How to Use the Cohere (Embed & Rerank) MCP in Claude Code

Q: How do I install the Cohere (Embed & Rerank) MCP Server for Claude Code?

Run the claude mcp add command with the HTTP transport flag and the server URL. This adds the configuration directly to your /.claude.json file to register the MCP Server, letting the CLI agent auto-discover the tools immediately.

Q: How does the tool handle conversational text transformations?

The agent uses chatcompletion to execute structured transformations on raw text inputs. This is perfect for rewriting messy logs into clean, human-readable markdown summaries directly inside your terminal session.

Pipe terminal data directly into Cohere's vector and ranking engines using Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cohere (Embed & Rerank) MCP to Claude Code

Create your Vinkius account to connect Cohere (Embed & Rerank) to Claude Code 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 (Embed & Rerank) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

CLI-driven semantic search pipelines

Running search operations from the terminal usually means dealing with clunky grep commands. Claude Code changes that by invoking `embed_texts` to generate vector representations of your local logs or documentation right from the shell. After embedding, the CLI agent runs `rerank_documents` to sort the terminal output by semantic relevance. You can pipe raw log files directly into the agent and get the most critical errors surfaced instantly without manual filtering.

Automated classification of shell outputs

This MCP Server allows Claude Code to categorize incoming streams of text on the fly. By using `classify_texts`, the agent groups log lines, error codes, or system alerts into static categories that you define. You can script this behavior into your deployment pipelines. The agent reads the stdout, classifies the messages, and triggers specific scripts based on the resulting categories.

Optimize prompt contexts for Claude Code

Keeping your terminal context clean is essential when working with long log streams. The agent uses `tokenize_text` to check the exact structural segmentation of your text, ensuring you never overflow the CLI's token limits. If you need to debug API availability or swap models mid-session, the agent calls `list_models` to inspect active Cohere endpoints. It keeps your automated shell scripts running with the correct configuration without manual intervention.

Setup guide

Set up Cohere (Embed & Rerank) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see cohere-embed-rerank-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Cohere (Embed & Rerank) transactions." It will automatically discover and invoke the available Cohere (Embed & Rerank) tools.

Terminal

claude mcp add --transport http cohere-embed-rerank-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Cohere (Embed & Rerank) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "cohere-embed-rerank-mcp": {
      "type": "url",
      "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 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 (Embed & Rerank) 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 (Embed & Rerank) MCP in Claude Code

The CLI agent uses the MCP Server to vectorize your piped terminal inputs and files with `embed_texts`. It then runs `rerank_documents` to prioritize the most relevant text blocks, making it easy to search through massive log files directly from the command line.

Yes, you can run Claude Code in non-interactive mode to process text streams. The agent can take raw stdout, run `classify_texts` to categorize the data, and pipe the output to another CLI utility.

Run the `claude mcp add` command with the HTTP transport flag and the server URL. This adds the configuration directly to your `~/.claude.json` file to register the MCP Server, letting the CLI agent auto-discover the tools immediately.

The agent uses `chat_completion` to execute structured transformations on raw text inputs. This is perfect for rewriting messy logs into clean, human-readable markdown summaries directly inside your terminal session.

All text and documents piped through the CLI are encrypted in transit using standard HTTPS before reaching Cohere. Vinkius hosts the execution environment in a secure, sandboxed MCP Server isolate that does not store, inspect, or persist any of your command-line 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