Bring Task Tracking
to OpenAI Agents SDK
Learn how to connect Basecamp to OpenAI Agents SDK and start using 17 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Basecamp MCP Server?
Connect your Basecamp account to any AI agent and take full control of your project management, team collaboration, and task tracking through natural conversation.
What you can do
- Project Management — Create, list, update, and inspect projects with full dock metadata (message boards, to-do sets, schedules).
- To-Do CRUD — Create, update, complete, and uncomplete to-do items across any to-do list, with assignees and due dates.
- Team Visibility — List all people in your account or within a specific project to find assignee IDs and check roles.
- Message Boards — Read messages posted on project boards to stay aligned with team decisions and announcements.
- Comments — Add comments to any recording (to-do, message, document) to provide feedback or status updates.
- Profile Verification — Retrieve your authenticated profile to confirm connectivity and check access permissions.
How it works
1. Subscribe to this server
2. Enter your Basecamp OAuth access token and account ID
3. Start managing your projects from Claude, Cursor, or any MCP client
Who is this for?
- Project Managers — create tasks, assign team members, and track completion status through simple AI commands.
- Team Leads — monitor project boards, review messages, and add comments without switching context.
- Remote Teams — stay synchronized by querying project states and to-do progress directly from the workspace.
Built-in capabilities (17)
This is separate from archiving or trashing — a completed to-do remains active but is marked as done. Use uncomplete_todo to reverse this action. Mark a to-do item as completed
). The recording_id is the unique numeric ID of the item you want to comment on. The content must be provided as rich text (HTML). All subscribers to the recording will be notified of the new comment. Add a comment to any Basecamp recording
The project will be initialized with default tools (message board, to-do set, schedule, etc.) enabled via its dock. Returns the newly created project with its numeric ID and dock tool IDs. Create a new project in Basecamp
Requires the todolist_id and the content (title) of the to-do. Optionally include a rich text description, assignee IDs (array of person IDs), and a due date in YYYY-MM-DD format. The to-do will be created as pending (not completed). Create a new to-do item in a to-do list
Get full details of a specific message
Use this to verify connectivity or identify the current operator. Get the authenticated Basecamp user profile
Use this to look up details about a team member or assignee. Get full details of a specific person
). The dock contains the IDs you need to access tools like the to-do set or message board. Get full details of a specific project
Get full details of a specific to-do item
Each message includes title, content preview, author, category, and creation date. You need the message_board_id which can be found via the project dock. List all messages on a project message board
Useful for finding assignee IDs before creating or updating to-dos. List all people in the Basecamp account
Returns names, emails, and roles. Useful for checking team composition before assigning tasks. List all people assigned to a specific project
Optionally filter by status: "active" (default), "archived", or "trashed". Each project includes its name, description, purpose, dock (enabled tools), and bookmark status. List all projects in Basecamp
By default returns only pending (not completed) items. Set completed to true to see completed items instead. Each to-do includes its content, assignees, due date, completion status, and comments count. You need the todolist_id which can be found via the project dock. List all to-dos in a specific to-do list
Use this when a previously completed task needs to be reopened or reworked. Mark a completed to-do item as pending again
At least one of name or description must be provided. Returns the updated project details including the full dock listing. Update an existing project in Basecamp
At least one field must be provided. Does not affect completion status — use the complete_todo or uncomplete_todo tools for that. Update an existing to-do item in Basecamp
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 17 tools from Basecamp through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Basecamp, 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
Basecamp in OpenAI Agents SDK
Basecamp and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Basecamp 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 | 3,400+ 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 Basecamp in OpenAI Agents SDK
The Basecamp 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 17 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
Basecamp for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Basecamp MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I create a to-do and assign it to a team member directly via the AI agent?
Yes! Use the create_todo tool with the to-do list ID, content, and the assignee person IDs. You can also set a due date. The to-do will be created and assigned instantly in Basecamp.
How do I find the to-do list ID I need to create tasks in?
First, use get_project to retrieve the project details — the dock will contain the todoset ID. Then use the Basecamp UI or the to-do set to find your specific to-do list IDs within that project.
Can I mark a to-do as completed and later reopen it if needed?
Absolutely. Use the complete_todo tool to mark a to-do as done, and uncomplete_todo to reopen it. This only affects the completion status — the to-do remains active and visible in the project.
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.