Gigasheet

Appends rows to an existing Gigasheet dataset using column letters as keys. Use when you need to add new data rows to a sheet by specifying values for each column position (A, B, C, etc.).

Tool to append data from a source sheet to a target sheet by matching column names. Use when you need to combine data from two existing sheets based on column name matching rather than column IDs. This action matches columns from the source sheet to the target sheet based on column names, with options for case-insensitive matching and trimming whitespace. Unmatched columns can optionally be added as new columns to the target sheet.

Tool to apply generic HTTP enrichment to a Gigasheet dataset. Use when you need to enrich dataset rows by calling external APIs and adding the response data as new columns. This action creates an enrichment job that calls a specified HTTP endpoint for each row (or batch of rows) in your dataset, extracts data from the API responses using JSON paths, and creates new columns with the enriched data. The operation is asynchronous and returns a job handle for monitoring progress. Common use cases: - Enrich customer records by calling a CRM API - Validate email addresses using a validation service - Lookup product details from an external catalog - Geocode addresses using a mapping API - Fetch social media profiles for contact enrichment

Calculate expected credits for a user-defined HTTP enrichment operation. Use this before initiating an enrichment to estimate costs based on the number of rows and columns that will be processed. This tool helps you: - Estimate credit costs before running an enrichment - Understand resource requirements for filtered enrichments - Plan budget for large-scale enrichment operations

Tool to cancel a running enrichment task. Use when you need to stop an in-progress HTTP enrichment job that was previously initiated. This action attempts to cancel an enrichment task identified by its task handle. Cancellation is only possible for tasks that are still in progress (not yet completed or already failed). The task handle is returned when you start an enrichment job using the apply enrichment endpoint.

Tool to check if a source of the given type is available. Use this to verify whether a specific connector integration (e.g., Snowflake, Salesforce) is configured and available for the authenticated user. This updates corresponding connection statuses.

Tool to combine multiple files into a new file. Use when you need to merge several files where column names and types match. Optionally add source filename tracking or append rows to the first file in-place.

Tool to copy a file in Gigasheet. Use when you need to duplicate an existing file/sheet into your library with an optional new name and destination folder.

Tool to count how many duplicates will be removed and how many rows remain when deduplicating. Use when you need to preview the impact of a deduplication operation before executing it, or to understand the number of duplicate rows in a dataset based on specific column combinations.

Tool to count the number of groups matching certain criteria in a Gigasheet dataset. Use when you need to determine how many distinct groups exist based on specified row grouping columns and optional filters. This action is useful for understanding data distribution and cardinality before performing more expensive operations like full group aggregations. It supports advanced features like pivot mode, filtering, and sorting configurations.

Counts rows in a Gigasheet dataset matching specified filter criteria. Returns the number of rows matching the provided filters, groupings, and other parameters. For basic row counting, only the handle and optionally filterModel need to be specified. Advanced features like pivot mode, grouping, and aggregations are available for complex counting scenarios. Common use cases: - Count all rows in a dataset - Count rows matching specific filter conditions - Count grouped rows in pivot tables - Validate filter results before exporting data For detailed information on constructing filter models, refer to the Gigasheet Filter Model Detail Guide at https://gigasheet.readme.io/reference/post_dataset-handle-count-rows

Tool to get total activity count on a given Gigasheet dataset. Use when you need to determine how many activities (creates, updates, deletes) have been performed on a dataset. This action counts activities matching the specified criteria such as time range, users, action types, and categories. Non-blank criteria are AND-ed together, while multi-value fields (Actions, Categories, Users) are OR-ed. Returns the total count of matching activities.

AI analysis assistant for Gigasheet datasets. Use this to ask natural language questions about sheet data and get AI-powered insights. Only available for sheets where you have write permissions. Common use cases: - Get summaries of data patterns and trends - Ask questions about specific columns or values - Request analysis of data relationships - Extract key insights from large datasets Note: Requires write access to the target sheet.

Tool to add a comment to a column in a Gigasheet dataset. Use this when you need to annotate or document a specific column with explanatory text. Optionally notify other users by tagging their email addresses.

Tool to add a comment to a specific cell in a Gigasheet dataset. Use when you need to annotate or add notes to a particular cell location in the sheet.

Tool to add a label column to a Gigasheet dataset with values based on conditional filters. Use when you need to categorize or label rows based on column values. This action creates a new column where each row's label is determined by evaluating filter conditions. Cases are evaluated in order, and the first matching case determines the label. Rows not matching any case receive the defaultLabel (if specified). Before using this tool: 1. Obtain a valid dataset handle using actions like GIGASHEET_POST_UPLOAD_URL or GIGASHEET_GET_DATASET_HANDLE 2. Identify column IDs/names using GIGASHEET_GET_DATASET_HANDLE_COLUMNS 3. Construct appropriate filter models - note that filter values must be strings even for numeric comparisons Example use case: Create a "Priority" column that labels rows as "High" if Amount > 1000, "Medium" if Amount > 100, otherwise "Low".

