How to Use the Chroma (Vector DB) MCP in Pydantic AI

Q: How do I add Chroma (Vector DB) to Pydantic AI?

Initialize an MCPToolset with your Vinkius HTTP URL. Pass that toolset array into your Agent definition. The framework automatically parses the schema.

Q: Why did Pydantic AI deprecate MCPServerHTTP for Chroma (Vector DB)?

The framework moved to a unified approach. MCPToolset now handles both Streamable HTTP and SSE transports natively, providing better type safety across the board.

Q: Can the agent verify the database connection first?

Yes. It calls the checkheartbeat tool. This validates fundamental network availability against the Chroma API nodes before running heavy queries.

Connect Chroma to Pydantic AI. Run type-safe vector queries and validate every document returned by this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chroma (Vector DB) MCP to Pydantic AI

Create your Vinkius account to connect Chroma (Vector DB) 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 Chroma (Vector DB) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Vector Queries

Silent failures ruin production pipelines. When your agent calls the `query_embeddings` tool, Pydantic AI validates the high-dimensional semantic clustering results against your defined schemas at runtime. If Chroma returns an unexpected format, the agent fails loudly. You catch the validation error immediately instead of passing hallucinated document IDs down the chain.

Collection Management via MCP Server

Auditing your vector store requires precise structural tracking. The `list_collections` and `get_collection` tools pull explicitly defined collections from your tenant database. Your agent then fires `count_documents` to verify the total volume matches your expectations. Because you use `MCPToolset` with a unified HTTP approach, the connection remains stable and strictly typed.

Strict Document Extraction

Grabbing raw text demands exactness. The `get_documents` tool retrieves physical documents and semantic context inside known arrays, completely bypassing fuzzy matching. For a quick look, the agent executes `peek_documents` to extract a bounded preview. Vinkius handles the underlying authentication, so you just pass the endpoint token and let the framework handle the rest.

Setup guide

Set up Chroma (Vector DB) 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": {
        "chroma-vector-db-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Chroma (Vector DB) 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 Chroma. 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 Chroma (Vector DB) 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 Chroma (Vector DB) MCP in Pydantic AI

Initialize an `MCPToolset` with your Vinkius HTTP URL. Pass that toolset array into your Agent definition. The framework automatically parses the schema.

The framework moved to a unified approach. `MCPToolset` now handles both Streamable HTTP and SSE transports natively, providing better type safety across the board.

Yes. It calls the `check_heartbeat` tool. This validates fundamental network availability against the Chroma API nodes before running heavy queries.

Since Pydantic AI is model-agnostic, you pair it with local models or external APIs. The MCP Server runs externally on Vinkius and responds regardless of which LLM triggers the tool.

Every request spins up an isolated V8 sandbox. We parse the vector arrays and document bounds, execute the query, and destroy the environment. Zero trust means zero retained data.

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