superset-mcp

Provides an MCP server that lets AI agents interact with an Apache Superset instance (manage dashboards/charts/datasets/tags and run/inspect SQL Lab queries) via a set of MCP tools.

Evaluated Mar 30, 2026 (21d ago)

Repo ↗ Ai Ml ai-ml devtools infrastructure api mcp analytics superset

⚙ 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

README states credentials are stored locally in .env and access token is stored in .superset_token. Tool-driven actions can modify/delete Superset resources, so least-privilege and agent call restrictions are important. TLS enforcement and secure token transport/storage hardening are not described in the provided content; rate limiting and detailed auth error handling are not documented.

⚡ Reliability

Uptime/SLA

Version Stability

Breaking Changes

Error Recovery

Best When

You control both the MCP runtime and the Superset instance, and you want agents to automate Superset metadata and SQL Lab tasks.

Avoid When

You cannot restrict agent permissions or audit/monitor tool calls; or you require well-specified operational behaviors (retries, pagination, rate limits) to be documented.

Use Cases

• Agent-assisted Superset administration (list/create/update/delete dashboards and charts)
• Programmatic dataset and database connection management
• Natural-language-driven SQL Lab querying and saved query workflows
• Metadata exploration (databases, catalogs, functions, related objects, tags, recent activity)
• Dynamic chart exploration artifact creation (form data/permalinks)

Not For

• High-security environments without additional hardening/review (the tooling enables destructive operations like deletes)
• Untrusted agent execution where tool calls could be used to exfiltrate/modify business data
• Production setups without TLS and careful secret/token management
• Use cases requiring strict guarantees around idempotency, pagination, or retry safety (not documented)

Interface

REST API

GraphQL

gRPC

MCP Server

Yes

SDK

Webhooks

Authentication

Methods: Authenticate with Superset (via MCP tool superset_auth_authenticate_user) Check token validity (superset_auth_check_token_validity) Refresh token (superset_auth_refresh_token)

OAuth: No Scopes: No

Auth is configured via SUPERSET_USERNAME and SUPERSET_PASSWORD and then an access token is managed/stored locally (per README: .superset_token). No explicit scope granularity is described.

Pricing

Free tier: No

Requires CC: No

Open-source (MIT) library; costs are primarily your infrastructure/LLM usage and any Superset hosting.

Agent Metadata

Pagination

none

Idempotent

False

Retry Guidance

Not documented

Known Gotchas

⚠ Tools include destructive operations (e.g., delete dashboards/charts/tags); agents should be constrained with permissions and guarded prompts/approval flows.
⚠ Token is stored locally in .superset_token; ensure secure local handling and cleanup for shared environments.
⚠ No documented behavior for pagination, rate limiting, retries, or idempotency—agents may need defensive handling.

Alternatives

Direct Apache Superset REST API calls from your own application Superset Python client / custom scripts using Superset APIs Other Superset integration/connectors that provide SDKs or typed APIs

Full Evaluation Report

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

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 2026-03-30.