Wso2 Docs MCP Server runs on your own machine — the client starts it, so there is no endpoint to ping. 138 installs a week from npm. Last commit 31 Oct 2026.
Semantic search over WSO2 docs (APIM, IS, MI, Choreo, Ballerina) via RAG and pgvector.
Today is the operative word: we check Wso2 Docs MCP Server every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add wso2-docs-mcp-server -e 'DATABASE_URL=<DATABASE_URL>' -- npx -y wso2-docs-mcp-server
{
"mcpServers": {
"wso2-docs-mcp-server": {
"command": "npx",
"args": [
"-y",
"wso2-docs-mcp-server"
],
"env": {
"DATABASE_URL": "<DATABASE_URL>"
}
}
}
}
[mcp_servers.wso2-docs-mcp-server]
command = "npx"
args = ["-y", "wso2-docs-mcp-server"]
env = { DATABASE_URL = "<DATABASE_URL>" }
{
"mcpServers": {
"wso2-docs-mcp-server": {
"command": "npx",
"args": [
"-y",
"wso2-docs-mcp-server"
],
"env": {
"DATABASE_URL": "<DATABASE_URL>"
}
}
}
}
{
"servers": {
"wso2-docs-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"wso2-docs-mcp-server"
],
"env": {
"DATABASE_URL": "<DATABASE_URL>"
}
}
}
}
Put your own value in place of
<DATABASE_URL> (PostgreSQL connection string for pgvector (e.g. postgresql://user:pass@localhost:5432/wso2docs)).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
EMBEDDING_PROVIDER (Embedding backend to use: ollama (default, local), openai, gemini, or voyage), OPENAI_API_KEY (Required only when EMBEDDING_PROVIDER=openai), GEMINI_API_KEY (Required only when EMBEDDING_PROVIDER=gemini), VOYAGE_API_KEY (Required only when EMBEDDING_PROVIDER=voyage).
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
IT Glue MCP server for MSPs — documents, flexible assets, semantic vector search, RBAC, and BYOK
IT Glue MCP server for MSPs — documents, flexible assets, semantic vector search, RBAC, and BYOK
Web design analysis with 26 MCP tools: layout, motion, quality, semantic search via pgvector
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
Shared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).
Docs + source RAG for Pipe language: semantic search, cited answers, code symbol lookup.
Team engineering memory for AI coding assistants. 47 MCP tools, pgvector semantic search.
Answers built from our own checks of this server.