
        - cursor: current cursor position {row, col} (1-based)
        - fields: list of input fields with position, length, value, and type
        - dimensions: screen size {rows, cols}
        """
        if _session is None:
            return {"error": "Not connected. Call connect() first."}
    
        return _session.screen.get_screen_data()
  • Registration of read_screen as an MCP tool using the @mcp.tool() decorator from FastMCP.
    @mcp.tool()
    async def read_screen() -> dict:
  • The get_screen_data() helper method on ScreenBuffer that collects and structures the screen content (text rows, cursor, input fields, dimensions).
    def get_screen_data(self) -> dict:
        input_fields = []
        for f in self.fields:
            if f.is_input:
                input_fields.append({
                    "row": f.row + 1,
                    "col": f.col + 1,
                    "length": f.length,
                    "value": self.get_field_value(f).rstrip(),
                    "field_type": f.field_type,
                })
        return {
            "screen": self.get_text_rows(),
            "cursor": {"row": self.cursor_row + 1, "col": self.cursor_col + 1},
            "fields": input_fields,
            "dimensions": {"rows": self.rows, "cols": self.cols},
        }
  • Constant definition for the OP_READ_SCREEN opcode (0x08) used in TN5250 session protocol handling.
    OP_READ_SCREEN = 0x08
  • Handler in the TN5250 session for the OP_READ_SCREEN opcode, which unlocks the keyboard when a read screen operation completes.
    elif opcode == OP_READ_SCREEN:
        self._keyboard_locked = False
        self._unlock_event.set()
Behavior2/5

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

No annotations provided. The description mentions return structure but does not disclose side-effect behavior (e.g., read-only nature, safety). It lacks explicit transparency beyond output details.

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?

Very concise with bullet-pointed return values. Front-loaded purpose, every sentence adds value. No redundancy.

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?

For a zero-parameter read tool, the description fully explains behavior and return format. No missing details given the simplicity.

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?

No parameters exist, so schema coverage is 100%. Baseline for zero parameters is 4. Description adds no parameter-specific meaning, but none needed.

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 it reads the current 5250 screen content with a specific verb and resource. It distinguishes itself from sibling tools (connect, disconnect, send_key, etc.) which handle connection and input operations.

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

Usage Guidelines3/5

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

The description does not explicitly state when to use this tool versus alternatives, but the purpose is self-explanatory given sibling differentiation. Implicitly requires connection but no explicit guidance.

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/WhitehornLtd/ibmi-mcp'

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