How to Use the Chroma (Vector DB) MCP in VS Code Copilot

Give your entire engineering team live Chroma access through VS Code Copilot.

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 VS Code Copilot

Create your Vinkius account to connect Chroma (Vector DB) to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Team-Wide Chroma (Vector DB) MCP Server Setup

You want your whole team building against the same vector database context. By adding this configuration to your project files, every developer gets instant access to the same tools. They can run `query_embeddings` to identify precise logical bounds matching high-dimensional semantic clustering. Nobody has to share API keys in Slack or write custom testing scripts. Copilot reads the shared config and can immediately `get_documents` to retrieve exact physical documents. Your entire engineering org stays aligned on the actual data structures returning from your nodes.

Audit and Inspect Collections

Debugging a bad retrieval pipeline is miserable when you cannot see the underlying collections. Copilot can execute `list_collections` to show you all explicitly defined vector collections within a given tenant database. You can dig deeper into any specific block. Running `get_collection` identifies the bounded logical settings configuring that specific vector collection. If you need a quick look at the actual records, `peek_documents` extracts an explicitly attached bounded preview of the database limits.

Verify Node Health and Document Counts

Sometimes the issue is not your code, it is the database itself. Before you spend an hour hunting for a bug, have your agent run `check_heartbeat`. This validates fundamental network availability against your explicit API nodes. Once you know the node is up, you can verify your data ingestion. The `count_documents` tool executes explicit structural tracking to enumerate total document volumes. You know instantly if your latest batch job actually inserted the records.

Setup guide

Set up Chroma (Vector DB) MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Chroma (Vector DB) MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Chroma (Vector DB) tools listed. Try asking: "List my recent Chroma (Vector DB) transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "chroma-vector-db-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 VS Code Copilot

Commit a .vscode/mcp.json file to your repository with the Vinkius endpoint. Anyone who pulls the repo gets immediate access to the database tools through their chat interface.

Yes. Switch your chat to Agent mode and ask it to run a vector search. It executes the query and returns the exact nearest-neighbor matches directly into your editor.

It handles that natively. You can pull a bounded preview of the database or run a structural tracking command to count the exact volume of documents currently indexed.

No. As long as you are running VS Code version 1.96 or higher, the protocol is built right into the editor. You just configure the JSON file and start working.

Security is handled at the protocol level through an isolated V8 sandbox. Your high-dimensional semantic clustering data and physical document text traverse a zero-trust architecture. The environment is entirely ephemeral and shuts down instantly after the request completes.

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