Skip to main content
Glama
zinin

sketchup-mcp2

by zinin
OverviewSchemaRelated ServersScoreDiscussions
Local

get_version

Check server version and Python-Ruby compatibility to verify runtime health. Returns version details and compatibility status even when other tools fail.

Instructions

Return the server version and Python↔Ruby compatibility verdict.

Useful as a runtime sanity probe — always returns a payload, even when the connection or other tools surface errors. The result is a JSON string with fields: python_version, ruby_version, min_compatible_ruby, max_compatible_ruby, ruby_min_compatible_python, ruby_max_compatible_python, compatible (bool), error (string | null).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • src/sketchup_mcp/tools.py:453-534 (handler)
    The actual tool handler function decorated with @mcp.tool() — calls the Ruby backend via _raw_call, performs two-way version compatibility checks, and always returns a diagnostic JSON payload.
    @mcp.tool()
async def get_version(ctx: Context) -> str:
    """Return the server version and Python↔Ruby compatibility verdict.

    Useful as a runtime sanity probe — always returns a payload, even
    when the connection or other tools surface errors. The result is a
    JSON string with fields: python_version, ruby_version,
    min_compatible_ruby, max_compatible_ruby, ruby_min_compatible_python,
    ruby_max_compatible_python, compatible (bool), error (string | null).
    """
    def _payload(ruby_version, ruby_min, ruby_max, compatible, error_msg):
        return json.dumps({
            "python_version": compat.CLIENT_VERSION,
            "ruby_version": ruby_version,
            "min_compatible_ruby": compat.MIN_RUBY,
            "max_compatible_ruby": compat.MAX_RUBY,
            "ruby_min_compatible_python": ruby_min,
            "ruby_max_compatible_python": ruby_max,
            "compatible": compatible,
            "error": error_msg,
        })

    try:
        raw = await _raw_call(ctx, "get_version")
    except ConnectionError as e:
        return _payload(None, None, None, False,
                        f"SketchUp not running or extension not started: {e}")
    except SketchUpError as e:
        # Covers old Ruby returning -32601 "unknown tool: get_version"
        # and any other JSON-RPC error envelope. Version compatibility is
        # validated once at connect-time in ``_handshake``; once a
        # connection survives that, tool-level errors here come from the
        # Ruby handler itself (not from per-request version checks).
        return _payload(None, None, None, False, str(e))

    # Defensive parse: any unexpected shape (missing keys, non-list content,
    # non-string text, invalid JSON, non-dict payload) must STILL produce a
    # payload — the tool's contract is "always returns a payload even on
    # mismatch / error", so a KeyError/IndexError/TypeError/JSONDecodeError
    # escaping here would violate it.
    try:
        ruby_payload = json.loads(raw["content"][0]["text"])
        if not isinstance(ruby_payload, dict):
            raise TypeError(
                f"ruby payload is {type(ruby_payload).__name__}, expected dict"
            )
    except (KeyError, IndexError, TypeError, json.JSONDecodeError) as e:
        return _payload(None, None, None, False,
                        f"unexpected get_version response shape: {e}")
    ruby_version = ruby_payload.get("ruby_version")
    ruby_min = ruby_payload.get("min_compatible_python")
    ruby_max = ruby_payload.get("max_compatible_python")

    # Two-way compatibility: BOTH sides' tables must accept the counterpart.
    try:
        compat.check_ruby_version(ruby_version)
        python_accepts_ruby, py_error = True, None
    except IncompatibleVersionError as e:
        python_accepts_ruby, py_error = False, str(e)

    try:
        ruby_accepts_python = bool(
            ruby_min and ruby_max and
            compat.parse(ruby_min)
            <= compat.parse(compat.CLIENT_VERSION)
            <= compat.parse(ruby_max)
        )
    except ValueError:
        ruby_accepts_python = False

    compatible = python_accepts_ruby and ruby_accepts_python
    if py_error:
        error_msg = py_error
    elif not ruby_accepts_python:
        error_msg = (
            f"SketchUp plugin advertises Python compatibility "
            f"{ruby_min}..{ruby_max}, which excludes v{compat.CLIENT_VERSION}."
        )
    else:
        error_msg = None

    return _payload(ruby_version, ruby_min, ruby_max, compatible, error_msg)
  • src/sketchup_mcp/tools.py:453-462 (schema)
    Docstring serves as the schema definition — describes the input (none) and the output shape (8 JSON fields). No Pydantic model since the tool takes no arguments.
    @mcp.tool()
async def get_version(ctx: Context) -> str:
    """Return the server version and Python↔Ruby compatibility verdict.

    Useful as a runtime sanity probe — always returns a payload, even
    when the connection or other tools surface errors. The result is a
    JSON string with fields: python_version, ruby_version,
    min_compatible_ruby, max_compatible_ruby, ruby_min_compatible_python,
    ruby_max_compatible_python, compatible (bool), error (string | null).
    """
  • src/sketchup_mcp/tools.py:453-534 (registration)
    Registered via the @mcp.tool() decorator on the FastMCP instance 'mcp' imported from sketchup_mcp.app. The side-effect import in app.py (import sketchup_mcp.tools) triggers registration.
    @mcp.tool()
async def get_version(ctx: Context) -> str:
    """Return the server version and Python↔Ruby compatibility verdict.

