How to Use the Cohere (AI Platform) MCP in Claude Code

Q: How do I add the Cohere (AI Platform) MCP Server to Claude Code?

Run the claude mcp add command in your terminal with the server URL. Claude Code updates its local configuration and connects to the MCP tools instantly.

Q: How does Claude Code list available Cohere (AI Platform) models?

Claude Code invokes the listmodels tool to check API availability. It displays the models directly in your terminal or uses them to configure downstream tasks.

Q: Can I pipe the output of these tools to other CLI commands?

Yes. Claude Code outputs raw text from tools like generatetext directly to stdout, allowing you to pipe the results into tools like grep or sed.

Pipe terminal outputs and run headless Cohere text generation with 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 (AI Platform) MCP to Claude Code

Create your Vinkius account to connect Cohere (AI Platform) 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 (AI Platform) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Cohere text generation via Claude Code

The `generate_text` tool executes static generation tasks targeting foundational limits directly from your CLI. Claude Code uses this to write commit messages, generate shell scripts, or draft release notes based on git diffs. Because Claude Code runs entirely in the terminal, you can pipe the output of this MCP Server directly into other CLI utilities. This lets you automate documentation updates or code generation in headless environments.

Tokenize terminal inputs with Claude Code

The `tokenize_text` tool retrieves the exact structural segmentation limiting NLP contexts. Claude Code uses this to verify that terminal outputs or log files fit within model limits before sending them to the API. If a log file exceeds limits, Claude Code splits the file based on the token count and processes it in chunks. This prevents broken pipes and API errors in your terminal workflows.

Command-line document reranking with Claude Code

The `rerank_documents` tool structures specific contextual chunks to find the most relevant information in your files. Claude Code runs this tool to search through local markdown documentation or log directories. By filtering out irrelevant data, the tool ensures Claude Code only processes the exact context needed to answer your terminal queries. This keeps your CLI operations fast and resource-efficient.

Setup guide

Set up Cohere (AI Platform) 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-ai-platform-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http cohere-ai-platform-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 (AI Platform) 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-ai-platform-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 (AI Platform) 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 (AI Platform) MCP in Claude Code

Run the `claude mcp add` command in your terminal with the server URL. Claude Code updates its local configuration and connects to the MCP tools instantly.

Yes. You can run Claude Code in non-interactive mode inside your deployment scripts to trigger tools like `classify_inputs` or `generate_text` automatically.

Claude Code invokes the `list_models` tool to check API availability. It displays the models directly in your terminal or uses them to configure downstream tasks.

Yes. Claude Code outputs raw text from tools like `generate_text` directly to stdout, allowing you to pipe the results into tools like grep or sed.

Your command outputs, tokens, and file contents are sent directly to Cohere via secure HTTPS. Vinkius hosts the MCP server on a zero-trust architecture, ensuring no terminal history or payload data is cached on our infrastructure.

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