What dependencies does Strands Mcp require?
Strands Mcp requires Docker (for Elasticsearch/Kibana), Python, and Playwright (with Chromium browser) for the scraper. The MCP server uses Python and communicates with Elasticsearch.
@ShawnKyzer
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"strands-agents-docs": {
"command": "python",
"args": [
"-u",
"mcp_server/main.py"
],
"cwd": "/your_local_directory/strands-mcp",
"env": {
"ELASTICSEARCH_URL": "http://localhost:9200"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Strands Mcp is an MCP (Model Context Protocol) server that scrapes the Strands Agents documentation (v1.1.x) and indexes it in Elasticsearch, making it searchable for Amazon Q Developer and integrable with the Windsurf IDE.
Start Elasticsearch and Kibana with docker-compose up -d. Install dependencies (pip or uv), install Playwright browsers, and run the scraper (python scraper/main.py). Then start the MCP server (python mcp_server/main.py) on port 8000. Configure Amazon Q or Windsurf using the provided integration guides (AMAZON_Q_INTEGRATION.md or WINDSURF_INTEGRATION.md).
strands-agents-docsStrands Mcp requires Docker (for Elasticsearch/Kibana), Python, and Playwright (with Chromium browser) for the scraper. The MCP server uses Python and communicates with Elasticsearch.
Set the environment variable `ELASTICSEARCH_URL` (default `http://localhost:9200`) when running the scraper or MCP server. The default index name is `strands-agents-docs`.
The scraper crawls the official Strands Agents documentation hosted at `https://strandsagents.com/latest/documentation/docs/`.
Elasticsearch runs on port 9200, Kibana on port 5601, and the MCP server on port 8000. The Windsurf integration uses stdio transport.
The MCP server and scraper can run locally without Docker, but Elasticsearch must be available separately (e.g., via Docker or a remote instance). The provided `docker-compose.yml` starts Elasticsearch and Kibana.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
MCP Toolbox for Databases is an open source MCP server for databases.

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
A curated list of references for MLOps
Painless E2E Automation for Mobile and Web
Comments