autocomplete_action
ChatGPTResolve autocomplete options for a connector action (HubSpot object types, Slack channels, Metabase questions, …). Pass slug from search_actions.autocompletes. Resolve params to concrete values first — do not pass $this expression paths. Put chosen values in execute_action data, not action.config.
browse_context
ChatGPTList the files and folders at a path in the workspace context. Pass depth -1 with no path for the full tree in one call. Navigates structure without reading any content.
describe_model
ChatGPTReturn a model's columns, dataset slug, and unquoted dataset.model reference without querying rows.
execute_action
ChatGPTRun one action on a single input. Creates a run and consumes credits. If the result is outcome executing, poll with get_run. Do not loop this over a list — use execute_action_batch.
execute_action_batch
ChatGPTRun one action over many records in a single batch. Cheaper and observable than looping execute_action. If the result is outcome executing, poll with get_batch.
get_action_schema
ChatGPTResolve the input and output JSON schemas of a connector, native, tool, or agent action without executing it. Pass the action object from search_actions. For connector fields that need a picked id (list, object type, campaign), call autocomplete_action.
get_batch
ChatGPTGet one batch by uuid. If execute_action_batch returned outcome "executing", call this until the batch has finished. A finished batch includes one page of the CSV in data.text. Pass offset and limit to read further pages (limit default 100, max 100). If truncated is true, call again with the next offset. totalRows is the total when this page reaches the end of the file. Read data.text. Do not fetch the URL. Does not return the raw batch record or internal storage keys.
get_run
ChatGPTGet one run by uuid. Returns the same shape as execute_action: the last node output, run uuid, and credits used. If execute_action returned outcome "executing", call this until the run has finished. Does not return computed configs, execution traces, or other debug payloads.
get_usage
ChatGPTCredit usage for the last 7 days, grouped by integration. Check this before running paid actions.
list_models
ChatGPTList data models in this workspace. Use describe_model then query_models.
list_runs
ChatGPTList recent ad-hoc action runs in this workspace. Does not include play or tool workflow runs.
map_context
ChatGPTList every indexed file in the workspace context (path, title, summary, folder) without reading any file body. The context is the workspace's knowledge base — playbooks, ICP definitions, scoring rubrics, internal docs. Start here to discover what exists, then search_context or read_context for the parts the task needs. This surface is read-only; write through the workspace's context capability.
query_models
ChatGPTRun one read-only SQL SELECT over this workspace's models. Reference a model as dataset.model — take the exact reference from describe_model. Joins, aggregates and CTEs are allowed; anything other than SELECT is refused. Aggregate rather than paging: the row cap is small.
read_context
ChatGPTRead a UTF-8 file from the workspace context. Reads with no endLine return only the first 250 lines and set truncated; pass a 1-indexed inclusive startLine/endLine range to page through the rest or target a section. The response always carries totalLines.
search_actions
ChatGPTSearch actions you can run: integration catalog (connector), Cargo native, workspace tools, and agents. Each result includes autocompletes when input fields need a picked id. Use the returned action with execute_action or execute_action_batch, get_action_schema, and autocomplete_action. Never fan out execute_action record-by-record — use execute_action_batch.
search_context
ChatGPTSearch context file contents and return matching lines (path, line number, snippet), never whole files. At most 5 matches per file, so results spread across files. Use it to locate a term, then read_context a tight range around the hits.
whoami
ChatGPTReturn the signed-in user, the workspace this MCP session is bound to, and a plan/credits snapshot.
autocomplete_action
Claudebrowse_context
Claudedescribe_model
Claudeexecute_action
Claudeexecute_action_batch
Claudeget_action_schema
Claudeget_batch
Claudeget_run
Claudeget_usage
Claudelist_models
Claudelist_runs
Claudemap_context
Claudequery_models
Clauderead_context
Claudesearch_actions
Claudesearch_context
Claudewhoami
Claude
