GoModel
Self-hosted AI gateway with caching, budgets, failover and an MCP aggregation endpoint
- Platforms
- Linux, macOS, Windows
- Runs
- Remotely
- Version
- 0.2.5
- Listing updated
- 4 days ago
Similar MCP servers
About GoModel
GoModel is an MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.
The headline product is an LLM gateway that accepts OpenAI-compatible requests at /v1 and Anthropic-compatible requests at /v1/messages, so official SDKs work after changing a base URL. It routes to a long provider list including OpenAI, Anthropic, Gemini, Vertex AI, Bedrock, Azure OpenAI, Mistral, Groq, Ollama and vLLM.
Gateway features include exact and semantic caching, cost tracking, budgets and rate limits by user path, virtual models with load balancing, session pinning, failover with circuit breakers, guardrails and plugins, with a dashboard at /admin/dashboard. Its MCP piece aggregates upstream MCP servers behind one authenticated endpoint, configured with a MASTER_KEY and an MCP_SERVERS JSON object.
It runs from a Docker image or an install script. The registry notes that leaving the master key unset runs the gateway with no authentication.
Install
Run in a terminal
claude mcp add gomodel --env GOMODEL_MASTER_KEY='<GOMODEL_MASTER_KEY>' -- docker run -i --rm -e GOMODEL_MASTER_KEY docker.io/enterpilot/gomodel:0.2.5Add to claude_desktop_config.json
{
"mcpServers": {
"gomodel": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GOMODEL_MASTER_KEY",
"docker.io/enterpilot/gomodel:0.2.5"
],
"env": {
"GOMODEL_MASTER_KEY": "<GOMODEL_MASTER_KEY>"
}
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"gomodel": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GOMODEL_MASTER_KEY",
"docker.io/enterpilot/gomodel:0.2.5"
],
"env": {
"GOMODEL_MASTER_KEY": "<GOMODEL_MASTER_KEY>"
}
}
}
}Add to .vscode/mcp.json
{
"servers": {
"gomodel": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GOMODEL_MASTER_KEY",
"docker.io/enterpilot/gomodel:0.2.5"
],
"env": {
"GOMODEL_MASTER_KEY": "<GOMODEL_MASTER_KEY>"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"gomodel": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GOMODEL_MASTER_KEY",
"docker.io/enterpilot/gomodel:0.2.5"
],
"env": {
"GOMODEL_MASTER_KEY": "<GOMODEL_MASTER_KEY>"
}
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"gomodel": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GOMODEL_MASTER_KEY",
"docker.io/enterpilot/gomodel:0.2.5"
],
"env": {
"GOMODEL_MASTER_KEY": "<GOMODEL_MASTER_KEY>"
}
}
}
}Using several servers? Build one config file with the MCP config generator.
Configuration
GOMODEL_MASTER_KEYGateway API key clients authenticate with; unset runs the gateway in unsafe (no-auth) mode.MCP_SERVERSJSON object of upstream MCP servers to aggregate, e.g. {"github":{"url":"https://api.githubcopilot.com/mcp/","headers":{"Authorization":"Bearer ${GITHUB_PAT}"}}}. Servers can also be declared in config.yaml or the admin dashboard.
What it does
- OpenAI and Anthropic APIs
- Accepts both request formats so SDKs need only a new base URL.
- Many providers
- Routes to dozens of hosted and local model providers.
- Caching and budgets
- Exact and semantic caching with spend limits and cost tracking.
- Failover
- Reroutes to backup providers with retries and circuit breakers.
- MCP gateway
- Aggregates upstream MCP servers behind one authenticated endpoint.
- Admin dashboard
- Manages providers and settings in a web UI.
Good for
- Put one gateway in front of several LLM providers
- Cap spend per team or key
- Expose several MCP servers through one authenticated URL
- Keep provider prompt caches warm with session pinning
GoModel FAQ
How do I run it?
With Docker (docker run enterpilot/gomodel) or the install script.
What formats does it accept?
OpenAI-compatible at /v1 and Anthropic-compatible at /v1/messages.
What if no master key is set?
The gateway runs in unsafe no-auth mode.
Where is the dashboard?
At /admin/dashboard on the server.
How do I add GoModel to Claude Code?
Run this command in your terminal: claude mcp add gomodel --env GOMODEL_MASTER_KEY='<GOMODEL_MASTER_KEY>' -- docker run -i --rm -e GOMODEL_MASTER_KEY docker.io/enterpilot/gomodel:0.2.5
What are the best alternatives to GoModel?
The closest alternatives to GoModel are ByMorning, LLM Gateway, codai, MCP-Bridge and Unified AI System MCP Gateway.
Where this comes from
- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.
