MCP AI Gateway
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_KEY | Yes | API key | |
| API_FORMAT | Yes | API format | |
| HTTP_PROXY | No | HTTP proxy URL | |
| DESCRIPTION | No | Custom model description | |
| HTTPS_PROXY | No | HTTPS proxy URL | |
| API_ENDPOINT | No | Custom endpoint | |
| DEFAULT_MODEL | No | Default model | |
| ANTHROPIC_VERSION | No | Anthropic API version | |
| DEFAULT_MAX_TOKENS | No | Default max tokens setting | |
| DEFAULT_TEMPERATURE | No | Default temperature setting | |
| OPENAI_ORGANIZATION | No | OpenAI organization ID |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| chat_completionB | Send a chat completion request to the configured AI API provider (ANTHROPIC). Supports parameters like model, messages, temperature, max_tokens, stream, etc. Returns the raw response from the API without format conversion. Custom AI model for enterprise use |
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 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'chat_completion' has a clear, distinct purpose of sending chat completion requests to an AI API provider.
The single tool name 'chat_completion' follows a clear and consistent verb_noun pattern. Since there is only one tool, there is no inconsistency to evaluate, and the naming convention is appropriate for its function.
A single tool is generally too few for a server's purpose, as it limits functionality and may indicate an incomplete or overly narrow scope. For an 'MCP AI Gateway' that presumably handles AI interactions, one tool feels insufficient for typical enterprise use cases.
The tool surface is severely incomplete for an AI gateway domain. While 'chat_completion' covers basic chat requests, there are obvious gaps such as tools for managing models, handling different API providers, processing responses, or supporting other AI tasks beyond chat completions.