Tool to create a new column based on a formula input in a Gigasheet dataset. Use when you need to calculate values based on existing columns. This action creates a new column with values computed from a formula. You must reference columns by letter (e.g., 'A', 'B', 'C') using the 'formula' parameter. The 'literalFormula' parameter can be provided alongside 'formula' for documentation purposes to show the human-readable column names, but cannot be used alone. Formula syntax supports: - Column references: A, B, C (required, use column letters) - Arithmetic operations: +, -, *, / - Functions: UPPER(), LOWER(), CONCATENATE(), etc. - Example: "A * 2", "UPPER(B)", "CONCATENATE(B, C)" Before using this tool: 1. Obtain a valid dataset handle using GIGASHEET_POST_UPLOAD_URL or GIGASHEET_GET_DATASET_HANDLE 2. Use GIGASHEET_GET_DATASET_HANDLE_COLUMNS to identify column letters for formula construction 3. Construct the appropriate formula expression based on your calculation needs

Tool to edit a formula column in a Gigasheet dataset. Use when you need to update an existing formula column with a new formula, rename it, or reposition it. The column must already exist and be a formula column created previously.

Tool to calculate a formula preview on a Gigasheet dataset and return sample results with involved column values. Use this action when you need to: - Test a formula expression before applying it to an entire column - Preview formula calculations on sample data - Validate formula syntax and see example outputs - View which columns are involved in the formula computation The action returns sample rows showing the formula result along with the values from columns referenced in the formula. This is useful for validating formulas before creating computed columns or performing bulk calculations.

Tool to add an iterator column to a Gigasheet dataset based on current filters and order. Use when you need sequential row numbers in your data. This action creates a new column with sequential numbers (1, 2, 3, ...) for each row. The numbering respects any applied filters and sort order, making it useful for ranking, indexing, or tracking row positions after data transformations. Before using this tool: 1. Obtain a valid dataset handle using GIGASHEET_POST_UPLOAD_URL or GIGASHEET_GET_DATASET_HANDLE 2. Optionally define filters using filterModel to number only specific rows 3. Optionally specify sort order using sortModel to control the numbering sequence

Tool to create a new liveshare for a Gigasheet dataset. Returns a share ID and URL for accessing the current CSV data in the sheet. Use when you need to generate a shareable link that provides live access to dataset content.

Tool to create a new view for a Gigasheet dataset with a specified name and client state version. Use when you need to save a specific dataset state as a named view for later reference.

Tool to explode JSON data in a column into separate columns. Extracts all keys from JSON objects and creates a new column for each key. Use when you need to flatten nested JSON data in a Gigasheet dataset.

Tool to retrieve ungrouped aggregated values for a Gigasheet file. Returns aggregated data as specified in the request payload, including support for pivot mode, filtering, sorting, and various aggregation functions. Use when you need to compute summary statistics across columns without grouping by specific keys.

Tool to create an empty file in your Gigasheet Library. Use when you need a blank spreadsheet with a specified number of rows and columns.

Tool to create a new folder in your Gigasheet Library. Use when you need to organize datasets by creating a new directory for file storage.

Creates a cross-file lookup to enrich data by matching values between two sheets. Use when you need to pull related data from a reference sheet into your source sheet based on matching column values. This is similar to VLOOKUP in Excel. Before using this tool: 1. Obtain valid handles for both the source and reference datasets 2. Identify the column IDs (A, B, C, etc.) in both sheets using GIGASHEET_GET_DATASET_HANDLE_COLUMNS 3. Ensure the columns you're matching have compatible data types The lookup will create a new column in the source sheet with values from the reference sheet where matches are found.

Tool to interact with Gigasheet Sheet Assistant via the Model Context Protocol (MCP) over HTTP. Use when you need to query or manipulate sheet data through MCP-compatible LLM tools. This endpoint implements JSON-RPC 2.0 protocol and supports MCP methods like 'tools/list' (to discover available tools) and 'tools/call' (to execute specific tools). The Sheet Assistant can perform operations like querying data, analyzing sheets, and other data manipulation tasks.

Tool to split a column into multiple columns based on a separator. Use when you need to divide column values into separate columns in a Gigasheet dataset.

Tool to delete Sheet Assistant chat history for a specific sheet. Use when you need to clear all AI assistant conversation logs associated with a sheet handle.

Tool to delete multiple columns from a Gigasheet dataset by their column names. Use when you need to remove specific columns from a sheet.

Tool to delete a connector source for the authenticated user. Use when you need to remove an integration connection such as Salesforce, S3, or Google Sheets from Gigasheet.

