longhorn-mcpSAFE
MCP server for the Longhorn distributed storage manager API — full read/write coverage of volumes, snapshots, backups, nodes, and more, with a --read-only mode, stdio + Streamable HTTP transports, and an official Helm chart.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An MCP server for the Longhorn distributed storage manager API. Full read/write coverage of Longhorn's REST API (volumes, snapshots, backups, backing images, nodes, settings, engine images, recurring jobs, and more), a --read-only mode, both stdio and Streamable HTTP transports, and an official Helm chart.
AI-assisted development. The majority of this codebase — implementation, tests, and this documentation — was written with AI assistance (Claude). Review accordingly, especially before running write-mode tools against a production Longhorn cluster.
Quick start
npx -y longhorn-mcp --longhorn-url=http://:9500
Longhorn's manager API is unauthenticated — reachability is the only access control. If you're not running this against an in-cluster Longhorn (see Connecting popular MCP clients → Remote/HTTP), you'll need a VPN, SSH tunnel, or kubectl port-forward svc/longhorn-backend 9500:9500 to reach it safely. Never expose Longhorn's manager API directly to an untrusted network.
CLI reference
4097b4ea1769OBSERVED · 2026-10-11Connect
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.
claude mcp add longhorn-mcp -- npx -y [email protected]
Trust 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
- declared (2 observation(s))
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
.helmignore
CLAUDE.md
assert.throws(() => inputSchema.parse({ method: 'GET', path: '/v1/volumes/../../etc/passwd' }), /\/v1\//);@modelcontextprotocol/node, @modelcontextprotocol/server, zod
Gates applied: no_behavioural_pass.
4097b4ea1769full audit observations/trust-audit/mcp-server/rafaelgaspar__longhorn-mcp.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 |
|---|---|---|---|---|---|
| 2026-10-11 | 4097b4ea1769 | SAFE | B | 89 | first audit |
Questions
What is the longhorn-mcp MCP server?
MCP server for the Longhorn distributed storage manager API — full read/write coverage of volumes, snapshots, backups, nodes, and more, with a --read-only mode, stdio + Streamable HTTP transports, and an official Helm chart.
Is longhorn-mcp 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 longhorn-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does longhorn-mcp run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as longhorn-mcp at 0.1.8.
How current is this page?
The grade is for one exact copy of the source (4097b4ea1769), read on 2026-10-11. The repository is watched and re-audited when it changes.