Bring Ci Cd
to OpenAI Agents SDK
Learn how to connect Drone CI to OpenAI Agents SDK and start using 39 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Drone CI MCP Server?
Connect your Drone CI server to any AI agent to streamline your DevOps lifecycle through natural language.
What you can do
- Build Management — List, get details, restart, or stop builds across your repositories using
list_builds,get_build, andrestart_build. - Repository Control — Enable, update, or repair repository settings and sync them with your source control provider via
enable_repoandsync_user_repos. - Secret & Config Management — Manage environment secrets, cron jobs, and templates without leaving your chat interface using
list_secretsandcreate_cron_job. - User Administration — (Admin only) Create, update, or delete users and manage organizational access with
list_usersandcreate_user. - Log Inspection — Fetch build logs to debug pipeline failures instantly using
get_build_logs.
How it works
- Subscribe to this server
- Provide your Drone Server URL and Personal Access Token
- Start orchestrating your pipelines from Claude, Cursor, or any MCP client
Who is this for?
- DevOps Engineers — Monitor pipeline health and trigger builds via voice or text.
- Software Developers — Check build logs and status directly from the IDE.
- SREs — Manage secrets and cron jobs across multiple projects efficiently.
Built-in capabilities (39)
Approve a blocked build
Change repository ownership to current user
Create a custom build for a branch
Create a new cron job
Create a new repository secret
Create a new template
Create a new user account (Admin)
Decline a blocked build
Delete a cron job
Delete a repository secret
Delete a template
Delete a user account (Admin)
Disable or delete a repository
Enable/register a repository in Drone
Get specific build info including stages and steps
Get logs for a specific step in a build stage
Get cron job details
Get current authenticated user info
Get current user repositories
Get repository info
Get repository secret details
Get template details
Get user info by login (Admin)
List recent builds for a repository
List cron jobs for a repository
List repository secrets
List organization templates
Requires administrative privileges. List all registered users (Admin)
Promote a build to a target environment
Repair repository webhooks
Restart a specific build
Stop a running build (Admin)
Synchronize user repositories
Manually trigger an existing cron task
Update a cron job
Update repository configuration
Update a repository secret
Update a template
Update a user account (Admin)
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 39 tools from Drone CI through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Drone CI, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Drone CI in OpenAI Agents SDK
Drone CI and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Drone CI to OpenAI Agents SDK 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 Drone CI in OpenAI Agents SDK
The Drone 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 39 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK 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
Drone CI for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Drone CI MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I view the logs of a specific build to debug an error?
Yes, use the get_build_logs tool by providing the owner, repo name, and build number. Your agent will retrieve the full output from the pipeline steps.
How do I trigger a new build for a repository?
You can use the create_build tool to trigger a new build or restart_build to re-run an existing build number for a specific repository.
Is it possible to manage environment secrets through this agent?
Absolutely. You can use list_secrets, create_secret, and update_secret to manage your repository's sensitive data securely from the conversation.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
Gumlet
12 toolsOptimize images and stream video with automatic format conversion, lazy loading, and CDN delivery that loads pages faster.
Caddy Server
13 toolsManage your Caddy web server via API — update configurations, monitor upstreams, and handle PKI certificates directly from your AI agent.
Portainer
6 toolsManage Docker containers and environments via Portainer — list, create, and start containers directly from your AI agent.
Instantly
10 toolsEquip your AI agent with direct access to Instantly — manage cold email campaigns, track deliverability, and scale outreach across unlimited sending accounts.