Remove MCP server from project

- Delete mcp_server.py
- Remove MCP startup from __main__.py
- Remove process_mcp_transcribe_task from tasks.py
- Clean MCP references from README.md

README.md

@@ -7,7 +7,6 @@ ScrAIbe is a transcription and summarization service that:
 - Provides:
   - A web GUI for uploading audio and receiving transcripts via email.
   - A CLI and Python API for direct integration.
-  - An MCP-style HTTP API (OpenAPI) for LLMs and external systems.
   - A watch-folder mode for automatic transcription, summarization, and email delivery.
 
 No local speech models or heavy dependencies are required. ScrAIbe is designed as a thin client in front of your own AI services.
@@ -35,13 +34,6 @@ For more information: https://apstrom.ca
     - Final transcript (MD + DOCX + JSON) when ready.
     - Summary as MD + DOCX (if requested).
     - Error notification if processing fails.
-- MCP-style HTTP API (optional):
-  - Exposes an OpenAPI-compliant REST endpoint for external LLMs or services.
-  - Allows:
-    - Audio upload for transcription.
-    - Job status checks.
-    - Retrieval of transcript JSON (no summary).
-  - Enabled via MCP_SERVER_ENABLED=true.
 - Watch-folder mode (optional):
   - Monitors a directory for audio files.
   - For each file:
@@ -81,7 +73,6 @@ For more information: https://apstrom.ca
     - Output formatting (e.g., .md with transcript + summary)
   - Runs:
     - Web GUI (Gradio) – always enabled
-    - MCP-style HTTP API (FastAPI) – optional
     - Watch-folder mode – optional
     - Celery worker (async processing)
     - Redis (in-container by default)
@@ -233,19 +224,6 @@ Accent color (UI and emails):
     - Email headings, links, and email addresses
   - Default: #7C6DA0
 
-MCP-style HTTP API:
-
-- MCP_SERVER_ENABLED:
-  - Enable MCP-style HTTP API (default: false).
-  - Values: true/false.
-- MCP_SERVER_HOST:
-  - Bind address (default: 0.0.0.0).
-- MCP_SERVER_PORT:
-  - Port (default: 8000).
-- MCP_USE_CELERY:
-  - Use Celery for async transcription (default: true).
-  - If false, transcription runs in-process.
-
 Watch-folder mode:
 
 - WATCH_ENABLED:
@@ -355,8 +333,6 @@ Core runtime dependencies:
 - celery[redis]
 - redis
 - python-docx
-- fastapi
-- uvicorn
 - ffmpeg (for audio preprocessing)
 
 No local Whisper, PyTorch, or Pyannote models are required.

scraibe/__main__.py

@@ -5,12 +5,9 @@ Entrypoint for running ScrAIbe as a module:
 
 Always launches the Web GUI (Gradio).
 Optionally launches:
-- MCP-style API server
 - Watch-folder mode
 """
 
-import os
-import threading
 import logging
 
 logger = logging.getLogger("scraibe.__main__")
@@ -18,35 +15,7 @@ logger = logging.getLogger("scraibe.__main__")
 from .webui import create_app
 
 
-def _run_mcp_server():
-    """
-    Run MCP server in a separate thread.
-    """
-    import uvicorn
-    from . import mcp_server
-
-    host = os.getenv("MCP_SERVER_HOST", "0.0.0.0")
-    port = int(os.getenv("MCP_SERVER_PORT", "8000"))
-
-    uvicorn.run(
-        mcp_server.app,
-        host=host,
-        port=port,
-        log_level="info",
-    )
-
-
 if __name__ == "__main__":
-    # Optionally start MCP server in background (non-blocking)
-    mcp_enabled = os.getenv("MCP_SERVER_ENABLED", "false").strip().lower() in ("true", "1", "yes")
-    if mcp_enabled:
-        try:
-            t = threading.Thread(target=_run_mcp_server, daemon=True)
-            t.start()
-            logger.info("MCP server started in background.")
-        except Exception as e:
-            logger.warning("Failed to start MCP server (WebUI will continue): %s", e)
-
     # Optionally start watch-folder mode (non-blocking)
     try:
         from .watcher import start_watcher

