Loading…
Deploys a GitHub repository to a live HTTPS URL directly from an AI coding tool.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 7 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The dockhold MCP server exposes 12 tools, focused primarily on developer and database capabilities. Its published description reads: "Deploys a GitHub repository to a live HTTPS URL directly from an AI coding tool". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates dockhold F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check dockhold's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add dockhold to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://api.dockhold.eu/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
List the apps in your Dockhold account, with each app's id, status, URL, and source repo. Call this first whenever the user asks about their apps, or when you need an app_id for any other tool.
Get detailed status for one app: deploy status, URL, last deployed commit, and any error message. Call this to check whether a deploy has finished, to get an app's live URL, or to see why an app is in
Get the most recent runtime logs for one app. Call this when an app is crashing, returning errors, or a deploy succeeded but the app misbehaves: the logs usually name the cause.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: deploy_app
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "repo_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: deploy_app
A tool description tries to alter the model’s use of another tool.
matically; poll get_app_status to watch it. This tool needs a GitHub repo URL:RecommendationDescriptions must describe only their own tool.
tool: get_resource_usage
The text tells the model WHEN to call this tool relative to others ("always call first", "before any other tool", "chain to X tool") — a toxic-flow injection that hijacks the agent’s orchestration rather than describing the tool.
size. Call this before any resize tool (the allowed sizes come from its steps fields),RecommendationTool metadata must describe only the tool, never sequence the agent’s calls.
tool: resize_app
A tool description tries to alter the model’s use of another tool.
ne of the sizes get_resource_usage reports under compute.steps_mb, and the new sizRecommendationDescriptions must describe only their own tool.
tool: resize_database
A tool description tries to alter the model’s use of another tool.
ne of the sizes get_resource_usage reports under db_ram.steps_mb and fit your dataRecommendationDescriptions must describe only their own tool.
tool: resize_database_storage
A tool description tries to alter the model’s use of another tool.
ne of the sizes get_resource_usage reports under storage.steps_gb and fit your stoRecommendationDescriptions must describe only their own tool.
tool: list_github_repos
A tool description tries to alter the model’s use of another tool.
all this before deploy_app when the target repo is private, or when the usRecommendationDescriptions must describe only their own tool.
tool: deploy_group
A tool description tries to alter the model’s use of another tool.
parallel; poll get_app_status with each returned app_id.RecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Deploy a GitHub repository as a live web app on Dockhold. Call this when the user wants to put an app online, get a shareable HTTPS URL, or host a demo. Returns the new app id. Two paths: a PUBLIC rep
Restart an existing app (rolling restart with zero downtime). Call this after changing configuration, or to recover an app that is stuck or misbehaving. It reruns the current build; it does not pull n
Set a single environment variable on an app and roll it out. Call this when an app needs plain configuration such as LOG_LEVEL or a feature flag. For secrets (API keys, passwords, tokens) use the Secr
Show your account's compute, database-RAM, and storage pools: how much you've bought, how much is used, and how much is free, plus every app's current size. Call this before any resize tool (the allow
Change how much memory one app gets. Call this when an app is running out of memory (OOM) or the user asks to make an app bigger or smaller. memory_mb must be one of the sizes get_resource_usage repor
Change how much memory an app's managed database gets. Call this when the database is slow or out of memory. db_ram_mb must be one of the sizes get_resource_usage reports under db_ram.steps_mb and fit
Grow the disk of an app's managed database. Call this when the database is running out of disk space. GROW-ONLY: you can increase storage but never shrink it. storage_gb must be one of the sizes get_r
List the GitHub repositories you have connected to Dockhold, across every installation. Call this before deploy_app when the target repo is private, or when the user asks which repos they can deploy.
Deploy several connected services in one go (e.g. a frontend + an API). Call this when the user's project is split across multiple repos that must talk to each other; for a single repo use deploy_app.