Skip to main content
Glama

build_banks

Build audio banks for the default platform in FMOD Studio via TCP scripting, compiling imported sounds and events into deployable assets.

Instructions

Build banks for the default platform. Can take a minute or two.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Core handler that executes the FMOD Studio project build via JavaScript eval and collects built bank paths.
    async def build_banks(client: StudioClient) -> dict[str, Any]:
        """Build banks for the currently open project.
    
        Uses Studio's default build platform (the one selected in the project
        preferences). Returns the list of bank paths that were built, if Studio
        exposes them; otherwise just a success flag.
        """
        js = """
            studio.project.build();
            var banks = [];
            try {
                var all = studio.project.model.Bank.findInstances();
                for (var i = 0; i < all.length; i++) banks.push(all[i].getPath());
            } catch (e) {}
            return { ok: true, built: true, banks: banks };
        """
        # Building can take a while on large projects; allow 10 minutes.
        return await client.eval(js, timeout=600.0)
  • MCP tool registration that wraps the project.build_banks handler as a FastMCP tool.
    @mcp.tool()
    async def build_banks() -> dict[str, Any]:
        """Build banks for the default platform. Can take a minute or two."""
        return await project.build_banks(_studio())
  • Test asserting that build_banks is registered as a tool on the MCP server.
    EXPECTED_TOOLS = {
        # discovery
        "ping",
        "list_banks",
        "list_events",
        "list_buses",
        "get_event",
        # audio + events
        "import_audio",
        "create_event",
        "add_single_sound",
        "set_event_property",
        "assign_to_bank",
        "assign_to_bus",
        # effects
        "list_effect_types",
        "add_effect",
        "list_effects",
        "get_effect",
        "set_effect_param",
        "remove_effect",
        "bypass_effect",
        # project
        "save_project",
        "build_banks",
        # escape
        "run_js",
    }
  • Unit test for the build_banks tool, verifying it sends correct JS and returns expected result.
    async def test_build_banks(client: StudioClient, mock_studio: MockStudio):
        mock_studio.responder = responder_sequence([("OK", {"ok": True, "built": True, "banks": ["bank:/Master"]})])
        result = await project.build_banks(client)
        assert result["built"] is True
        assert "studio.project.build" in _last_sent_js(mock_studio)
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It adds the behavioral fact that the operation can take a minute or two, which is helpful. However, it does not disclose other traits like whether it is destructive, requires authentication, or its effect on the system state.

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 extremely concise: two sentences with no unnecessary words. It front-loads the purpose and then adds a single behavioral note. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of parameters and the presence of an output schema (not detailed but exists), the description is mostly sufficient. However, it omits context about prerequisites (e.g., does something need to be set up first?), the meaning of 'default platform,' and whether there are side effects beyond the time delay. It is adequate but not rich.

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?

There are no parameters, so the input schema is complete. The description does not need to add parameter meaning. With 0 parameters, the baseline is 4, and no further elaboration is necessary.

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 clearly states the action ('Build banks') and the resource ('for the default platform'). It distinguishes this from sibling tools like list_banks and assign_to_bank by implying a generation process. However, it could be more specific about what 'build' entails.

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?

No guidance on when to use this tool versus alternatives (e.g., when banks need to be updated after changes). The only hint is the time warning, but no explicit when-to or when-not-to use.

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/jmperez127/fmod-mcp'

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