apps-script-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| APPS_SCRIPT_BRIDGE_KEY | Yes | The secret key copied from the execution log when running the bridge's setup function. | |
| APPS_SCRIPT_BRIDGE_URL | Yes | The /exec URL of the deployed Apps Script web app bridge. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Edit and run Google Apps Script as the signed-in Google user through a personal web app bridge. Use run_code for one-off snippets (Sheets, Docs, Drive, Gmail, Calendar), and the project tools to read, write and run standalone script projects. Call bridge_status first if anything fails.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": false,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| bridge_statusA | Check the bridge: its version, the Google account it runs as, and whether the Drive service is enabled (needed to create and edit projects). |
| run_codeA | Run Apps Script (JavaScript, V8) as the user and return the result and logs.
|
| list_projectsA | List standalone Apps Script projects in the user's Drive, optionally filtered by a title substring. Scripts bound to a Sheet/Doc/Form are not listed, but work with the other tools when you pass their script ID. |
| create_projectB | Create a standalone Apps Script project with an empty Code file. |
| get_projectA | Get a standalone project's title and every file with its full source.
|
| write_fileA | Create or fully replace one file in a project; other files are kept.
|
| delete_fileB | Delete one file from a project (the appsscript manifest cannot be deleted). |
| run_functionA | Run a top-level function from a project's saved code and return its result and logs. The project's .gs files are loaded into the bridge and executed there, so
it runs as the user but outside the real project: there is no active
document (getActiveSpreadsheet() returns null), and the project's own
libraries, advanced services, script properties and triggers are not
available. Only standalone projects can be loaded. |
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 8 tools
Most tools map to distinct resources/actions (list/create/get project, write/delete file, bridge_status). The only real overlap is run_code vs run_function, both of which execute code, but the descriptions clearly separate ad-hoc bridge execution from invoking a saved top-level function in a project.
Seven of eight tools follow a clean verb_noun snake_case pattern (run_code, list_projects, create_project, get_project, write_file, delete_file, run_function). bridge_status deviates as a noun-first status query, a minor inconsistency but still readable.
Eight tools is well within the sweet spot and each earns its place: bridge health, raw execution, project lifecycle, file lifecycle, and saved-function invocation. Nothing feels padded or missing at the count level.
The project/file lifecycle is largely covered (list, create, get, write, delete file) plus execution paths. The notable gap is delete_project (and project rename/metadata), though the run_code escape hatch with DriveApp access lets an agent work around it.