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. Exposed over MCP by the wso2 mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

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).

Adding it to your client

wso2-docs-mcp-server on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Its toolset

Everything the assistant can do here goes through one of these:

  • search_wso2_docs — Semantic search across all products. Optional product and limit filters
  • get_wso2_guide — Search within a specific product (apim, mi, bi, choreo, is, ballerina, library)
  • explain_wso2_concept — Broad concept search across all products, returns 8 top results
  • list_wso2_products — Returns all supported products with IDs and base URLs
  • Core — The Core tool exposed by this server

Configuration

You will need 6 environment variables: DATABASE_URL, EMBEDDING_PROVIDER, OPENAI_API_KEY, OLLAMA_BASE_URL, GEMINI_API_KEY, VOYAGE_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • 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

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the wso2 mcp server does with a few real requests.

When to reach for it

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Wso2's toolset — search_wso2_docs, get_wso2_guide, explain_wso2_concept and 2 more — is a fair guide to whether it matches your workflow. It is maintained by iamvirul; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

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.
CoreThe Core tool exposed by this server.

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

It connects Wso2 to MCP-compatible AI assistants such as Claude and Cursor, exposing 5 tools (search_wso2_docs, get_wso2_guide, explain_wso2_concept, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Wso2 directly.