Docker (0xshariq) MCP Server
@0xshariq/docker-mcp-server
npm
v2.0.4
Published by @0xshariq — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
A comprehensive Model Context Protocol (MCP) server that provides Docker container and image management capabilities for AI assistants and automation tools. Includes 15 Docker operations + workflow combinations with complete CLI alias system, enhanced log
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 8 = 92. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −2 | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 20
high Tool "docker-compose" exposes command/code executionMTC-CAP-001
Tool "docker-compose" appears to run shell commands or evaluate code (parameter "command"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool docker-compose
high Tool "docker-exec" exposes command/code executionMTC-CAP-001
Tool "docker-exec" appears to run shell commands or evaluate code (keyword "exec" in tool name, parameter "command"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool docker-exec
high Tool "docker-dev" exposes command/code executionMTC-CAP-001
Tool "docker-dev" appears to run shell commands or evaluate code (parameter "command"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool docker-dev
high Shell/command execution in server code (bin/advanced/dbridge.js)MTC-SRC-002
In the server's implementation (`bin/advanced/dbridge.js:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: import { spawn } from 'child_process'; import { fileURLToPath } from 'url'; import path from 'path'; import chalk from
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/advanced/dbridge.js
high Shell/command execution in server code (bin/advanced/dclean.js)MTC-SRC-002
In the server's implementation (`bin/advanced/dclean.js:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: import { spawn } from 'child_process'; import { fileURLToPath } from 'url'; import path from 'path'; import chalk from
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/advanced/dclean.js
high Shell/command execution in server code (bin/advanced/dcompose.js)MTC-SRC-002
In the server's implementation (`bin/advanced/dcompose.js:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: spawn, execSync } from 'child_process'; import { fileURLToPath } from 'url'; import path from 'path'; import chalk from
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/advanced/dcompose.js
high Shell/command execution in server code (bin/advanced/ddev.js)MTC-SRC-002
In the server's implementation (`bin/advanced/ddev.js:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: import { spawn } from 'child_process'; import { fileURLToPath } from 'url'; import path from 'path'; import chalk from
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/advanced/ddev.js
high Shell/command execution in server code (bin/advanced/ddown.js)MTC-SRC-002
In the server's implementation (`bin/advanced/ddown.js:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: import { spawn } from 'child_process'; import { fileURLToPath } from 'url'; import path from 'path'; import chalk from
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/advanced/ddown.js
high Shell/command execution in server code (bin/advanced/dinspect.js)MTC-SRC-002
In the server's implementation (`bin/advanced/dinspect.js:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: import { spawn } from 'child_process'; import { fileURLToPath } from 'url'; import path from 'path'; import chalk from
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/advanced/dinspect.js
high Shell/command execution in server code (bin/advanced/dlist.js)MTC-SRC-002
In the server's implementation (`bin/advanced/dlist.js:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: import { spawn } from 'child_process'; import { fileURLToPath } from 'url'; import path from 'path'; import chalk from
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/advanced/dlist.js
high Shell/command execution in server code (bin/advanced/dlogin.js)MTC-SRC-002
In the server's implementation (`bin/advanced/dlogin.js:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: import { spawn } from 'child_process'; import { fileURLToPath } from 'url'; import path from 'path'; import chalk from
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/advanced/dlogin.js
high Shell/command execution in server code (bin/advanced/dlogout.js)MTC-SRC-002
In the server's implementation (`bin/advanced/dlogout.js:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: import { spawn } from 'child_process'; import { fileURLToPath } from 'url'; import path from 'path'; import chalk from
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/advanced/dlogout.js
high Shell/command execution in server code (bin/advanced/dnetwork.js)MTC-SRC-002
In the server's implementation (`bin/advanced/dnetwork.js:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: import { spawn } from 'child_process'; import { fileURLToPath } from 'url'; import path from 'path'; import chalk from
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server bin/advanced/dnetwork.js
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([docker-logs]) co-exist with external-action tools ([docker-compose, docker-exec, docker-dev]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [docker-logs] → sinks [docker-compose, docker-exec, docker-dev]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow docker-logs → docker-compose
medium Unconstrained command parameter "command" on "docker-compose"MTC-CAP-006
Tool "docker-compose" takes a command-shaped parameter "command" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool docker-compose · inputSchema.properties.command
medium Unconstrained command parameter "command" on "docker-exec"MTC-CAP-006
Tool "docker-exec" takes a command-shaped parameter "command" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool docker-exec · inputSchema.properties.command
medium Unconstrained command parameter "command" on "docker-dev"MTC-CAP-006
Tool "docker-dev" takes a command-shaped parameter "command" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool docker-dev · inputSchema.properties.command
low Mutating tool "docker-compose" declares no destructiveHintMTC-CAP-005
Tool "docker-compose" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool docker-compose
low Mutating tool "docker-exec" declares no destructiveHintMTC-CAP-005
Tool "docker-exec" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool docker-exec
low Mutating tool "docker-dev" declares no destructiveHintMTC-CAP-005
Tool "docker-dev" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool docker-dev
Tools 25
Each tool and what it can reach — statically extracted from the published source.
docker-composeruns code / shelldocker-devruns code / shelldocker-execruns code / shelldocker-logsingests untrusted inputdocker-bridgeno sensitive capabilitydocker-buildno sensitive capabilitydocker-cleanno sensitive capabilitydocker-containersno sensitive capabilitydocker-imagesno sensitive capabilitydocker-inspectno sensitive capability
Show 15 more tools ↓
docker-listno sensitive capabilitydocker-loginno sensitive capabilitydocker-logoutno sensitive capabilitydocker-mcp-serverno sensitive capabilitydocker-networkno sensitive capabilitydocker-pruneno sensitive capabilitydocker-publishno sensitive capabilitydocker-pullno sensitive capabilitydocker-removeno sensitive capabilitydocker-resetno sensitive capabilitydocker-restartno sensitive capabilitydocker-runno sensitive capabilitydocker-startno sensitive capabilitydocker-stopno sensitive capabilitydocker-volumeno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (25 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v2.0.4 latest |
A 92/100 | 20 | 1.13.0 | 2026-09-07 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @0xshariq/docker-mcp-server --onlineOther implementations of Docker 14
Independent packages implementing the same tool, scanned with the same engine. Compare all 15 side by side →
Community Docker server: manage containers, images, volumes and networks in natural language.
Lets AI agents interact with Docker containers locally or remotely via SSH, including container operations, logs, monitoring, and cleanup.
Universal Docker MCP server for AI assistants (Cursor, Claude Desktop)
MCP server for Docker CLI integration - 150 tools for containers, images, compose, volumes, networks, cleanup, observability, buildx, manifests, contexts, registry auth, Swarm orchestration, stacks, configs, secrets, content trust, Scout, plugins, and sys
MCP server for executing commands in Docker containers
Manages Docker containers, images, volumes, and Compose services from your IDE.
More in Cloud & DevOps
Operator control CLI for AdGuard Home with an MCP adapter
interacting with Aliyun (Alibaba Cloud) services through This MCP server provides tools.
MCP server for the Aspro.Cloud REST API
MCP server for Atlassian Confluence and Jira Cloud APIs
AuroraCloud-first MCP server that exposes AuroraDocs workspace data to Claude Desktop and other AI agents
The official AWS Knowledge Base retrieval server using Bedrock Agent Runtime.