    Useful as a runtime sanity probe — always returns a payload, even
    when the connection or other tools surface errors. The result is a
    JSON string with fields: python_version, ruby_version,
    min_compatible_ruby, max_compatible_ruby, ruby_min_compatible_python,
    ruby_max_compatible_python, compatible (bool), error (string | null).
    """
    def _payload(ruby_version, ruby_min, ruby_max, compatible, error_msg):
        return json.dumps({
            "python_version": compat.CLIENT_VERSION,
            "ruby_version": ruby_version,
            "min_compatible_ruby": compat.MIN_RUBY,
            "max_compatible_ruby": compat.MAX_RUBY,
            "ruby_min_compatible_python": ruby_min,
            "ruby_max_compatible_python": ruby_max,
            "compatible": compatible,
            "error": error_msg,
        })

    try:
        raw = await _raw_call(ctx, "get_version")
    except ConnectionError as e:
        return _payload(None, None, None, False,
                        f"SketchUp not running or extension not started: {e}")
    except SketchUpError as e:
        # Covers old Ruby returning -32601 "unknown tool: get_version"
        # and any other JSON-RPC error envelope. Version compatibility is
        # validated once at connect-time in ``_handshake``; once a
        # connection survives that, tool-level errors here come from the
        # Ruby handler itself (not from per-request version checks).
        return _payload(None, None, None, False, str(e))

    # Defensive parse: any unexpected shape (missing keys, non-list content,
    # non-string text, invalid JSON, non-dict payload) must STILL produce a
    # payload — the tool's contract is "always returns a payload even on
    # mismatch / error", so a KeyError/IndexError/TypeError/JSONDecodeError
    # escaping here would violate it.
    try:
        ruby_payload = json.loads(raw["content"][0]["text"])
        if not isinstance(ruby_payload, dict):
            raise TypeError(
                f"ruby payload is {type(ruby_payload).__name__}, expected dict"
            )
    except (KeyError, IndexError, TypeError, json.JSONDecodeError) as e:
        return _payload(None, None, None, False,
                        f"unexpected get_version response shape: {e}")
    ruby_version = ruby_payload.get("ruby_version")
    ruby_min = ruby_payload.get("min_compatible_python")
    ruby_max = ruby_payload.get("max_compatible_python")

    # Two-way compatibility: BOTH sides' tables must accept the counterpart.
    try:
        compat.check_ruby_version(ruby_version)
        python_accepts_ruby, py_error = True, None
    except IncompatibleVersionError as e:
        python_accepts_ruby, py_error = False, str(e)

    try:
        ruby_accepts_python = bool(
            ruby_min and ruby_max and
            compat.parse(ruby_min)
            <= compat.parse(compat.CLIENT_VERSION)
            <= compat.parse(ruby_max)
        )
    except ValueError:
        ruby_accepts_python = False

    compatible = python_accepts_ruby and ruby_accepts_python
    if py_error:
        error_msg = py_error
    elif not ruby_accepts_python:
        error_msg = (
            f"SketchUp plugin advertises Python compatibility "
            f"{ruby_min}..{ruby_max}, which excludes v{compat.CLIENT_VERSION}."
        )
    else:
        error_msg = None

    return _payload(ruby_version, ruby_min, ruby_max, compatible, error_msg)
  • src/sketchup_mcp/connection.py:43-53 (helper)
    get_version is listed in _RETRY_SAFE_TOOLS frozenset, marking it as a read-only diagnostic tool eligible for stale-socket auto-retry.
    _RETRY_SAFE_TOOLS: frozenset[str] = frozenset(
    {
        "get_model_info",
        "list_components",
        "get_component_info",
        "find_components",
        "list_layers",
        "get_selection",
        "get_viewport_screenshot",  # read-only viewport capture; idempotent in
                                    # both restore_view modes (no document state changes)
        "get_version",              # read-only diagnostic; no side effects

Tool Definition Quality

A4.5/5.0
Behavior4/5

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

With no annotations provided, the description carries full burden. It discloses that the tool always returns a payload, even during connection or other errors, and describes the result structure (JSON string with specific fields). This provides meaningful behavioral context beyond basic purpose.

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 two sentences plus a field listing, with no wasted words. The main purpose is front-loaded, and every sentence adds value.

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 parameters and an output schema, the description is remarkably complete: it explains when to use, what it returns, and its reliability. It adds details about the compatibility fields beyond the bare schema.

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?

The tool has zero parameters, so baseline is 4 per guidelines. The description adds no parameter information because none exist. It correctly focuses on return value and usage context.

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 returns server version and compatibility verdict, which is a specific verb+resource. It distinguishes from sibling tools by describing its unique role as a runtime sanity probe.

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?

The description explicitly recommends using it as a runtime sanity probe and notes it always returns a payload even when other tools error. While it doesn't list alternatives or exclusions, the context is clear enough for an agent to decide when to invoke it.

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/zinin/sketchup-mcp2'

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