Search and chat with a RAGStack knowledge base through its MCP server, with tools for document uploads and website ingestion.
The RAGStack MCP server connects an assistant to a configured RAGStack knowledge base. It supports document search, chat with source citations, uploads and website-ingestion jobs. The Python package is ragstack-mcp, separate from deploying the RAGStack application itself.
Ask a focused question and inspect the returned sources. Keep document identifiers or citations with the answer so another reader can check the underlying material. Upload and scrape tools add content to the knowledge base; identify the destination and source URLs before requesting ingestion.
Run uvx ragstack-mcp and set RAGSTACK_GRAPHQL_ENDPOINT and RAGSTACK_API_KEY from the RAGStack dashboard. The MCP client connects to that deployment rather than creating an AWS application automatically. Scrape jobs have their own status and scope controls, so starting a job should be followed by checking its result.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| search_knowledge_base | Search indexed knowledge-base content. |
| chat_with_knowledge_base | Ask a question and receive an answer with source citations. |
| start_scrape_job | Start website ingestion with the requested scope. |
| get_scrape_job_status | Inspect a scrape job’s status. |
{
"mcpServers": {
"ragstack-kb": {
"command": "uvx",
"args": [
"ragstack-mcp"
],
"env": {
"RAGSTACK_GRAPHQL_ENDPOINT": "https://YOUR_DEPLOYMENT.appsync-api.YOUR_REGION.amazonaws.com/graphql",
"RAGSTACK_API_KEY": "YOUR_RAGSTACK_API_KEY"
}
}
}
}Replace both placeholders with the endpoint and API key from your RAGStack deployment.
Python and uv for uvx, plus an existing RAGStack GraphQL endpoint and API key from the deployment dashboard.
| Variable | Description | Required |
|---|---|---|
| RAGSTACK_GRAPHQL_ENDPOINT | GraphQL endpoint for the intended RAGStack deployment. | Yes |
| RAGSTACK_API_KEY | API key from the deployment’s dashboard. | Yes |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Enables AI assistants to securely interact with Azure DevOps through a standardized protocol.