Bring Task Management
to Pydantic AI
Learn how to connect Sally to Pydantic AI and start using 12 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Sally MCP Server?
Connect your Sally instance to any AI agent and take full control of your API-first project management through natural conversation.
What you can do
- Projects — Create, list, and inspect projects with full metadata.
- Tasks — Full CRUD with priorities (P1-P4), statuses, labels, and assignees.
- Comments — Add comments to any task for collaboration and status updates.
- Kanban Board — Retrieve the aggregated board view showing tasks organized by status columns.
- Timesheets — Access timesheet reports with tracked hours and billing information.
- Profile — Verify your authenticated identity and workspace permissions.
How it works
1. Subscribe to this server
2. Enter your Sally API key, instance URL, and workspace slug
3. Start managing projects from Claude, Cursor, or any MCP client
Who is this for?
- Project Managers — create tasks, track progress, and review board status through AI commands.
- AI Developers — automate agent-driven task management in a system designed for human+agent collaboration.
- Operations Teams — monitor project velocity and timesheet data without switching tools.
Built-in capabilities (12)
Comments are visible to all project members. Add a comment to a task
Check Sally instance health
Create a new project
Optionally set priority (P1-P4), status, and labels. Create a new task in a project
Get the Kanban board view
Get the authenticated user profile
Get details of a specific project
Get full details of a specific task
Get timesheet report for the workspace or project
List all projects in the workspace
Optionally filter by project ID to see tasks for a specific project. List tasks, optionally filtered by project
Only provided fields are changed. Update an existing task
Why Pydantic AI?
Pydantic AI validates every Sally tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Sally integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Sally connection logic from agent behavior for testable, maintainable code
Sally in Pydantic AI
Sally and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Sally to Pydantic AI 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 Sally in Pydantic AI
The Sally 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 12 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI 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
Sally for Pydantic AI
Every tool call from Pydantic AI to the Sally 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 task with priority, labels, and status in one step?
Yes! Use create_task with the project ID, title, priority (P1-P4), status name, and comma-separated labels. The task is created instantly with all metadata.
How do I view my Kanban board from the AI agent?
Use get_board to retrieve the aggregated board data. Optionally pass a project ID to scope it to a specific project. Tasks are grouped by their status columns.
Does Sally require a hosted instance or cloud account?
Sally is a self-hosted, API-first project management system. You need your own Sally instance URL, an API key (atpm_ prefix), and your workspace slug to connect.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Sally MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai