Skip to main content
Glama
@gammainfra/mcp-server

@gammainfra/mcp-server

by yuz0101

@gammainfra/mcp-server

Model Context Protocol (MCP) server for GammaInfra — intelligent LLM routing across every major provider via one OpenAI-shape API.

Drop this server into Claude Code, Claude Desktop, Cursor, Cline, Continue, or any MCP-compatible host, and your agent gets direct tool access to:

  • chat_completions — call any supported model (or gammainfra/auto for smart routing) with cost, latency, and quality controls. Routing metadata (which provider served, exact cost in USD, fallback chain) is returned as a structured routing_meta field.

  • list_models — full model catalog with pricing and capability flags.

  • get_balance — managed + BYOK balances.

  • get_status — overall + per-provider health, 24h request count.

Quickstart

  1. Get a GammaInfra API key — sign up free at https://gammainfra.com/signup ($3 trial credit, no credit card).

  2. Add the server to your MCP client config (instructions per client below).

  3. Restart the client. The four tools become available to your agent immediately.

Related MCP server: TianGong-AI-MCP

Installation

The server runs via npx — no manual install needed. The first invocation downloads and caches the package.

Claude Code

claude mcp add gammainfra \
  --env GAMMAINFRA_API_KEY=sk-gammainfra-... \
  -- npx -y @gammainfra/mcp-server

Or edit ~/.claude.json and add to the mcpServers block:

{
  "mcpServers": {
    "gammainfra": {
      "command": "npx",
      "args": ["-y", "@gammainfra/mcp-server"],
      "env": { "GAMMAINFRA_API_KEY": "sk-gammainfra-..." }
    }
  }
}

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "gammainfra": {
      "command": "npx",
      "args": ["-y", "@gammainfra/mcp-server"],
      "env": { "GAMMAINFRA_API_KEY": "sk-gammainfra-..." }
    }
  }
}

Restart Claude Desktop. The "GammaInfra" server should appear in the tools menu.

Cursor

Edit ~/.cursor/mcp.json:

{
  "mcpServers": {
    "gammainfra": {
      "command": "npx",
      "args": ["-y", "@gammainfra/mcp-server"],
      "env": { "GAMMAINFRA_API_KEY": "sk-gammainfra-..." }
    }
  }
}

Cline (VS Code)

Open Cline's settings (gear icon → MCP Servers tab) and add:

{
  "gammainfra": {
    "command": "npx",
    "args": ["-y", "@gammainfra/mcp-server"],
    "env": { "GAMMAINFRA_API_KEY": "sk-gammainfra-..." },
    "disabled": false
  }
}

Environment variables

Var

Required

Default

Description

GAMMAINFRA_API_KEY

yes

—

Your GammaInfra API key, format sk-gammainfra-{32_chars}.

GAMMAINFRA_BASE_URL

no

https://api.gammainfra.com/v1

Override for staging/dev.

Tool reference

chat_completions

Send a chat completion request and receive the model response plus routing metadata.

Parameters:

Name

Type

Required

Description

model

string

yes

gammainfra/auto for smart routing, gammainfra/fast/gammainfra/cheap for tier shortcuts, or pin a specific model like openai/gpt-5-mini.

messages

array

yes

OpenAI-shape conversation messages.

temperature

number

no

0..2.

max_tokens

int

no

max_completion_tokens

int

no

GPT-5 family requires this instead of max_tokens.

cost_quality

float

no

0.0..1.0 continuous dial. Sent as X-GammaInfra-Cost-Quality.

max_latency_ms

int

no

60..600000. Caps total wall-clock incl. fallback retries. Also enforced client-side as a hard request abort.

preference

string

no

quality, cost, or latency.

region

string

no

us, eu, apac, or specific AWS region.

tools, tool_choice, response_format, top_p, frequency_penalty, presence_penalty

various

no

Standard OpenAI fields, forwarded as-is.

Returns: { response: <OpenAI response>, routing_meta: { provider, endpoint, cost_usd, input_cost_usd, output_cost_usd, router_version, logical_model, fallback_chain, attempted_count, request_id, ... } }

Timeout note: Every request has a 10-minute client-side hard timeout (via AbortController) so a hung upstream can't wedge the MCP process. For chat_completions, a supplied max_latency_ms replaces that default as the hard abort bound.

Streaming note: MCP tool responses are non-streaming. The server always sends stream: false to the upstream and does not accept a stream parameter on the tool input (it's rejected by schema validation). For streaming, use the GammaInfra HTTP API directly.

list_models

No parameters. Returns the full model catalog including direct-pin slugs, per-token pricing, and capability flags (supports_tools, supports_vision).

get_balance

Name

Type

Required

Description

include_byok

boolean

no

Default false. Also fetch the BYOK balance. Off by default to avoid an extra request — and a guaranteed 404 — for customers without BYOK enrollment.

Returns { managed_balance_usd, byok_balance_usd, currency }. With include_byok omitted/false, byok_balance_usd is null and no BYOK request is made (no byok_error). With include_byok: true, if BYOK isn't enrolled, byok_balance_usd is null and a byok_error field describes the cause.

get_status

No parameters. Returns GammaInfra's current overall health, per-provider state and live p50 latency, and 24h request count.

Development

git clone https://github.com/yuz0101/gammainfra-mcp-server.git
cd gammainfra-mcp-server
npm install
npm run test          # 30 tests, ~1s
npm run build         # tsc → dist/
npm run typecheck

License

MIT — see LICENSE.

Available Tools

4 tools
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.

Inputs: model (required), messages (required), tools, top_p, +11 more.

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).

Inputs: include_byok.

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.

Inputs: no named parameters.

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.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: health status, chat completions, model listing, and balance checking. No overlap.

    Naming Consistency4/5

    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.

    Tool Count5/5

    Four tools is well-scoped for the server's purpose—covering health, chat, models, and balance without bloat or deficiency.

    Completeness4/5

    Covers core operations (chat, model discovery, status, balance), but lacks features like usage history or streaming support, which are minor gaps.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that bridges MCP clients with local LLM services, enabling seamless integration with MCP-compatible applications through standard tools like chat completion, model listing, and health checks.
      -
    • F
      license
      Not graded
      quality
      Not graded
      maintenance
      High-performance Model Context Protocol server supporting multiple LLM providers (OpenRouter, OpenAI, Groq) with WebSocket API and conversation history persistence.
      -