Skip to main content
Glama
dmang-dev

mcp-dolphin

dolphin_read32

Reads a 32-bit big-endian value from PowerPC memory at a specified address. Use for pointers, timestamps, and counters in GameCube and Wii games.

Instructions

PURPOSE: Read an unsigned 32-bit big-endian value from PowerPC memory at the given absolute address. USAGE: The workhorse — most game state and pointers are 32-bit. Use for timestamps, large counters, RGBA colors, full pointers (PowerPC is a 32-bit ISA so pointers fit here). For 8/16/64-bit values use the corresponding sibling. BEHAVIOR: No side effects — pure read. Address MUST be 4-byte aligned. Returns an error on unmapped address, bridge disconnect, or FAIL.

GameCube + Wii main address space landmarks (PowerPC, big-endian): 0x80000000-0x817FFFFF MEM1 main RAM (24 MiB) — GameCube + Wii game code & data GameCube games stay entirely within MEM1. Wii games use MEM1 for code and frequently-accessed data. 0x80000020 OS_GLOBALS — game-info struct (disc ID, FST, etc.) 0x80000034 OS_ARENA_LO (start of free MEM1 heap) 0x80003100 OS_REPORT (developer-console mirror, varies by SDK) 0x90000000-0x93FFFFFF MEM2 (64 MiB) — Wii ONLY. Larger texture/asset data, IOS work areas. Reading MEM2 on a GameCube game returns garbage / FAIL. 0xCC000000-0xCC00FFFF Hollywood I/O (Wii) / Flipper I/O (GameCube) — DMA, GPU FIFO, AI, EXI registers. Reads are usually safe, writes can wedge the emulator. Avoid. 0xCD000000-0xCD007FFF Wii-only Hollywood registers.

Notes: • All multi-byte values are BIG-ENDIAN on the real hardware. Felk's memory.read_u*/write_u* helpers handle the byte swap for you — the value you see is the value the game sees as a u32. • Addresses are 32-bit; Felk truncates the high bits of any u64 address argument. • Pointers in MEM1 are often stored as 4-byte addresses with the high bit set (e.g. 0x81234567). Dereferencing them requires no masking — pass the raw value back into memory.read_*.

RETURNS: Single line 'ADDR_HEX: VAL_DEC (0xVAL_HEX)'.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
addressYesAbsolute PowerPC virtual address (0x80000000-0x9FFFFFFF). Pass as a number; hex literals like 0x80001000 are fine. Reads 4 consecutive bytes starting here and interprets them as a big-endian value. MUST be 4-byte aligned (address % 4 === 0). PowerPC raises an alignment exception on misaligned access in hardware, but Dolphin's emulated bus is forgiving and silently returns the aligned-down word — i.e. you get the bytes from address & ~3, not what you asked for. For unaligned multi-byte reads use dolphin_read_range and assemble client-side. Useful ranges: 0x80000000-0x817FFFFF for MEM1 (GC + Wii), 0x90000000-0x93FFFFFF for MEM2 (Wii only).

Implementation Reference

  • Tool definition schema for dolphin_read32, specifying input requires a 4-byte-aligned integer `address` parameter.
    {
      name: "dolphin_read32",
      description:
        "PURPOSE: Read an unsigned 32-bit big-endian value from PowerPC memory at the given absolute address. " +
        "USAGE: The workhorse — most game state and pointers are 32-bit. Use for timestamps, large counters, RGBA colors, full pointers (PowerPC is a 32-bit ISA so pointers fit here). For 8/16/64-bit values use the corresponding sibling. " +
        "BEHAVIOR: No side effects — pure read. Address MUST be 4-byte aligned. Returns an error on unmapped address, bridge disconnect, or FAIL.\n\n" +
        GC_WII_MEMORY_MAP + "\n\n" +
        "RETURNS: Single line 'ADDR_HEX: VAL_DEC (0xVAL_HEX)'.",
      inputSchema: {
        type: "object",
        required: ["address"],
        properties: {
          address: { type: "integer", minimum: 0, description: addrParamDesc(4) },
        },
        additionalProperties: false,
      },
    },
  • Handler for dolphin_read32: reads a 32-bit unsigned big-endian value from PowerPC memory via the bridge's memory.read_u32 call, formats address and value as hex.
    case "dolphin_read32": return ok(`${addrHex(a())}: ${fmtHex(await dol.call<number>("memory.read_u32", [a()]))}`);
  • src/tools.ts:491-491 (registration)
    Registration of dolphin_read32 via CallToolRequestSchema handler dispatch (case switch at line 511).
    server.setRequestHandler(CallToolRequestSchema, async (req) => {
  • src/tools.ts:488-489 (registration)
    Registration of all tools (including dolphin_read32) via ListToolsRequestSchema from the TOOLS array.
    export function registerTools(server: Server, dol: DolphinClient): void {
      server.setRequestHandler(ListToolsRequestSchema, async () => ({ tools: TOOLS }));
  • Helper functions fmtHex and addrHex used by dolphin_read32 handler for formatting output.
    function fmtHex(n: number | bigint): string {
      return `${n} (0x${n.toString(16).toUpperCase()})`;
    }
Behavior5/5

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

With no annotations, the description fully discloses behavior: 'No side effects — pure read.', alignment requirement, error conditions (unmapped address, disconnect, FAIL), endianness handling, and memory mapping details (MEM1, MEM2, Hollywood I/O). It also explains pointer dereferencing and byte swap.

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 well-structured with labeled sections (PURPOSE, USAGE, BEHAVIOR, NOTES, RETURNS). It is front-loaded and every sentence adds essential information for an emulator memory reading 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 the complexity and lack of output schema, the description is exceptionally complete: it covers purpose, usage, behavior, alignment, error handling, memory map, endianness, and return format. No gaps are apparent.

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?

Schema coverage is 100% with a detailed address description. The description adds context beyond the schema, such as the byte swap helper behavior, pointer dereferencing notes, and memory map ranges. It provides slightly more value than the baseline 3.

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 states the exact action: reading an unsigned 32-bit big-endian value from PowerPC memory. It specifies the resource (32-bit value at absolute address) and distinguishes from sibling tools by mentioning use cases (timestamps, counters, colors, pointers) and referring to 8/16/64-bit variants.

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 explicitly says 'Use for timestamps, large counters, RGBA colors, full pointers' and 'For 8/16/64-bit values use the corresponding sibling.' It also provides alignment requirements and address ranges, giving clear when-to-use and implicit when-not-to-use 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/dmang-dev/mcp-dolphin'

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