An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Glama to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Find and run external intelligence capabilities without leaving your chat.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 8 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 8 available through Glama.

  1. 01

    Glama get mcp server info

    This capability fetches specific installation instructions and parameters for a single Glama MCP. You just need to provide the namespace and slug.

  2. 02

    Glama get gateway model details

    This capability inspects the specific configurations of a model through the Glama proxy. It returns details like context window size and pricing for a given model string.

  3. 03

    Glama get gateway models

    This capability lists every AI model supported by the Glama OpenAI-compatible gateway. It is the primary way to audit available proxy models.

  4. 04

    Glama get hosted instances

    This capability pulls all Private Hosted MCP instances tied to your Glama account. It lets your agent see exactly what you have running in your private environment.

Capability set02 / 02

05-08

4 capabilities in this set.

Part of 8 available through Glama.

  1. 05

    Glama send telemetry

    This capability sends execution metrics and usage data back to the Glama Telemetry backend. Use it to log how your agent performs when using external capabilities.

  2. 06

    Glama run gateway chat

    This capability executes a conversational prompt through the Glama proxy network. It allows your agent to run logic chains using specific models outside of its local memory.

  3. 07

    Glama get mcp attributes

    This capability retrieves the semantic categories and filtering attributes used in the Glama MCP Registry. It helps your agent understand how capabilities are classified.

  4. 08

    Glama list mcp servers

    This capability searches the global Glama directory for available MCPs. It supports loose text matching so your agent can find capabilities even with vague descriptions.

Real work

What teams actually run

01

Rapid Capability Prototyping

An engineer finds a specific protocol in the registry and immediately tests it within their current AI session.

02

Multi-Model Routing

An agent switches between a large model for reasoning and a smaller model for speed via the Glama gateway.

03

Enterprise Data Integration

A user finds a specific CRM MCP to pull customer data directly into their workflow.

04

Performance Monitoring

A developer sends usage metrics back to Glama to track how often specific capabilities are successfully called.

Automate a task

Put Glama to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Glama works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Glama to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

825ms average. Fast in production.

Glama is checked daily against the live service.

Daily averagePeak 926ms
Oct 3Today
Fastest day
640ms
Slowest day
926ms
14-day trend
Slowing+17%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 8 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Glama, so you can see the experience inside your AI.

It does not authenticate your account with Glama. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Glama Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_3I3xkcQ0Lir2EbUp0HqzccT0Pcn6Iy0qjp9A5LCu/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Glama capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "glama-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_3I3xkcQ0Lir2EbUp0HqzccT0Pcn6Iy0qjp9A5LCu/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Glama in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Glama owners hand off.

This MCP is built for technical users who need to bridge the gap between their local AI environment and a distributed network of models and capabilities.

  • 01

    DevOps Engineers

    They use it to prototype API models and retrieve specific protocols without using web dashboards.

  • 02

    Financial Analysts

    They use it to locate enterprise integrations and map variables to external endpoints.

  • 03

    Operations Managers

    They use it to pull metric attributes and manage hosted proxies to reduce execution friction.

FAQ

Questions Glama owners ask.

  • 01

    How do I find new capabilities with this MCP?

    Your agent can use the glama_list_mcp_servers capability to search the global Glama directory using text matching.

  • 02

    Can I use this to access different LLMs?

    Yes. The glama_run_gateway_chat capability lets you proxy prompts through the Glama gateway to access various models.

  • 03

    Do I need to manage my own API keys for every model?

    No. The Glama gateway acts as a proxy, allowing you to access multiple models through a single connection.

  • 04

    Can I see my private MCP instances?

    Yes. The glama_get_hosted_instances capability allows your agent to fetch all private instances assigned to your Glama account.

  • 05

    How does the agent know the context window of a model?

    The agent can use glama_get_gateway_model_details to check specific configurations like context windows and pricing.

  • 06

    Can I test alternative AI models entirely within the terminal using the Glama integration?

    Yes. Capabilities like glama_get_gateway_models list available OpenAI-compatible proxies, and glama_run_gateway_chat allows your Vinkius agent to run text completions outside itself natively.

  • 07

    Does the Glama server provide telemetry data back to the registry?

    Yes. Active MCP usage events can be logged seamlessly applying the glama_send_telemetry capability in specific sequences to inform publishers about proxy executions.

  • 08

    Are private hosted instances queryable?

    Yes. By executing glama_get_hosted_instances, your agent limits queries exclusively to private proxies explicitly belonging to your linked environment.

Explore

More in Friends

Suggestions

Connect Glama to Claude, Cursor, ChatGPT & more