Grist MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GRIST_API_KEY | Yes | Your Grist API key, used for authentication. | |
| GRIST_BASE_URL | Yes | The base URL for your Grist instance (e.g., https://docs.getgrist.com). |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| grist_get_workspacesA | List workspaces with filtering. Use browse mode ({limit: 20}) to see all, or search mode ({name_contains: "Sales"}) to filter. Detail levels: summary Example: {"limit":20,"detail_level":"summary"} Use grist_help({tools:["grist_get_workspaces"]}) for full schema. |
| grist_get_documentsC | Find documents by ID (fastest), name search, workspace filter, or browse all. Detail levels: summary (name, id, workspace, access ~50 tokens/doc) or d Example: {"docId":"qBbArddFDSrKd2jpv3uZTj"} Use grist_help({tools:["grist_get_documents"]}) for full schema. |
| grist_get_tablesC | Get table structure and schema. Detail levels: names (table IDs only ~20 tokens/table), columns (+ column names ~50 tokens/table), or full_schema (+ t Example: {"docId":"abc123","detail_level":"names"} Use grist_help({tools:["grist_get_tables"]}) for full schema. |
| grist_query_sqlA | Execute SQL queries for JOINs, aggregations, and complex filters. Use grist_get_records for single-table queries without SQL. Supports parameterized q Example: {"docId":"abc123","sql":"SELECT c.Name, o.Total FROM Customers c JOIN Orders o ON c.id = o.Customer"} Use grist_help({tools:["grist_query_sql"]}) for full schema. |
| grist_get_recordsA | Fetch records with filters. No SQL needed. Use grist_query_sql for JOINs and aggregations. Filter syntax: {"Status": "Active"}, {"Priority": 1}, {"IsA Example: {"docId":"abc123","tableId":"Contacts","filters":{"Status":"Active"}} Use grist_help({tools:["grist_get_records"]}) for full schema. |
| grist_manage_recordsB | CRUD for records: add, update, delete, upsert. Batched operations execute sequentially for cross-table dependencies. Use natural formats (no "L" prefi Example: {"docId":"abc123","operations":[{"action":"add","tableId":"Contacts","records":[{"Name":"Alice","Email":"alice@example.com"}]}]} Use grist_help({tools:["grist_manage_records"]}) for full schema. |
| grist_manage_schemaC | Batch schema operations: tables (create/rename/delete), columns (add/modify/remove), and summary tables. Ref columns need refTable. Summary tables aut Use grist_help({tools:["grist_manage_schema"]}) for full schema. |
| grist_manage_pagesC | Declarative page layouts with cols/rows splits. create_page returns sectionIds; use link_widgets to connect. Actions: create_page, set_layout, link_wi Use grist_help({tools:["grist_manage_pages"]}) for full schema. |
| grist_create_documentA | Creates a new Grist document in a workspace. Optionally fork an existing document to copy its structure and data. Returns the new document ID and URL. Example: {"name":"Customer CRM","workspaceId":123} Use grist_help({tools:["grist_create_document"]}) for full schema. |
| grist_manage_webhooksB | Batch webhook CRUD for real-time notifications. list and clear_queue must be solo operations. Example: {"docId":"abc123","operations":[{"action":"create","fields":{"url":"https://api.example.com/hook","tableId":"Tasks","eventTypes":["add"]}}]} Use grist_help({tools:["grist_manage_webhooks"]}) for full schema. |
| grist_helpA | Discover available tools and get detailed documentation with JSON schemas. Call without params to list all tools. Use tools param for full docs + sche Example: {} Use grist_help({tools:["grist_help"]}) for full schema. |
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 11 tools
Each tool targets a distinct operation: document CRUD, record retrieval via filters or SQL, workspace listing, schema and page management, webhooks, and help. The only potential overlap is between grist_get_records and grist_query_sql, but their descriptions clearly differentiate simple filtering from complex SQL joins.
All tools consistently follow the 'grist_verb_noun' pattern (e.g., grist_create_document, grist_manage_records, grist_query_sql). The naming is uniform and predictable across the set, with no mixed conventions like camelCase or random verbs.
With 11 tools, the server is well-scoped for a Grist integration. It covers essential operations for documents, records, schema, pages, webhooks, and queries without excessive granularity or unnecessary overlap.
The tool surface covers most lifecycle operations: creating and reading documents, full CRUD for records, schema modifications, page layout, and webhook management. Notably missing are update and delete for documents, and workspace modification, but these are minor gaps for typical workflows.