Wso2 MCP Server

Semantic search over WSO2 docs (APIM, MI, Choreo, Ballerina) via RAG and pgvector.

Local serverstdio

What is the Wso2 MCP Server?

Semantic search over WSO2 docs (APIM, MI, Choreo, Ballerina) via RAG and pgvector.

What it actually does

A production-ready Model Context Protocol (MCP) server that provides AI assistants (Claude Desktop, Claude Code, Cursor, VS Code) with semantic search over WSO2 documentation via Retrieval-Augmented Generation (RAG).

Configuration

  • Node.js ≥ 20 - Docker (for pgvector) - Embeddings - no API key required by default: - Ollama (recommended) - runs locally, model auto-downloaded on first run - If Ollama is not running, the server automatically falls back to HuggingFace ONNX (in-process, also downloads automatically) - Cloud providers are also supported: OpenAI, Google Gemini, Voyage AI

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

ToolWhat it does
search_wso2_docsSemantic search across all products. Optional product and limit filters.
get_wso2_guideSearch within a specific product (apim, mi, bi, choreo, is, ballerina, library).
explain_wso2_conceptBroad concept search across all products, returns 8 top results.
list_wso2_productsReturns all supported products with IDs and base URLs.

How to install the Wso2 MCP Server

{
  "mcpServers": {
    "wso2-docs": {
      "command": "node",
      "args": ["/ABSOLUTE/PATH/TO/wso2-docs-mcp-server/dist/src/index.js"],
      "env": {
        "DATABASE_URL": "postgresql://wso2mcp:wso2mcp@localhost:5432/wso2docs",
        "EMBEDDING_PROVIDER": "ollama"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Node.js ≥ 20 - Docker (for pgvector) - Embeddings - no API key required by default: - Ollama (recommended) - runs locally, model auto-downloaded on first run - If Ollama is not running, the server automatically falls back to HuggingFace ONNX (in-process, also downloads automatically) - Cloud providers are also supported: OpenAI, Google Gemini, Voyage AI
VariableDescriptionRequired
DATABASE_URLEndpoint or connection string the server talks to.Yes
EMBEDDING_PROVIDERConfiguration value read at startup.Optional
OPENAI_API_KEYCredential the server authenticates with.Yes
OLLAMA_BASE_URLEndpoint or connection string the server talks to.Yes
GEMINI_API_KEYCredential the server authenticates with.Yes
VOYAGE_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • “Use Wso2 to search wso2 docs.”
  • “Use Wso2 to get wso2 guide.”
  • “Use Wso2 to explain wso2 concept.”

Frequently asked questions

Semantic search over WSO2 docs (APIM, MI, Choreo, Ballerina) via RAG and pgvector. Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.