Schema | WSO2 Docs MCP Server

WSO2 Docs MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`CHUNK_SIZE`	No	Approximate tokens per chunk	800
`DATABASE_URL`	Yes	PostgreSQL connection string (required)
`CHUNK_OVERLAP`	No	Overlap tokens between chunks	100
`TOP_K_RESULTS`	No	Default search result count	10
`GEMINI_API_KEY`	No	Required if EMBEDDING_PROVIDER=gemini
`OPENAI_API_KEY`	No	Required if EMBEDDING_PROVIDER=openai
`VOYAGE_API_KEY`	No	Required if EMBEDDING_PROVIDER=voyage
`OLLAMA_BASE_URL`	No	Ollama server URL	http://localhost:11434
`CACHE_TTL_SECONDS`	No	In-memory query cache TTL	3600
`CRAWL_CONCURRENCY`	No	Concurrent HTTP requests during crawl	5
`EMBEDDING_PROVIDER`	No	Embedding provider: ollama \| openai \| gemini \| voyage	ollama
`EMBEDDING_DIMENSIONS`	No	Must match model output dimensions	768
`GEMINI_EMBEDDING_MODEL`	No	Gemini model	text-embedding-004
`OLLAMA_EMBEDDING_MODEL`	No	Model pulled and used via Ollama	nomic-embed-text
`OPENAI_EMBEDDING_MODEL`	No	OpenAI model	text-embedding-3-small
`VOYAGE_EMBEDDING_MODEL`	No	Voyage model	voyage-3
`HUGGINGFACE_EMBEDDING_MODEL`	No	ONNX fallback when Ollama is not running	Xenova/nomic-embed-text-v1

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityActive

ResponsivenessNo issues