scraibe/mcp_server.py

@@ -1,304 +0,0 @@
-"""
-MCP-style HTTP server for ScrAIbe.
-
-- Exposes an OpenAPI-compliant endpoint for external LLMs to:
-  - Submit audio (as base64, URL, or internal path) via JSON.
-  - Receive transcript JSON (no summary).
-- WebUI remains always enabled; this is additive.
-
-Configuration (env):
-- MCP_SERVER_ENABLED: "true"/"false" (default: false)
-- MCP_SERVER_HOST: bind address (default: 0.0.0.0)
-- MCP_SERVER_PORT: port (default: 8000)
-- MCP_USE_CELERY: "true"/"false" (default: true)
-  - If true, uses Celery tasks; if false, runs synchronously.
-"""
-
-import os
-import time
-import uuid
-import base64
-import logging
-from typing import Optional
-
-import httpx
-from fastapi import FastAPI, HTTPException
-from pydantic import BaseModel, Field
-
-from .autotranscript import Scraibe
-
-logger = logging.getLogger("scraibe.mcp_server")
-
-app = FastAPI(
-    title="ScrAIbe MCP Transcription API",
-    version="0.1.0",
-    description=(
-        "MCP-style HTTP API for ScrAIbe. "
-        "Allows external LLMs to submit audio and receive transcript JSON."
-    ),
-    openapi_tags=[
-        {"name": "transcription", "description": "Transcription endpoints"}
-    ],
-)
-
-# In-memory job store for MCP (simple; can be replaced with Redis later)
-_mcp_jobs: dict = {}
-
-
-class TranscribeRequest(BaseModel):
-    """
-    Input for transcription.
-
-    Exactly one of audio_base64, audio_url, or audio_path must be provided.
-    """
-    audio_base64: Optional[str] = Field(
-        None,
-        description="Base64-encoded audio file content."
-    )
-    audio_url: Optional[str] = Field(
-        None,
-        description="Public URL to the audio file."
-    )
-    audio_path: Optional[str] = Field(
-        None,
-        description="Internal file path on the server (for internal use only)."
-    )
-
-
-class TranscribeResponse(BaseModel):
-    job_id: str
-    status: str
-    message: str
-
-
-class JobStatusResponse(BaseModel):
-    job_id: str
-    status: str
-    message: str
-
-
-class TranscriptJSONResponse(BaseModel):
-    job_id: str
-    transcript: str
-    segments: list
-
-
-def _job_id() -> str:
-    return str(uuid.uuid4())
-
-
-def _save_audio_from_request(req: TranscribeRequest) -> str:
-    """
-    Save audio to a temporary file from base64, URL, or path.
-    Returns the local file path.
-    """
-    upload_dir = os.getenv("SCRAIBE_UPLOAD_DIR", "/tmp/scraibe_uploads")
-    os.makedirs(upload_dir, exist_ok=True)
-
-    if req.audio_base64:
-        try:
-            data = base64.b64decode(req.audio_base64)
-        except Exception as e:
-            raise HTTPException(status_code=400, detail=f"Invalid base64 audio: {e}")
-
-        ts = time.strftime("%Y%m%d%H%M%S")
-        tmp_name = f"mcp_upload_{ts}_{uuid.uuid4().hex[:8]}.wav"
-        file_path = os.path.join(upload_dir, tmp_name)
-        with open(file_path, "wb") as f:
-            f.write(data)
-        return file_path
-
-    if req.audio_url:
-        try:
-            with httpx.stream("GET", req.audio_url, timeout=60) as resp:
-                if resp.status_code != 200:
-                    raise HTTPException(
-                        status_code=400,
-                        detail=f"Failed to download audio from URL: {resp.status_code}",
-                    )
-                ts = time.strftime("%Y%m%d%H%M%S")
-                tmp_name = f"mcp_url_{ts}_{uuid.uuid4().hex[:8]}.wav"
-                file_path = os.path.join(upload_dir, tmp_name)
-                with open(file_path, "wb") as f:
-                    for chunk in resp.iter_bytes():
-                        f.write(chunk)
-            return file_path
-        except HTTPException:
-            raise
-        except Exception as e:
-            raise HTTPException(status_code=400, detail=f"Error downloading audio: {e}")
-
-    if req.audio_path:
-        path = req.audio_path
-        if not os.path.isfile(path):
-            raise HTTPException(status_code=400, detail="audio_path does not exist")
-        return path
-
-    raise HTTPException(
-        status_code=400,
-        detail="Provide exactly one of: audio_base64, audio_url, or audio_path",
-    )
-
-
-@app.get("/health", tags=["transcription"])
-async def health():
-    return {"status": "ok"}
-
-
-@app.post(
-    "/transcribe",
-    tags=["transcription"],
-    operation_id="transcribe",
-    response_model=TranscribeResponse,
-)
-async def transcribe(req: TranscribeRequest):
-    """
-    Submit an audio file for transcription.
-
-    Input (JSON body):
-      - audio_base64: base64-encoded audio file
-      - audio_url: URL to audio file
-      - audio_path: local file path (for internal use)
-
-    Returns:
-      {
-        "job_id": "<id>",
-        "status": "queued" | "processing",
-        "message": "..."
-      }
-
-    Use GET /transcribe/{job_id}/status and /json to retrieve results.
-    """
-    use_celery = os.getenv("MCP_USE_CELERY", "true").strip().lower() in ("true", "1", "yes")
-
-    # Save audio to a temporary file
-    try:
-        file_path = _save_audio_from_request(req)
-    except HTTPException:
-        raise
-    except Exception as e:
-        logger.error("Error saving MCP upload: %s", e)
-        raise HTTPException(status_code=500, detail=f"Error saving file: {e}")
-
-    job_id = _job_id()
-
-    if use_celery:
-        try:
-            from .tasks import process_mcp_transcribe_task
-        except ImportError:
-            # Fallback: run synchronously
-            use_celery = False
-
-        if use_celery:
-            try:
-                process_mcp_transcribe_task.delay(
-                    audio_path=file_path,
-                    job_id=job_id,
-                    language=None,
-                    num_speakers=None,
-                )
-            except Exception as e:
-                logger.error("Error enqueuing MCP job: %s", e)
-                _mcp_jobs[job_id] = {
-                    "status": "error",
-                    "message": f"Error enqueuing job: {e}",
-                    "file_path": file_path,
-                }
-                return TranscribeResponse(
-                    job_id=job_id,
-                    status="error",
-                    message=_mcp_jobs[job_id]["message"],
-                )
-
-            _mcp_jobs[job_id] = {
-                "status": "queued",
-                "message": "Job queued for processing.",
-                "file_path": file_path,
-            }
-            return TranscribeResponse(
-                job_id=job_id,
-                status="queued",
-                message=_mcp_jobs[job_id]["message"],
-            )
-
-    # Synchronous path
-    _mcp_jobs[job_id] = {
-        "status": "processing",
-        "message": "Transcription started (synchronous).",
-        "file_path": file_path,
-    }
-
-    def _run_sync():
-        try:
-            scraibe = Scraibe(verbose=False)
-            result = scraibe.transcribe(
-                audio_file=file_path,
-                language=None,
-                num_speakers=None,
-                verbose=False,
-                for_export=True,
-            )
-            transcript_text = result.get("transcript", "")
-            segments = result.get("segments", [])
-            _mcp_jobs[job_id]["status"] = "completed"
-            _mcp_jobs[job_id]["transcript"] = transcript_text
-            _mcp_jobs[job_id]["segments"] = segments
-            _mcp_jobs[job_id]["message"] = "Transcription completed."
-        except Exception as e:
-            logger.error("MCP sync transcription error: %s", e)
-            _mcp_jobs[job_id]["status"] = "error"
-            _mcp_jobs[job_id]["message"] = f"Transcription error: {e}"
-
-    import threading
-    t = threading.Thread(target=_run_sync, daemon=True)
-    t.start()
-
-    return TranscribeResponse(
-        job_id=job_id,
-        status="processing",
-        message=_mcp_jobs[job_id]["message"],
-    )
-
-
-@app.get(
-    "/transcribe/{job_id}/status",
-    tags=["transcription"],
-    operation_id="get_status",
-    response_model=JobStatusResponse,
-)
-async def get_status(job_id: str):
-    job = _mcp_jobs.get(job_id)
-    if not job:
-        raise HTTPException(status_code=404, detail="Job not found")
-    return JobStatusResponse(
-        job_id=job_id,
-        status=job["status"],
-        message=job.get("message", ""),
-    )
-
-
-@app.get(
-    "/transcribe/{job_id}/json",
-    tags=["transcription"],
-    operation_id="get_json",
-    response_model=TranscriptJSONResponse,
-)
-async def get_json(job_id: str):
-    job = _mcp_jobs.get(job_id)
-    if not job:
-        raise HTTPException(status_code=404, detail="Job not found")
-
-    if job["status"] != "completed":
-        raise HTTPException(
-            status_code=400,
-            detail=f"Job not completed. Current status: {job['status']}",
-        )
-
-    transcript_text = job.get("transcript", "")
-    segments = job.get("segments", [])
-
-    return TranscriptJSONResponse(
-        job_id=job_id,
-        transcript=transcript_text,
-        segments=segments,
-    )

scraibe/tasks.py

@@ -506,71 +506,6 @@ def process_transcription_task(
         logger.info("Cleanup completed for job %s.", task_id)
 
 
-@celery_app.task(
-    name="scraibe.tasks.process_mcp_transcribe_task",
-    bind=True,
-    max_retries=1,
-    task_time_limit=14400,
-    task_soft_time_limit=13500,
-)
-def process_mcp_transcribe_task(
-    self,
-    audio_path: str,
-    job_id: str,
-    language: str,
-    num_speakers: int,
-):
-    """
-    Async task used by MCP-style API:
-    - Transcribe audio
-    - Store transcript + segments in shared MCP job store
-    - Clean up temporary file
-    """
-    from .mcp_server import _mcp_jobs
-
-    log_level = os.getenv("LOG_LEVEL", "INFO")
-    setup_logging(level=log_level)
-
-    # Initialize status
-    _mcp_jobs.setdefault(
-        job_id,
-        {
-            "status": "processing",
-            "message": "Transcription started (async).",
-            "file_path": audio_path,
-        },
-    )
-
-    try:
-        scraibe = Scraibe(verbose=True)
-        result = scraibe.transcribe(
-            audio_file=audio_path,
-            language=language or None,
-            num_speakers=int(num_speakers) if num_speakers else None,
-            verbose=True,
-            for_export=True,
-        )
-
-        transcript_text = result.get("transcript", "")
-        segments = result.get("segments", [])
-
-        _mcp_jobs[job_id]["status"] = "completed"
-        _mcp_jobs[job_id]["transcript"] = transcript_text
-        _mcp_jobs[job_id]["segments"] = segments
-        _mcp_jobs[job_id]["message"] = "Transcription completed."
-
-        logger.info("MCP job %s completed.", job_id)
-
-    except Exception as e:
-        logger.error("MCP job %s failed: %s", job_id, e, exc_info=True)
-        _mcp_jobs[job_id]["status"] = "error"
-        _mcp_jobs[job_id]["message"] = f"Transcription error: {e}"
-
-    finally:
-        _remove_file(audio_path)
-        logger.info("MCP job %s cleanup completed.", job_id)
-
-
 @celery_app.task(
     name="scraibe.tasks.process_watch_file_task",
     bind=True,