Compatible with every major AI agent and IDE
What is the Dagger (Programmable CI) MCP Server?
Connect to the Dagger Engine to orchestrate your delivery pipelines using a powerful, programmable GraphQL API. This server allows your AI agent to interact directly with Dagger's Directed Acyclic Graph (DAG) of operations.
What you can do
- Container Orchestration — Initialize scratch containers, pull images, and manage OCI-compatible states.
- GraphQL Workflows — Execute raw GraphQL queries to compose complex build and test logic dynamically.
- Source Control — Query Git repositories and host environments to pull source code into your pipelines.
- Resource Management — Handle secrets securely, manage persistent cache volumes, and fetch remote files via HTTP.
- Module Inspection — Query the current module state and engine version to ensure environment consistency.
How it works
- Ensure a Dagger Engine is running in your environment.
- Provide the session port and token generated by the Dagger CLI.
- Start building and deploying through natural language commands.
Who is this for?
- DevOps Engineers — Automate pipeline debugging and execution without leaving the chat interface.
- Software Developers — Run builds, tests, and container operations directly from the code editor.
- SREs — Inspect engine states and orchestrate infrastructure tasks using programmable CI logic.
Built-in capabilities (10)
You can chain fields to create a Directed Acyclic Graph (DAG) of operations. Execute a raw GraphQL query against the Dagger engine
Constructs a cache volume
Creates a scratch container and returns its ID
Queries the current module
Creates an empty directory and returns its ID
Queries a Git repository
Queries the host environment
Returns a file from a URL
g., env://VAR_NAME, file://PATH, cmd://COMMAND). Creates a new secret
Get the Dagger Engine version
Why AutoGen?
AutoGen enables multi-agent conversations where agents negotiate, delegate, and collaboratively use Dagger (Programmable CI) tools. Connect 10 tools through Vinkius and assign role-based access. a data analyst queries while a reviewer validates, with optional human-in-the-loop approval for sensitive operations.
- —
Multi-agent conversations: multiple AutoGen agents discuss, delegate, and collaboratively use Dagger (Programmable CI) tools to solve complex tasks
- —
Role-based architecture lets you assign Dagger (Programmable CI) tool access to specific agents. a data analyst queries while a reviewer validates
- —
Human-in-the-loop support: agents can pause for human approval before executing sensitive Dagger (Programmable CI) tool calls
- —
Code execution sandbox: AutoGen agents can write and run code that processes Dagger (Programmable CI) tool responses in an isolated environment
Dagger (Programmable CI) in AutoGen
Dagger (Programmable CI) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Dagger (Programmable CI) to AutoGen through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Dagger (Programmable CI) in AutoGen
The Dagger (Programmable CI) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 10 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in AutoGen only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Dagger (Programmable CI) for AutoGen
Every tool call from AutoGen to the Dagger (Programmable CI) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I run a specific build command using Dagger?
You can use the execute_graphql_query tool to send a raw GraphQL query to the Dagger engine, allowing you to chain container operations like from, withExec, and stdout.
Can I access files from my local machine in the pipeline?
Yes, the query_host tool allows you to retrieve the state ID for your host environment, which can then be used to mount local directories into your Dagger containers.
How are secrets handled in this integration?
Use the query_secret tool to load secrets from URIs (like env:// or file://). This returns a secret ID that can be safely passed to other Dagger operations without exposing the plaintext value.
How does AutoGen connect to MCP servers?
Create an MCP tool adapter and assign it to one or more agents in the group chat. AutoGen agents can then call Dagger (Programmable CI) tools during their conversation turns.
Can different agents have different MCP tool access?
Yes. AutoGen's role-based architecture lets you assign specific MCP tools to specific agents, so a querying agent has different capabilities than a reviewing agent.
Does AutoGen support human approval for tool calls?
Yes. Configure human-in-the-loop mode so agents pause and request approval before executing sensitive MCP tool calls.
McpWorkbench not found
Install: pip install "autogen-ext[mcp]"
Explore More MCP Servers
View all →
GitHub Alternative
14 toolsManage repositories, issues, pull requests and workflows via GitHub — search code, audit commits and track CI/CD from any AI agent.

Runlayer
27 toolsAI enterprise control plane: manage MCP servers, skills, agents, and security policies via agents.

Kintone
10 toolsManage custom business apps, records, and workflows via Kintone.

Anthropic Alternative
6 toolsAccess Claude models via Anthropic API — send messages, count tokens, manage batches and discover models from any AI agent.