Tool to delete a comment from a cell in a Gigasheet dataset. Use this when you need to remove a specific comment that was previously added to a cell. The comment ID can be obtained using the list comments action.

Deletes rows in a Gigasheet dataset that do NOT match the specified filter criteria. Use this when you want to keep only the rows that match a filter and remove everything else. The filter uses Conjunctive Normal Form (CNF) where conditions can be combined with AND/OR logic.

Tool to delete duplicated rows from a Gigasheet dataset based on specified columns and sort model. Use when you need to remove duplicate entries identified by matching values in one or more columns. When multiple rows have identical values in the specified columns, the sort model determines which row to keep (if not specified, default sheet row order is used). Optionally apply a filter to deduplicate only a subset of rows.

Tool to delete selected rows from a Gigasheet dataset. Use when you need to remove specific rows identified by their row IDs (iterator numbers). Row IDs are subject to change, so it's best practice to obtain them immediately before deletion using a query or list action.

Tool to delete rows in a Gigasheet dataset that match a specified filter. Use when you need to remove specific rows based on filter criteria. The filterModel uses Conjunctive Normal Form (CNF) structure with column identifiers, filter values, and match conditions.

Tool to delete a specific view from a Gigasheet dataset. Use when you need to remove a saved view from a dataset. Requires both the dataset handle and the view handle to identify the view to delete.

Tool to delete a live share of a Gigasheet dataset. Use when you need to revoke or remove an existing live share link. The shareid is the unique identifier of the live share to be deleted.

Deletes a Gigasheet sheet or folder by its unique handle identifier. For sheets, this permanently removes the dataset. For folders, use recursive=True to delete the folder along with all its contents (sheets and subfolders), or omit/set to false to delete only empty folders. The handle can be obtained from sheet URLs or from create/upload operations.

Tool to delete a single column from a Gigasheet sheet by its column identifier. Use when you need to permanently remove a specific column from a sheet.

Tool to delete a saved filter template by its unique handle. Use when you need to remove a persisted filter configuration that is no longer needed.

Tool to delete multiple columns from a Gigasheet file. Use when you need to remove specific columns from a sheet by their identifiers.

Tool to retrieve rows from a Gigasheet file matching specified filter criteria. Use when you need to query or extract data from a sheet with optional filtering, sorting, and pagination. For basic filtering, only the filterModel field needs to be specified.

Generates an AI-powered description for a Gigasheet dataset. Use this when you need to automatically create a summary or description of a dataset's content and structure based on its data.

Tool to retrieve AI chat history for a sheet. Returns up to 20 most recent messages exchanged with the sheet assistant. Use when you need to review previous AI interactions or understand the conversation context for a specific sheet.

Tool to get comments for a specific cell in a Gigasheet dataset. Use when you need to retrieve comments that have been added to a particular cell at the intersection of a column and row.

Retrieves the current client-state version and timestamp for a specified sheet. The version identifier is used when creating or updating views and saved states. Call this action after obtaining a sheet handle to get the latest version before performing state-related operations.

Tool to get connection parameters for a specific connector. Use when you need to discover what parameters are required to set up a connector integration.

Tool to retrieve connection parameters for a specific connector type. Use when you need to discover what parameters are required to configure a data source connection.

Tool to list connector connections. Use after setting a valid Gigasheet API token.

Tool to retrieve information about connected data sources for the user. Returns a list of data sources with their type, status, and folder location. Use after setting a valid Gigasheet API token.

Tool to get parameters required for a specific connector source type. Use when configuring a data source connection to understand what information needs to be collected from the user.

Tool to get comments for a specific column in a dataset sheet. Use when you need to retrieve comments that have been added to a particular column.

Retrieves comprehensive metadata for a specific dataset in Gigasheet. This tool fetches detailed information about a dataset including its processing status, file properties, column structure, owner information, and more. Use this after uploading a file or when you have a valid dataset handle to get its current state and schema. Common use cases: - Check if a dataset has finished processing (Status field) - Get column names and data types for the dataset - Retrieve file size, row count, and creation timestamps - Verify dataset ownership and access

Tool to list all column metadata (IDs, names, types) for a dataset. Use after obtaining a dataset handle.

Tool to retrieve the download URL for an exported dataset. Use after initiating an export and obtaining its handle.

Tool to retrieve CSV data from a Gigasheet liveshare. Returns the current data in text CSV format. Use when you need to export or access shared dataset data via a liveshare link.

Tool to retrieve a dataset's note by handle. Use this to get AI-generated or user-provided descriptions of a dataset.

Tool to retrieve organization file permissions for a dataset. Use when you need to check what permissions the requester's organization has on a specific file. This action returns permissions only for the same organization that the requester is a member of. The permissions are returned as a list of integers representing different permission levels.