Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mirador-mcp What was our monthly sales trend for this year?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Adaptador MCP delgado para Mirador Core. Expone tools MCP sobre la Core Internal API (/internal/core/*) sin base de datos, sin llaves OpenAI y sin lógica de negocio propia.
MCP_API_KEY: token Bearer que deben enviar los clientes MCP.
CORE_INTERNAL_URL: URL interna de mirador-core en Railway.
CORE_SERVICE_TOKEN: token service-to-service aceptado por el core.
PORT: puerto HTTP, por defecto 3000.
Related MCP server: mysql-mcp-zag
pnpm install
pnpm devHealthcheck:
curl http://localhost:3000/healthzEndpoint MCP: http://localhost:3000/mcp con header Authorization: Bearer <MCP_API_KEY>.
ask_company_data
describe_business_schema
run_readonly_query
generate_chart_spec
search_company_knowledge
suggest_executive_questions
Todas las tools de datos delegan en POST /internal/core/ask; el catálogo delega en GET /internal/core/schema-catalog.
railway.json usa Nixpacks, pnpm start y healthcheck en /healthz. En producción, CORE_INTERNAL_URL debe apuntar al hostname privado de Railway del core.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
Unified gateway exposing 150+ tools across all NexGenData MCP servers via one endpoint.
Query, browse, and automate OmegaAI workspaces from any MCP client. Streamable HTTP with OAuth 2.0.
Query, join, profile, clean and convert CSV/JSON/Parquet with server-side DuckDB over MCP.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/C3SC0-V4113/Mirador-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
