MCP100 Assessment

Editorial verdict

Dagger-powered MCP server that gives coding agents isolated containerized development environments, logs and branch-based review workflows. Capabilities: Create isolated environments for coding agents; Run agent work in separate git branches; Inspect complete command history/logs; Intervene in an agent environment; Review/checkout resulting work

Reviewed October 21, 2026

Task Fit

Mapped

Cloud operations

Trust

Status warning

maintenance_source_health; tool_contract; install_supply_chain; advisory_freshness; adoption_evidence_presence

Maintenance

Date unavailable

No dated repository or package update is currently stored.

Popularity

Signals available

Visible usage signals are shown for discovery only, not as proof of safety.

Best for

Developers who want coding agents isolated from the primary working tree with observable, discardable environments.

Not ideal for

Users who need a broadly proven, low-risk, fully mature Recommended-grade integration today.

Avoid if

Avoid high-impact or sensitive production use unless the documented authentication, permissions, rollback, and data handling match your environment.

Trade-offs

The project explicitly states it is in early development and actively evolving.

Evidence scope

Evidence

Current source snapshot

Popularity

4.1k MCP repository stars

No MCP-specific package metric is stored

Repository identity: dagger/container-use

Stars observed October 21, 2026 · Downloads observed October 21, 2026

Repository evidence: exact. Exact current MCP implementation/distribution. Official repository says the project is in early development and actively evolving.

Package evidence: no_comparable_registry_package. Not MCP-specific/comparable for MCP-server adoption. No attributable public download metric was verified. Official repository says the project is in early development and actively evolving.

Maintenance

Publisher activity observed October 21, 2026

Current source snapshot

Trust review

Source relationship: First-party MCP

Reviewed October 21, 2026

Sources

GitHub repository ↗

Evidence-backed setup

Install & Agents

Choose your MCP client. A client connects to the MCP server; the language model is selected inside that client. Only stored, source-backed configurations are shown.

Claude Code

Transport not recorded

Publisher documented

Launch with `container-use stdio`.

The publisher provides client-specific setup instructions.

Verify safely: Verify the client establishes an MCP session and can enumerate the server's advertised capabilities before any high-impact action.

Uninstall and revoke

Remove or disable this MCP server entry from the client configuration; revoke OAuth/API credentials when the connection created or used dedicated credentials.

Evidence & methodology

Publisher-documented setup is not the same as MCP100 execution testing. “MCP100 logic checked” means the stored configuration shape was reviewed, not that third-party MCP software was run.

Evidence checked 2026-09-13T00:00:00Z

Evidence 1 ↗

Reviewed setup

Type-appropriate, source-backed setup for this mcp server profile.

Setup notes: Source rechecked October 21, 2026: Dagger Container Use MCP server and CLI Lifecycle: current active early development. Official repository says the project is in early development and actively evolving.

Read additional publisher installation details

From the publisher README

Publisher installation details

Original client setup and configuration retained from the publisher documentation.

View original README ↗

Publisher-documented clients

Claude CodeCursorGooseVS Code

These names appear in the publisher's installation documentation. MCP100-verified configurations are shown separately above when available.

Quick Start

Install

# macOS (recommended)
brew install dagger/tap/container-use

# All platforms
curl -fsSL https://raw.githubusercontent.com/dagger/container-use/main/install.sh | bash

Setup with Your Agent

Container Use works with any MCP-compatible agent. The setup is always the same: add container-use stdio as an MCP server.

👉 Complete setup guide for all agents (Cursor, Goose, VSCode, etc.)

Example with Claude Code:

# Add Container Use MCP server
cd /path/to/repository
claude mcp add container-use -- container-use stdio

# Add agent rules (optional)
curl https://raw.githubusercontent.com/dagger/container-use/main/rules/agent.md >> CLAUDE.md

The container-use command is also available as cu for convenience. Both commands work identically:

container-use stdio (used in documentation)
cu stdio (shortcut)

Loading optional publisher installation details…

Show source-catalog configuration

Launch with `container-use stdio`.

Capability

What it does

Dagger-powered MCP server that gives coding agents isolated containerized development environments, logs and branch-based review workflows. Capabilities: Create isolated environments for coding agents; Run agent work in separate git branches; Inspect complete command history/logs; Intervene in an agent environment; Review/checkout resulting work

Cloud & DevOpsSoftware & Technology

Representative uses

Developers who want coding agents isolated from the primary working tree with observable, discardable environments.

Important limits

Users who need a broadly proven, low-risk, fully mature Recommended-grade integration today.

Context Footprint

Not measured yet

Estimated token footprint of the MCP tool schemas exposed to the agent.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Local MCP transport does not imply hosted authentication; access to container/Dagger infrastructure is deployment-defined.
Permissions: Agents can run code and shell operations inside provisioned environments and create git branches; host/container boundary strength depends on the runtime configuration.
Data handling: Source code, commands and logs are stored in the local/container development environment and exposed to the AI client.
Cost: Open-source; local/remote container infrastructure and model providers may incur costs.
Risk and cautions: The project explicitly states it is in early development and actively evolving.

Related reviewed MCPs

Other options

Terraform MCP

MCP100 Recommended

Connect compatible AI clients to HashiCorp's documented MCP capabilities.

Choose this instead if

Choose Terraform MCP instead if connect compatible AI clients to HashiCorp's documented MCP capabilities.

Recommended after reviewed Batch 1 correction: exact 61-tool contract closes the prior formal Recommended gap.

Compare with Container Use View Terraform MCP details

Azure MCP Server

MCP100 Recommended

Connect agents to Azure resources and more than forty Azure services.

Choose this instead if

Choose Azure MCP Server instead if discovering and inspecting resources across supported Azure services.

Connect agents to Azure resources and more than forty Azure services.

Compare with Container Use View Azure MCP Server details

Cloudflare MCP

MCP100 Recommended

Access supported Cloudflare developer platform capabilities.

Choose this instead if

Choose Cloudflare MCP instead if searching and executing supported Cloudflare API operations across Workers, DNS, R2, Zero Trust, and related products.

Access supported Cloudflare developer platform capabilities.

Compare with Container Use View Cloudflare MCP details

Read publisher documentation

Publisher documentation

Publisher README

Original product, capability, tool, and usage documentation from the MCP publisher. Installation sections appear under Install & Agents.

View original README ↗

Container Use lets coding agents do their work in parallel environments without getting in your way. Go from babysitting one agent at a time to enabling multiple agents to work safely and independently with your preferred stack. See the full documentation.

It's an open-source MCP server that works as a CLI tool with Claude Code, Cursor, and other MCP-compatible agents. Powered by Dagger.

📦 Isolated Environments: Each agent gets a fresh container in its own git branch - run multiple agents without conflicts, experiment safely, discard failures instantly.
👀 Real-time Visibility: See complete command history and logs of what agents actually did, not just what they claim.
🚁 Direct Intervention: Drop into any agent's terminal to see their state and take control when they get stuck.
🎮 Environment Control: Standard git workflow - just git checkout <branch_name> to review any agent's work.
🌎 Universal Compatibility: Works with any agent, model, or infrastructure - no vendor lock-in.

🦺 This project is in early development and actively evolving. Submit issues and/or reach out to us on Discord in the #container-use channel.

Try It

Ask your agent to create something:

Create a hello world app in python using flask

Your agent will work in an isolated environment and give you URLs to view the app and explore the code!

Loading optional publisher documentation…

FAQ

Is this an official MCP?

github:dagger is listed as First-party MCP in MCP100’s current evidence.

Current official resources:

Publisher documentation ↗