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., "@MCP Excel-PostgreSQL Import sales.xlsx into the 'sales' table"
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.
Este servidor implementa el Model Context Protocol (MCP) para conectar asistentes de IA (como Claude Desktop) con tus datos locales. Permite leer y editar archivos Excel y realizar consultas a bases de datos PostgreSQL de forma segura y directa, facilitando flujos de trabajo de análisis de datos sin necesidad de exportaciones manuales.
Clona el repositorio e instala las dependencias:
npm installCompila el servidor (genera los archivos en dist/):
npm run buildRelated MCP server: Excel MCP Server
Agregar a tu configuración MCP (~/.MPC/mcp.json o Claude Desktop config):
{
"mcpServers": {
"excel-mcp-server": {
"command": "node",
"args": ["/path/to/your/project/dist/main.js"],
"cwd": "/path/to/your/project",
"env": {
"POSTGRES_USER": "your_user",
"POSTGRES_HOST": "localhost",
"POSTGRES_DB": "your_db",
"POSTGRES_PASSWORD": "your_password",
"POSTGRES_PORT": "5432"
}
}
}
}Excel: read_excel, write_excel, update_excel
PostgreSQL: connect_database, execute_query, create_table, insert_data, list_tables, describe_table, get_database_info
Integración: export_to_excel, import_from_excel
Lee un archivo Excel y devuelve los datos en formato JSON
| Name | Required | Description | Default |
|---|---|---|---|
| filePath | Yes | Ruta del archivo Excel | |
| sheetName | No | Hoja a leer (opcional, default: primera) | |
| hasHeaders | No | Primera fila son encabezados |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries full burden. It only states the basic function and does not disclose traits like error handling, size limits, or required permissions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence that is appropriately sized and front-loaded with the purpose. It wastes no words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema, the description adequately mentions the return format (JSON). However, it could be more complete by addressing potential errors or limitations, but the core information is present.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the description adds minimal value beyond what the schema already provides. The description does not elaborate on parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool reads an Excel file and returns data in JSON format, with a specific verb and resource. It distinguishes from the sibling tool write_excel which writes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No when-to-use or when-not-to-use guidance is provided. There is no mention of alternatives or context for selecting this tool over write_excel.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Escribe datos a un archivo Excel
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | Datos a escribir | |
| headers | No | Encabezados | |
| filePath | Yes | Ruta donde guardar | |
| sheetName | No | Nombre de la hoja | Sheet1 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only says 'write data' without disclosing whether it overwrites, appends, requires existing file, or other behavioral traits important for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no filler. It is front-loaded with the core action. Could benefit from slight expansion but is not wasteful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 4 parameters, no output schema, and no annotations, the description is too brief. It lacks details on data format requirements, error handling, or behavior when file exists, which are important for an action tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with basic descriptions for all 4 parameters. The tool description adds no extra semantic value beyond what the schema already provides, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Escribe datos a un archivo Excel' is clear and specific, using a verb ('escribe') and a resource ('archivo Excel'). It directly states the tool's action and distinguishes it from the sibling 'read_excel'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or when-not-to-use guidance is provided. However, the sibling 'read_excel' implies this tool is for writing, so usage context is somewhat clear through tool name contrast.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The two tools have completely distinct purposes: one reads Excel files, the other writes them. There is no possibility of confusion between read_excel and write_excel.
Both tools follow a clear verb_excel pattern (read, write), making the naming predictable and consistent.
Only 2 tools are provided, which is too few given the server name 'Excel-PostgreSQL' implies handling both Excel and PostgreSQL data. Even ignoring the PostgreSQL part, basic Excel operations like listing sheets or modifying specific cells are missing.
The tool surface is severely incomplete for a server claiming to cover both Excel and PostgreSQL. With only read and write for Excel, and no PostgreSQL tools at all, agents will lack essential capabilities.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Connect AI assistants to Google Sheets through controlled tools for reading and updating rows.
AI access to Quadratic spreadsheets: open files, run Python/SQL, query connected databases.
Create and manage documents, spreadsheets, and presentations from your AI assistant.
Gives your AI assistant persistent memory and intelligence about your work patterns.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/joseignaciom5/MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
