Apache Spark History Server MCP

Apache Spark History Server MCP enabling AI agents to query the Spark History Server — retrieving completed and running Spark job metadata, execution timelines, stage details, and task metrics — integrating Spark's job monitoring into agent-driven data engineering observability and pipeline debugging workflows.

Evaluated Mar 06, 2026 (0d ago) vcurrent
Homepage ↗ Repo ↗ Databases apache-spark spark-history big-data mcp-server data-engineering kubeflow
⚙ Agent Friendliness
72
/ 100
Can an agent use this?
🔒 Security
73
/ 100
Is it safe for agents?
⚡ Reliability
64
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
65
Documentation
68
Error Messages
65
Auth Simplicity
88
Rate Limits
85

🔒 Security

TLS Enforcement
78
Auth Strength
70
Scope Granularity
68
Dep. Hygiene
68
Secret Handling
80

Internal network. No built-in auth. Community MCP. Job data may be sensitive.

⚡ Reliability

Uptime/SLA
68
Version Stability
62
Breaking Changes
62
Error Recovery
65
AF Security Reliability

Best When

A data engineering team runs Apache Spark workloads and wants AI-assisted job monitoring and debugging — querying the History Server to understand job performance and failures.

Avoid When

You don't use Spark or need real-time active job monitoring rather than historical data.

Use Cases

  • Querying Spark job execution history from data engineering agents
  • Analyzing failed Spark job stages for debugging from troubleshooting agents
  • Monitoring Spark pipeline performance from data platform agents
  • Retrieving task-level execution metrics from performance analysis agents
  • Comparing job run times across Spark versions from benchmarking agents
  • Investigating data skew and bottlenecks from optimization agents

Not For

  • Teams not running Apache Spark jobs
  • Real-time Spark streaming monitoring (History Server shows completed jobs)
  • Spark job submission — this is read-only monitoring

Interface

REST API
Yes
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: none
OAuth: No Scopes: No

No authentication by default — Spark History Server typically runs on internal network. Configure network security for production deployments. Some clusters add authentication.

Pricing

Model: free
Free tier: Yes
Requires CC: No

Apache Spark is free open source. Community MCP is free. Spark compute infrastructure costs apply.

Agent Metadata

Pagination
offset
Idempotent
Full
Retry Guidance
Not documented

Known Gotchas

  • Spark History Server must be running and accessible
  • Job data retention is limited by History Server configuration
  • Large Spark clusters may have very large job histories — pagination important
  • Community MCP from individual contributor — niche data engineering tool
  • Spark History Server API version varies by Spark version
  • No authentication by default — ensure network-level security

Alternatives

Full Evaluation Report

Detailed scoring breakdown, competitive positioning, security analysis, and improvement recommendations for Apache Spark History Server MCP.

$99

Scores are editorial opinions as of 2026-03-06.

5220
Packages Evaluated
26151
Need Evaluation
173
Need Re-evaluation
Community Powered