How to Use the DocsBot MCP in Pydantic AI

Q: How do I initialize the DocsBot MCP Server using the latest Pydantic AI library?

Install the package using pip install "pydantic-ai-slimmcp". Use the unified MCPToolset("http://...") approach pointing to your Vinkius URL, and pass that toolset directly to your Agent's toolsets parameter.

Q: Can I use Pydantic AI to validate the structure of DocsBot interaction logs?

Yes, when your agent calls listbotinteractionlogs, the framework validates the raw JSON response against its internal schemas. This guarantees your log analysis scripts never run into unexpected null values.

Run type-safe DocsBot queries with Pydantic AI to guarantee zero-hallucination document retrieval and strict runtime schema validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DocsBot MCP to Pydantic AI

Create your Vinkius account to connect DocsBot 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 DocsBot with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce strict runtime types on DocsBot responses

Integrating directly with Pydantic AI allows you to validate responses from `get_bot_details` against strict schemas. Silent errors are the worst part of building LLM apps, but this setup ensures your code fails loudly before bad data propagates. Whenever the DocsBot API returns unexpected fields or missing data, your system will raise a validation error. This prevents corrupted structures from poisoning your downstream application logic.

Validate DocsBot knowledge base metadata in Pydantic AI

Querying `get_bot_knowledge_summary` lets your agent verify knowledge base metrics before running data pipelines. When building automated reporting tools, accuracy is everything. Validating these endpoints guarantees that metrics like file sizes or source counts match your data models exactly. You don't have to write manual parsing code to handle raw JSON strings.

Safely manage team and bot lists without silent failures

Managing workspace access is handled securely by querying `list_docsbot_teams` and `list_team_bots`. Managing multiple workspaces requires reliable tools, and this MCP Server lets your agent map out your organization's entire AI footprint. Since Pydantic AI handles the tool signatures under the hood, you can be sure that team IDs and bot configurations are parsed cleanly. This eliminates the risk of routing queries to the wrong team bot.

Setup guide

Set up DocsBot 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": {
        "docsbot-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent DocsBot 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 DocsBot. 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 DocsBot 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 DocsBot MCP in Pydantic AI

Install the package using `pip install "pydantic-ai-slim[mcp]"`. Use the unified `MCPToolset("http://...")` approach pointing to your Vinkius URL, and pass that toolset directly to your Agent's `toolsets` parameter.

The framework will immediately raise a validation error at runtime. This prevents tools like `get_docsbot_account_metadata` from passing malformed or incomplete user data into your application flow.

Yes, when your agent calls `list_bot_interaction_logs`, the framework validates the raw JSON response against its internal schemas. This guarantees your log analysis scripts never run into unexpected null values.

Yes, the unified toolset class handles both Streamable HTTP and SSE transports for this MCP setup out of the box. Ensure your external server is running, and the client will manage the connection automatically.

Your account metadata and API tokens are never stored by Vinkius. Every validation check on `get_docsbot_account_metadata` runs in an isolated, short-lived V8 sandbox that wipes all memory traces immediately after execution.

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