Files
mcp-server/spark_executor/server.py
T
Claude ff9dea0ba7 feat: log MCP tool list + descriptions on startup
main.py lifespan now enumerates every MCP tool with its description at
startup so operators can see at a glance what the server exposes.

The auto-generated '### Responses:' suffix that fastapi-mcp appends to
each tool description is truncated before logging to keep the startup
log scannable.

Docstrings added to all 12 route handlers in server.py so the MCP tool
descriptions are meaningful (without them, fastapi-mcp would emit empty
descriptions). Each route now carries a summary + description used by
the auto-generated OpenAPI schema.
2026-06-24 17:50:30 +08:00

204 lines
6.3 KiB
Python

# coding=utf-8
"""
@Time :2026/6/24
@Author :tao.chen
"""
from fastapi import FastAPI, Request
from fastapi.responses import JSONResponse
from spark_executor.tools.connections import (
delete_connection,
get_connection,
list_connections,
save_connection,
)
from spark_executor.tools.kill import kill_job
from spark_executor.tools.logs import get_job_logs
from spark_executor.tools.requests import (
ConnectionNameRequest,
EmptyRequest,
GetJobLogsRequest,
JobIdRequest,
PendingIdRequest,
PrepareSubmitJobRequest,
SaveConnectionRequest,
)
from spark_executor.tools.status import get_job_status
from spark_executor.tools.submit import (
cancel_pending_job,
confirm_submit_job,
get_pending_job,
list_pending_jobs,
prepare_submit_job,
)
app = FastAPI(title="Spark Executor MCP", version="0.0.1", description="Spark Executor MCP Server")
# --- Exception handlers: translate tool-layer errors into proper HTTP statuses ---
#
# Tool functions raise KeyError for "unknown id" (job_id, pending_id, connection
# name) and ValueError for invalid state transitions (e.g. confirming a
# CANCELLED pending). Without these handlers FastAPI would map them to a bare
# 500 "Internal Server Error" which is useless to MCP clients.
@app.exception_handler(KeyError)
async def _keyerror_handler(_request: Request, exc: KeyError) -> JSONResponse:
return JSONResponse(status_code=404, content={"detail": str(exc)})
@app.exception_handler(ValueError)
async def _valueerror_handler(_request: Request, exc: ValueError) -> JSONResponse:
return JSONResponse(status_code=400, content={"detail": str(exc)})
@app.get("/health")
def health_check():
return {"status": "ok"}
# MCP tool routes. fastapi-mcp discovers these and registers them as MCP tools.
# Each route takes a single Pydantic body model so tools/call (which sends args
# as JSON body) works for every tool, including those with dict-typed params
# like spark_conf.
# --- Pending submission flow (two-step submit) ---
@app.post(
"/prepare_submit_job",
summary="Prepare a Spark job submission (no spark-submit yet)",
description=(
"Snapshot the named Connection's master / deploy_mode / spark_conf / "
"yarn_rm_url into a PendingSubmission record and persist it. "
"Does NOT invoke spark-submit. Returns pending_id for use with "
"confirm_submit_job (the user-second-confirmation step)."
),
)
def _prepare_submit_job(req: PrepareSubmitJobRequest):
return prepare_submit_job(**req.model_dump())
@app.post(
"/confirm_submit_job",
summary="Confirm and submit a previously-prepared job",
description=(
"Actually invoke spark-submit for the PendingSubmission identified "
"by pending_id. Requires status=PENDING. On success, transitions the "
"pending entry to SUBMITTED and creates a Job record. On failure, "
"marks the entry FAILED and re-raises."
),
)
def _confirm_submit_job(req: PendingIdRequest):
return confirm_submit_job(pending_id=req.pending_id)
@app.post(
"/list_pending_jobs",
summary="List all pending submissions",
description="Return every PendingSubmission in any status (PENDING, SUBMITTED, CANCELLED, FAILED).",
)
def _list_pending_jobs(_req: EmptyRequest = EmptyRequest()):
return list_pending_jobs()
@app.post(
"/get_pending_job",
summary="Get a single pending submission",
description="Return the PendingSubmission identified by pending_id, including its current status and outcome fields.",
)
def _get_pending_job(req: PendingIdRequest):
return get_pending_job(req.pending_id)
@app.post(
"/cancel_pending_job",
summary="Cancel a pending submission",
description=(
"Flip a PENDING (or already-CANCELLED) PendingSubmission to CANCELLED. "
"Refuses to cancel entries that are SUBMITTED or FAILED — those are "
"terminal and must be killed via kill_job instead."
),
)
def _cancel_pending_job(req: PendingIdRequest):
return cancel_pending_job(req.pending_id)
# --- Spark job tools ---
@app.post(
"/get_job_status",
summary="Query YARN for a job's current status",
description=(
"Return the YARN application state (RUNNING / SUCCEEDED / FAILED / "
"KILLED / ACCEPTED / NEW / NEW_SAVING / SUBMITTED / etc.) plus the "
"raw YARN REST response body."
),
)
def _get_job_status(req: JobIdRequest):
return get_job_status(req.job_id)
@app.post(
"/get_job_logs",
summary="Fetch aggregated container logs for a job",
description=(
"Pull aggregated logs from the YARN ResourceManager. Returns the last "
"tail_chars characters (default 5000). Requires yarn.log-aggregation-enable "
"to be true on the target cluster."
),
)
def _get_job_logs(req: GetJobLogsRequest):
return get_job_logs(req.job_id, tail_chars=req.tail_chars)
@app.post(
"/kill_job",
summary="Kill a running job",
description="PUT state=KILLED to YARN REST API for the job's application_id.",
)
def _kill_job(req: JobIdRequest):
return kill_job(req.job_id)
# --- Connection management tools ---
@app.post(
"/save_connection",
summary="Save or update a named Spark connection",
description=(
"Upsert a Connection record (master URL, deploy mode, optional YARN RM URL, "
"spark_conf K/V) keyed by name. Used by prepare_submit_job via the "
"connection parameter."
),
)
def _save_connection(req: SaveConnectionRequest):
# exclude_none so we don't overwrite the function's default with explicit None
return save_connection(**req.model_dump(exclude_none=True))
@app.post(
"/list_connections",
summary="List all saved Spark connections",
description="Return every Connection in the registry (model_dump form).",
)
def _list_connections(_req: EmptyRequest = EmptyRequest()):
return list_connections()
@app.post(
"/get_connection",
summary="Get a single connection by name",
description="Return the Connection record, or 404 if not found.",
)
def _get_connection(req: ConnectionNameRequest):
return get_connection(req.name)
@app.post(
"/delete_connection",
summary="Delete a saved connection",
description="Remove a Connection by name. 404 if not found.",
)
def _delete_connection(req: ConnectionNameRequest):
return delete_connection(req.name)