How to Use the DottedSign MCP in Pydantic AI

Q: How do I register the DottedSign MCP Server in Pydantic AI?

Install pydantic-ai-slimmcp first. Initialize MCPToolset with your Vinkius HTTP endpoint, and pass it directly into the toolsets argument of your Agent. Avoid the deprecated MCPServerHTTP class.

Q: Does Pydantic AI validate the responses from DottedSign tools?

Yes, the framework wraps every tool call, like getme or retrievetask, in a runtime validation layer. If the API response deviates from the expected schema, the framework flags the validation error before your agent acts on the bad data.

Q: How do I handle DottedSign task cancellations safely in Pydantic AI?

Your agent calls canceltask by passing the validated task ID. Because Pydantic AI enforces type checks on all parameters, you prevent the agent from sending malformed IDs that would otherwise result in API errors.

Build type-safe Pydantic AI agents that run DottedSign workflows with zero silent runtime errors.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DottedSign MCP to Pydantic AI

Create your Vinkius account to connect DottedSign to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup DottedSign with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate DottedSign MCP Server payloads

Every response from `create_task` or `retrieve_task` is parsed against strict Pydantic models before your agent uses it. This setup blocks malformed API data from corrupting your database or breaking your application logic. If the DottedSign MCP Server returns an unexpected payload structure, Pydantic AI raises a validation error immediately. You get type safety across your entire document pipeline, ensuring your agent only works with clean, structured data.

Manage templates with type-safe schemas

Use `list_templates` to fetch available document structures, validating the output schema against your internal models. The agent uses this verified data to execute `create_task_from_template`, ensuring that every required field is populated correctly. This strict validation prevents your agent from sending incomplete contracts. If a template schema changes on the server, the agent catches the mismatch during execution rather than failing silently after sending a broken document.

Audit tasks with guaranteed data structures

Fetching compliance records using `get_audit_trail` requires precise data parsing. Pydantic AI validates the audit log schema at runtime, guaranteeing that signer IP addresses, timestamps, and event types match your database schemas. If you need to clean up old tasks, the agent calls `list_tasks` to identify candidates, validates their status, and executes `delete_task`. Every step of this lifecycle is type-checked, giving you confidence in your automated cleanup scripts.

Setup guide

Set up DottedSign MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "dottedsign-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to DottedSign tools.",
)

result = await agent.run("List recent DottedSign transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by DottedSign. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect DottedSign now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about DottedSign MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` first. Initialize `MCPToolset` with your Vinkius HTTP endpoint, and pass it directly into the `toolsets` argument of your `Agent`. Avoid the deprecated `MCPServerHTTP` class.

Yes, the framework wraps every tool call, like `get_me` or `retrieve_task`, in a runtime validation layer. If the API response deviates from the expected schema, the framework flags the validation error before your agent acts on the bad data.

Your agent calls `cancel_task` by passing the validated task ID. Because Pydantic AI enforces type checks on all parameters, you prevent the agent from sending malformed IDs that would otherwise result in API errors.

Yes, the framework is model-agnostic. You run local models or commercial APIs to manage your `list_users` and task management workflows, as long as the model supports the MCP Server protocol.

The integration routes PDF document files and audit trail logs through a zero-trust, ephemeral V8 sandbox. This architecture guarantees that no sensitive file content or signing histories are stored on Vinkius, maintaining strict compliance.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript