Wso2 Docs Mcp Server

iamvirul/wso2-docs-mcp-server

Built for anyone working with WSO2's ecosystem who needs quick access to API Manager, Micro Integrator, Choreo, and Ballerina documentation without leaving their editor. Uses RAG with pgvector to semantically search across docs, pulling fresh content via GitHub's Git Trees API for repos and falling back to web crawling where needed. The dual-ingestion setup chunks markdown intelligently and generates embeddings through Ollama locally or HuggingFace ONNX as fallback. Exposes semantic search as an MCP tool so Claude, Cursor, or VS Code can query WSO2 docs inline. Solid choice if you're tired of context-switching to browser tabs during integration work or troubleshooting middleware configs.

GitHub stars: 4
tools: 4
auth: Secret needed
transport: STDIO
env vars: 5
last updated: Nov 9, 2026

View on GitHub

Tools

4 tools

Public tool metadata for what this MCP can expose to an agent.

search_wso2_docsSemantic search across all products. Optional `product` and `limit` filters.

Semantic search across all products. Optional `product` and `limit` filters.

No parameter schema in public metadata yet.

get_wso2_guideSearch within a specific product (`apim`, `mi`, `bi`, `choreo`, `is`, `ballerina`, `library`).

Search within a specific product (`apim`, `mi`, `bi`, `choreo`, `is`, `ballerina`, `library`).

No parameter schema in public metadata yet.

explain_wso2_conceptBroad concept search across all products, returns 8 top results.

Broad concept search across all products, returns 8 top results.

No parameter schema in public metadata yet.

list_wso2_productsReturns all supported products with IDs and base URLs.

Returns all supported products with IDs and base URLs.

No parameter schema in public metadata yet.

Configuration

DATABASE_URL*

PostgreSQL connection string for pgvector (e.g. postgresql://user:pass@localhost:5432/wso2docs)

EMBEDDING_PROVIDER

Embedding backend to use: ollama (default, local), openai, gemini, or voyage

OPENAI_API_KEYsecret

Required only when EMBEDDING_PROVIDER=openai

GEMINI_API_KEYsecret

Required only when EMBEDDING_PROVIDER=gemini

VOYAGE_API_KEYsecret

Required only when EMBEDDING_PROVIDER=voyage

Readme

WSO2 Docs MCP Server

"This is an unofficial community project. Not affiliated with or endorsed by WSO2."

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).

Under the hood, it uses a blazing-fast dual-ingestion engine:

GitHub Native: Fetches raw Markdown directly from WSO2's public GitHub repositories via the Git Trees API (avoids web-scraping noise and rate limits)
Web Crawl Fallback: For products without dedicated GitHub docs repos (like the WSO2 Library)

Architecture

System Architecture

Documentation Sources

View the full README on GitHub

Details

Repository: github.com/iamvirul/wso2-docs-mcp-server
Categories: AI & LLM Tools, Search & Web Crawling
Package: wso2-docs-mcp-server
Transport: STDIO
Auth: Required
Registry: MCP registry, active

Related AI & LLM Tools MCP servers

View all

Memographindhar01/memographGraph-based memory system for LLMs with knowledge graphs and semantic search.4stars

CoinRithm Agent Tradingcoinrithm/coinrithm-agent-tradingKeyless prediction-market data across 12 venues plus paper-trading of crypto spot, futures, and PM.4stars

Nervous Systemlevelsofself/mcp-nervous-systemGovernance for LLM agents: 7 enforced rules + read-only reference tools. Safe in any MCP client.4stars

Mif Toolsvarun29ankus/mif-specConvert, validate, and inspect AI agent memories across formats0stars

Vetojigyasudham/veto93 agentic MCP tools + 49 specialist agents for every major AI CLI. Self-learning, no API keys.4stars

signet-evaljmcentire/signet-evalDeterministic policy enforcement and MCP management for AI agent tool calls.4stars