Schema | moe-mcp

moe-mcp

Describes the environment variables required to run the server.

Name	Required	Description
`AWS_REGION`	Yes	AWS region for Bedrock (must support Cohere Embed v4, Rerank 3.5, and Claude, e.g., us-west-2)
`QDRANT_URL`	Yes	Qdrant Cloud cluster URL (e.g., https://xyz.us-west-1-0.aws.cloud.qdrant.io)
`QDRANT_API_KEY`	Yes	Qdrant Cloud API key
`AWS_ACCESS_KEY_ID`	Yes	AWS access key ID for Bedrock access
`AWS_SECRET_ACCESS_KEY`	Yes	AWS secret access key for Bedrock access

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
ask_expertsA	Ask the mixture of domain experts a question. The server routes the question to the most relevant expert knowledge base(s), runs hybrid retrieval + reranking, and returns the best-supported passages. EACH passage includes a citation (title, author, location). You MUST cite these sources in your answer using their bracket numbers, and answer only from them. Args: question: The natural-language question. top_k: Max passages to return (default 8). experts: Optional list of expert names to force; omit to auto-route. synthesize: If true, the server also returns a grounded, cited answer string.
list_expertsA	List the available domain experts and how much each one knows.
get_sourceB	Fetch metadata about a cited source (to expand or verify a citation).

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
`experts_resource`	Browsable list of experts.

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tiennt235/moe'

If you have feedback or need assistance with the MCP directory API, please join our Discord server