SupersetSAFE
MCP server for managing Apache Superset — 128+ tools for dashboards, charts, datasets, SQL Lab, access control
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://pypi.org/project/mcp-superset/) [](https://pypi.org/project/mcp-superset/) [](https://www.python.org/downloads/) [](https://opensource.org/licenses/MIT) [](https://github.com/bintocher/mcp-superset/actions/workflows/ci.yml) [](https://github.com/bintocher/mcp-superset/actions/workflows/codeql.yml)
[](https://superset.apache.org/) [](https://modelcontextprotocol.io/) [](https://peps.python.org/pep-0561/) [](https://github.com/astral-sh/ruff) [](https://github.com/astral-sh/uv) [](#available-tools-132) [](https://github.com/bintocher/mcp-superset)
A comprehensive Model Context Protocol (MCP) server for Apache Superset. Gives AI assistants (Claude, GPT, etc.) full control over your Superset instance — dashboards, charts, datasets, SQL Lab, users, roles, RLS, and more — through 137 tools.
Comparison w
845c9f39b1c2OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-superset --env SUPERSET_PASSWORD=${SUPERSET_PASSWORD} -- None mcp-superset==0.2.3Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (5)
.pre-commit-config.yaml
- Three access states: `1` (full access), `0` (no access), `"visible_no_data"` (can open dashboard but charts fail)
Treat the cookie as a credential: it grants full access to your Superset
- **Session-cookie authentication for SSO/OAuth instances.** Where Superset sits behind OAuth/OIDC/SAML, the REST login endpoint is unusable. Setting `SUPERSET_SESSION_COOKIE` (and `SUPERSET_SESSION_C
Gates applied: no_behavioural_pass.
845c9f39b1c2full audit observations/trust-audit/mcp-server/bintocher__superset-2.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 845c9f39b1c2 | SAFE | B | 89 | first audit |
Questions
What is the Superset MCP server?
MCP server for managing Apache Superset — 128+ tools for dashboards, charts, datasets, SQL Lab, access control
Is Superset safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Superset need?
It reads SUPERSET_AUTH_PROVIDER and SUPERSET_PASSWORD from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Superset run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as mcp-superset.
How current is this page?
The grade is for one exact copy of the source (845c9f39b1c2), read on 2026-10-08. The repository is watched and re-audited when it changes.