Excel MCP Assistant
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EXCEL_INPUT_DIR | No | Host directory for input workbooks. Relative paths are resolved from the server working directory. | ./inputs |
| EXCEL_OUTPUT_DIR | No | Host directory for output workbooks and artifacts. Relative paths are resolved from the server working directory. | ./outputs |
| EXCEL_EXECUTION_IMAGE | No | Docker image used for the restricted execution container. | excel-mcp-executor:latest |
| EXCEL_EXECUTION_TIMEOUT_SECONDS | No | Timeout in seconds for code execution in the restricted Docker container. | 30 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| execute_pythonA | Execute Python for Excel work inside an isolated Docker container. Available libraries: openpyxl, pandas, numpy, matplotlib. Read files from
/inputs and write new or edited files to /outputs. Assign a JSON value to
|
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of overlap or confusion between tools. The tool's purpose is clearly stated as executing Python for Excel work in a Docker container.
The single tool uses a clear verb_noun snake_case convention (execute_python), which is predictable and readable. No other names exist to create inconsistency.
A single tool is too few for a server whose stated purpose is broad Excel assistance. While execute_python is powerful, the lack of specialized helpers (e.g., read_excel, write_excel, list_files) makes the surface feel under-provisioned.
Because execute_python allows arbitrary Python with openpyxl, pandas, numpy, and matplotlib, nearly any Excel operation is possible. Minor gaps exist, such as no native tool for formula evaluation or direct cell queries, but the general purpose tool covers the domain well.