How to Use the Glama MCP in Claude Code

Q: How do I add the Glama server to Claude Code?

Run the claude mcp add command with the HTTP transport flag and your Vinkius URL. Make sure to place all flags before the server name to register it in your /.claude.json file.

Q: Can Claude Code search the Glama directory programmatically?

Yes, the CLI agent runs glamalistmcpservers to search for tools based on your terminal prompts. It can then parse the results to find the exact utility you need.

Q: How does Claude Code run prompts through Glama gateway models?

The agent queries glamagetgatewaymodels to check active endpoints. It then uses glamarungatewaychat to send code blocks or system logs to the selected model for analysis.

Q: Does Claude Code support private Glama instances?

Yes, the CLI agent calls glamagethostedinstances to retrieve your private servers. This lets you run secure, internal tools directly from your terminal session using this MCP Server.

Query the Glama directory and run gateway models directly from your Claude Code terminal.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Glama MCP to Claude Code

Create your Vinkius account to connect Glama 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 Glama with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search the MCP directory from your CLI

Claude Code lets you discover new tools without opening a browser. The agent queries `glama_list_mcp_servers` directly from the terminal to find servers matching your current pipeline requirements. It retrieves installation commands using `glama_get_mcp_server_info`. This allows you to chain CLI commands to configure your environment on the fly.

Terminal-based gateway routing

Claude Code can audit available gateway models using `glama_get_gateway_models`. It then executes remote reasoning tasks by calling `glama_run_gateway_chat` directly from your shell. By checking `glama_get_gateway_model_details`, the agent determines context limits before sending large log files. This prevents out-of-memory errors during long terminal sessions.

Telemetry and private hosting

Claude Code queries `glama_get_hosted_instances` to fetch and execute private tools configured for your account. This MCP connection is ideal for secure CI/CD environments that need access to internal APIs. After completing a terminal run, the agent triggers `glama_send_telemetry` to log performance metrics. You get clear data on tool usage without manual logging setups.

Setup guide

Set up Glama 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 glama-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Glama transactions." It will automatically discover and invoke the available Glama tools.

Terminal

claude mcp add --transport http glama-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 Glama 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": {
    "glama-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 Glama. 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 Glama 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 Glama MCP in Claude Code

Run the `claude mcp add` command with the HTTP transport flag and your Vinkius URL. Make sure to place all flags before the server name to register it in your `~/.claude.json` file.

Yes, the CLI agent runs `glama_list_mcp_servers` to search for tools based on your terminal prompts. It can then parse the results to find the exact utility you need.

The agent queries `glama_get_gateway_models` to check active endpoints. It then uses `glama_run_gateway_chat` to send code blocks or system logs to the selected model for analysis.

Yes, the CLI agent calls `glama_get_hosted_instances` to retrieve your private servers. This lets you run secure, internal tools directly from your terminal session using this MCP Server.

Your execution metrics and terminal prompts are processed within Vinkius's ephemeral V8 isolates. No local logs or sensitive pipeline variables are cached or stored permanently on the MCP backend.

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