mcp-dockhand
MCP Server for Dockhand Docker Management - exposes 130+ API endpoints as MCP tools
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
strausmann
Source: Glama · also listed on github_repo_search
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
LOG_LEVELerror, warn, info or debug. debug adds one line per Dockhand request (method, endpoint template, status, duration). For requests through the client the duration spans the full response body and a bytes body-size field is added; the login and self-check probes (which bootstrap the client and so can't route through it) log time-to-headers without a bytes field. Never a path segment or a parameter value. An unrecognised value warns and falls back to info.MCP_BUILD_DATEMCP_GIT_SHAMCP_HOSTListen address. Kept as the wildcard address by default so the published Docker port (-p 8080:8080 / docker-compose.yml) keeps working; see [Securing the transport](#securing-the-transport) for the recommended way to protect the endpoint instead of binding loopback-onlyMCP_PORTPort for the MCP serverMCP_SERVER_VERSIONTRUSTED_PROXIESComma-separated addresses or CIDRs allowed to set X-Forwarded-For / X-Real-IP, e.g. 10.0.0.0/8, 100.64.0.0/10. Empty means the headers are ignored and the peer address is used.VITESTTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
357/357 tools missing one or more hints — get_audit_log (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_audit_events (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_audit_users (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +354 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool inputs are validated
355/357 tool handlers declare input schemas (99%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool test coverage
164/357 tools referenced in tests (46%)
Write tests that reference each tool by name so every tool has at least one test.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/strausmann/mcp-dockhand)?variant=verified to the badge URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check