@gammainfra/mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GAMMAINFRA_API_KEY | Yes | Your GammaInfra API key, format sk-gammainfra-{32_chars}. | |
| GAMMAINFRA_BASE_URL | No | Override for staging/dev. | https://api.gammainfra.com/v1 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| chat_completionsA | Send a chat completion request to GammaInfra and receive the model response plus routing metadata. Smart routing picks the best-fit model when model='gammainfra/auto'; pin a specific model like 'openai/gpt-5-mini' for direct dispatch. Returns the OpenAI-shape response in a 'response' field and routing decisions (provider, endpoint, cost in USD, router version, fallback chain) in a 'routing_meta' field. Streaming is not supported via MCP; the request always uses stream=false. |
| list_modelsA | List every model available on GammaInfra with pricing and capability flags. Covers OpenAI, Anthropic, Google, Mistral, Groq, DeepSeek, xAI, and Amazon Bedrock today; plus the meta-models gammainfra/auto, gammainfra/fast, and gammainfra/cheap. No parameters. |
| get_balanceA | Return the authenticated customer's GammaInfra balances: managed (USD) and currency. Pass include_byok=true to also fetch the BYOK (USD if enrolled) balance; when omitted, byok_balance_usd is null and no BYOK request is made. With include_byok=true, BYOK is reported inline as a byok_error string if the BYOK endpoint fails (e.g., customer has no BYOK enrollment). |
| get_statusA | Return GammaInfra's current health: overall state, per-provider health (latency p50 + state), and 24-hour request count. Useful before kicking off a long agent loop. No parameters. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: health status, chat completions, model listing, and balance checking. No overlap.
Names follow a verb_noun pattern (get_status, list_models, get_balance) except chat_completions which is a noun phrase, but still readable and consistent in style.
Four tools is well-scoped for the server's purpose—covering health, chat, models, and balance without bloat or deficiency.
Covers core operations (chat, model discovery, status, balance), but lacks features like usage history or streaming support, which are minor gaps.