Unofficial server that uses the DeepInfra OpenAI-compatible API for image generation, text processing and other AI tasks.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add deepinfra --env DEEPINFRA_API_KEY='<DEEPINFRA_API_KEY>' -- uv run mcp_deepinfra~/.codex/config.toml
[mcp_servers.deepinfra]
command = "uv"
args = ["run", "mcp_deepinfra"]
env = { DEEPINFRA_API_KEY = "<DEEPINFRA_API_KEY>" }
# codex mcp add deepinfra --env DEEPINFRA_API_KEY='<DEEPINFRA_API_KEY>' -- uv run mcp_deepinfra~/.cursor/mcp.json
{
"mcpServers": {
"deepinfra": {
"command": "uv",
"args": [
"run",
"mcp_deepinfra"
],
"env": {
"DEEPINFRA_API_KEY": "<DEEPINFRA_API_KEY>"
}
}
}
}.vscode/mcp.json
{
"servers": {
"deepinfra": {
"type": "stdio",
"command": "uv",
"args": [
"run",
"mcp_deepinfra"
],
"env": {
"DEEPINFRA_API_KEY": "<DEEPINFRA_API_KEY>"
}
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"deepinfra": {
"command": "uv",
"args": [
"run",
"mcp_deepinfra"
],
"env": {
"DEEPINFRA_API_KEY": "<DEEPINFRA_API_KEY>"
}
}
}
}claude_desktop_config.json
{
"mcpServers": {
"deepinfra": {
"command": "uv",
"args": [
"run",
"mcp_deepinfra"
],
"env": {
"DEEPINFRA_API_KEY": "<DEEPINFRA_API_KEY>"
}
}
}
}.trae/mcp.json
{
"mcpServers": {
"deepinfra": {
"command": "uv",
"args": [
"run",
"mcp_deepinfra"
],
"env": {
"DEEPINFRA_API_KEY": "<DEEPINFRA_API_KEY>"
}
}
}
}Environment variables
DEEPINFRA_API_KEY
Replace the placeholders with your own credentials and keep them out of version control.