レトロチップ音源（2A03 APU）風のMMLをLLMに作曲させるためのMCPサーバです https://git.takashi-2521.com/mml-composemusic-mcp.git/atom?h=v0.3.0 2026-09-13T05:13:04+00:00 2026-09-13T05:13:04+00:00 tanaka takashi isazaka@gmail.com 2026-09-13T05:12:41+00:00 urn:sha1:97b34627667fd699f4e0e054533eb89a205a2878 Replace the server-local wav_path result with a protocol-native multimedia response. - Split internal composition execution from MCP ToolResult serialization so filesystem paths never enter public payloads. - Return every successfully composed WAV as AudioContent with the audio/wav MIME type, regardless of file size. - Keep structured audio metadata, duration, note sequence, and validation details alongside the multimedia content. - Use CallToolResult.isError as the authoritative MCP execution status while retaining compose success and validate valid as domain fields. - Treat invalid compose/API requests and runtime failures as tool errors, while invalid MML discovered by validate remains a successful validation operation. - Sanitize synthesis, file-write, audio-serialization, and unexpected failure responses so internal paths and exception details are not exposed. - Add protocol-level coverage for base64 round trips, content block types, error semantics, ResourceLink absence, and path non-disclosure. - Update existing tests for the separated execution layer and path-free result contract. - Document AudioContent and isError behavior in the README, MCP schema, and design specification. - Require the tested FastMCP 3.4.4 API line and exclude the incompatible 4.x major version. Verification: 487 tests passed; ruff check passed; git diff --check passed; uv lock --check passed; and a manual MCP call returned TextContent plus AudioContent with no wav_path. 2026-07-11T10:02:14+00:00 tanaka takashi isazaka@gmail.com 2026-07-11T10:02:14+00:00 urn:sha1:ca35520338057512a71acd42bb116ffbb82cc192 - Add FastMCP server with compose_mml tool - Support ppmck and pyxel MML syntax - Add lexer and parsers for both formats - Add NES APU-style synthesizer (pulse/triangle/noise) to WAV - Add MML templates (basic/melody/chord/drum/empty) for both modes - Add tests for lexer, parser, and server - Support stdio, http, sse, streamable-http transports - Update README, pyproject.toml, and .gitignore