Schema | minimax-llm-mcp

minimax-llm-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`TRANSPORT`	No	Transport the server listens on. One of stdio or sse.	stdio
`RETRY_ON_429`	No	Whether to retry once on 429 Too Many Requests with a short back-off.	true
`MINIMAX_API_KEY`	Yes	Bearer token for the MiniMax M3 LLM API.
`REQUEST_TIMEOUT_MS`	No	Per-request timeout when calling the upstream API (in milliseconds).	300000
`MINIMAX_EMBEDDING_ENABLED`	No	Reserved for a future minimax_embed tool (out of scope in 0.1.0).	false

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": true }

Functions exposed to the LLM to take actions

Name	Description
minimax_chatC	Non-streaming chat completion against MiniMax M3. Returns the assistant content plus optional usage.
minimax_completeB	Single-turn text completion against MiniMax M3. Wraps a prompt (plus optional system) into a one-message conversation and returns the assistant content.
minimax_tool_callA	M3-native tool-use passthrough. Forwards `tools` and `tool_choice` verbatim to MiniMax M3 and returns the assistant content plus any proposed tool_calls. When the upstream finishes with finish_reason 'tool_calls', the text content is a structured JSON block with the call list.
minimax_count_tokensB	Local token count for a conversation using the cl100k_base BPE encoding. Returns total, model, encoding, and a per-message breakdown. Does not make a network call.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

A3.5/5.0

Scored 2026-06-25 17:20 across 4 tools

Disambiguation5/5

Each tool has a distinct purpose: chat completion, single-turn completion, local token counting, and tool-use passthrough. No overlap or confusion.

Naming Consistency5/5

All tools follow the consistent pattern 'minimax_<action>' with snake_case, making them predictable and easy to navigate.

Tool Count5/5

4 tools is well-scoped for an LLM server, covering the essential interactions without unnecessary bloat.

Completeness4/5

Covers core LLM operations but lacks streaming support, which is a common expectation for chat completions. Otherwise sufficient.

ActivityInactive

ResponsivenessNo issues