How to Use the Cohere MCP in Pydantic AI

Q: How do I register the Cohere MCP Server with my Pydantic AI agent?

Use pip install 'pydantic-ai-slimmcp' to install the package. Then, create an MCPToolset pointing to the Vinkius URL and pass it to your Pydantic AI Agent inside the toolsets list.

Q: Can I use Pydantic AI to dynamically check available Cohere models?

Yes. Your agent can invoke the listmodels tool to get a validated list of active models. Pydantic AI parses the model names, context lengths, and endpoints, ensuring your application code only interacts with verified model configurations.

Run Cohere models with runtime type validation using Pydantic AI and our MCP Server to catch API schema errors.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cohere MCP to Pydantic AI

Create your Vinkius account to connect Cohere 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 Cohere with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Structured Generation in Pydantic AI

The `chat` tool returns structured model responses that your Pydantic AI agent validates against your defined Pydantic schemas at runtime. When you call `chat` with `command-r-plus`, any returned citations or tool calls are instantly parsed and checked. If the API returns unexpected fields, the framework raises a validation error immediately. To set this up, install `pydantic-ai-slim[mcp]` and initialize the MCP toolset with your Vinkius HTTP URL. Pass this toolset into the `Agent` constructor to expose the tools securely.

Validated Vector Generation via MCP Server

The `embed` tool outputs vector arrays that Pydantic AI validates before they enter your application logic. When your agent calls `embed` using `embed-v4`, the framework ensures the returned embedding vectors match the exact float array structure defined in your Python types. This strict validation prevents corrupted or malformed vector data from silently breaking your downstream search queries. It guarantees that every vector stored in your database conforms to your exact specifications.

Strict Document Reranking Workflows

The `rerank` tool processes document relevance checks while Pydantic AI enforces type safety on the results. When the agent passes documents to `rerank-v3.5`, the returned relevance scores and document indices are parsed directly into typed Python objects. This layout ensures your agent never processes a null score or an invalid index. If the ranking data deviates from the expected schema, Pydantic AI halts execution, protecting your production pipeline from logic bugs.

Setup guide

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

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

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

Use pip install 'pydantic-ai-slim[mcp]' to install the package. Then, create an MCPToolset pointing to the Vinkius URL and pass it to your Pydantic AI Agent inside the toolsets list.

Yes. When your Pydantic AI agent calls tokenize to inspect a string, the framework validates the returned token IDs and token strings against its internal schema, ensuring you get a clean, typed response.

Yes. Your agent can invoke the list_models tool to get a validated list of active models. Pydantic AI parses the model names, context lengths, and endpoints, ensuring your application code only interacts with verified model configurations.

Pydantic AI has deprecated MCPServerHTTP in favor of the unified MCPToolset approach. This unified setup provides a cleaner API for handling external servers over both Streamable HTTP and SSE transports.

Every request to the server, including text payloads, token IDs, and vector embeddings, runs inside an ephemeral V8 Isolate sandbox. Vinkius operates on a zero-trust model, meaning your data is never logged or stored.

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