Authenticated Multi Llm Agent
Remote agent combining Anthropic and OpenAI clients with OAuth, via A2A and MCP
- Platforms
- API
- Runs
- Remotely
- Version
- 1.0.0
- Listing updated
- today
Similar MCP servers
About Authenticated Multi Llm Agent
Authenticated Multi Llm Agent is an MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.
This agent is assembled from four libraries: anthropic, openai, google-auth-oauthlib and mcp. Its site describes the combination as covering LLM clients, OAuth/OIDC authentication and agent protocol support.
It is reachable through a streamable HTTP MCP endpoint, and the site also links an A2A Agent Card and a governance page. That lets MCP-compatible clients and A2A-aware agents connect to it remotely, with no local package to install.
The page gives little detail beyond this composition, so specific tools, parameters and authentication flows are not documented there. It is listed on Smithery and belongs to a wider agent portfolio at getvda.ai.
Install
Run in a terminal
claude mcp add --transport http authenticated-multi-llm-agent https://authenticated-multi-llm-agent.getvda.ai/mcpAdd to Settings → Connectors → Add custom connector
https://authenticated-multi-llm-agent.getvda.ai/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"authenticated-multi-llm-agent": {
"url": "https://authenticated-multi-llm-agent.getvda.ai/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"authenticated-multi-llm-agent": {
"type": "http",
"url": "https://authenticated-multi-llm-agent.getvda.ai/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"authenticated-multi-llm-agent": {
"serverUrl": "https://authenticated-multi-llm-agent.getvda.ai/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"authenticated-multi-llm-agent": {
"type": "http",
"url": "https://authenticated-multi-llm-agent.getvda.ai/mcp"
}
}
}Using several servers? Build one config file with the MCP config generator.
What it does
- Multi-LLM clients
- Built on both the Anthropic and OpenAI client libraries, so it can work with more than one model provider.
- OAuth/OIDC authentication
- Uses google-auth-oauthlib to provide an authenticated flow for access.
- Remote MCP endpoint
- Exposes a streamable HTTP MCP endpoint that MCP clients can connect to directly.
- A2A Agent Card
- Publishes an Agent Card so it can be discovered and called through the Agent2Agent protocol.
- Governance page
- Links to a governance page associated with the agent.
Good for
- Connecting an MCP client to an authenticated multi-model agent
- Experimenting with agents reachable over both A2A and MCP
- Testing OAuth-protected agent endpoints
- Reference for composing Anthropic, OpenAI and MCP libraries
Authenticated Multi Llm Agent FAQ
Which protocols does it support?
It is exposed through both the Agent2Agent (A2A) protocol and the Model Context Protocol (MCP).
How do I connect to it over MCP?
Use the streamable HTTP endpoint at https://authenticated-multi-llm-agent.getvda.ai/mcp.
Which libraries is it composed from?
anthropic, google-auth-oauthlib, mcp and openai.
Where else is it listed?
It is listed on Smithery and part of the portfolio at getvda.ai/agents.
How do I add Authenticated Multi Llm Agent to Claude Code?
Run this command in your terminal: claude mcp add --transport http authenticated-multi-llm-agent https://authenticated-multi-llm-agent.getvda.ai/mcp
What are the best alternatives to Authenticated Multi Llm Agent?
The closest alternatives to Authenticated Multi Llm Agent are Authenticated Llm MCP Agent, Oauth Multi Llm Orchestrator, Authenticated Llm Traced Agent, Llm Orchestration Agent Openai and Authenticated Llm Agent.
Where this comes from
- Description: written from the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.