spark_history_mcp_server

Provides an MCP (SSE) server wrapper around an Apache Spark History Server, exposing tools to list and inspect Spark applications/jobs/stages/executors and to compare job environments/performance and identify bottlenecks.

Evaluated Apr 04, 2026 (17d ago)

Repo ↗ Ai Ml mcp spark history-server observability performance-debugging developer-tools sse

⚙ Agent Friendliness

/ 100

Can an agent use this?

🔒 Security

/ 100

Is it safe for agents?

⚡ Reliability

/ 100

Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality

Documentation

Error Messages

Auth Simplicity

Rate Limits

🔒 Security

TLS Enforcement

Auth Strength

Scope Granularity

Dep. Hygiene

Secret Handling

SSE endpoint is shown as plain http with localhost, and no auth/TLS/rate-limit guidance is documented. This increases risk if deployed beyond a trusted local network. Dependency hygiene and secret-handling practices are not verifiable from the provided README/metadata.

⚡ Reliability

Uptime/SLA

Version Stability

Breaking Changes

Error Recovery

Best When

You have access to a Spark History Server dataset and want an LLM agent to quickly explore Spark execution history via MCP tools.

Avoid When

You cannot access the History Server data or you need authenticated/secure-by-default access to the MCP endpoint for untrusted users.

Use Cases

• Diagnose Spark job performance issues using historical metrics (stages, executors, resource usage timelines).
• Compare two Spark jobs for environment or performance differences.
• Find slowest jobs/stages/SQL queries and inspect underlying execution details.

Not For

• Real-time streaming monitoring of currently running Spark applications (history server focus).
• Auditing or changing cluster configuration (appears read-only/inspection oriented).
• Production-grade multi-tenant service exposure without adding authentication/network protections.

Interface

REST API

GraphQL

gRPC

MCP Server

Yes ↗

SDK

Webhooks

Authentication

OAuth: No Scopes: No

No authentication method is described in the provided README. Assumes local/behind-trusted-network usage.

Pricing

Free tier: No

Requires CC: No

No pricing information provided (appears to be open-source/self-hostable).

Agent Metadata

Pagination

none

Idempotent

True

Retry Guidance

Not documented

Known Gotchas

⚠ README does not document parameter schemas, output formats, pagination, or limits for tools—agents may need trial-and-error.
⚠ No rate limit or timeout behavior is documented; long history queries could cause slow responses.
⚠ No auth details are provided; exposing the SSE endpoint publicly may be unsafe without additional controls.
⚠ Local URL example uses localhost; agents running remotely must ensure network reachability and correct configuration of application.yaml.

Alternatives

Use the Spark History Server UI directly. Build direct integrations against Spark History Server REST endpoints (if available) or parse history store metrics. Wrap the History Server with a custom REST API or GraphQL layer with proper auth and rate limiting.

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for spark_history_mcp_server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

API endpoint ↗ Agent guide ↗ Report inaccuracy

Scores are editorial opinions as of 2026-04-04.