Hosted DataForSEO MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Scored across 4 tools
execute_action and query_data have near-identical descriptions — both are labeled 'Step 3 (FINAL) of workflow', both mandate the same two prerequisite calls, and both end with 'construct the action/query body, follow the schema exactly.' An agent cannot reliably tell when to execute an action versus query data, which is a serious boundary failure. prompts_menu and query_contexts are clearer, but the core pair overlaps badly.
Three tools follow a verb_noun shape (execute_action, query_contexts, query_data) but prompts_menu inverts it to noun_noun, and the 'query' prefix is reused for both a discovery helper and a terminal data fetch. Readable overall, but the reuse of 'query' actively worsens the execute_action/query_data confusion rather than clarifying it.
Four tools for a discover → inspect → execute workflow plus a prompt catalog is a sensible, compact surface with no filler. The only concern is that the small count is achieved partly by making every tool a generic 'request' router, which pushes complexity into a string parameter rather than the tool set.
The workflow lifecycle (accounts → actions_details → execute/query) is covered, but the actual domain surface is opaque: the set of available actions/tables is only discoverable at runtime, so an agent cannot verify coverage from the tool list. There is no visible handling for failures, pagination, or non-data operations, leaving notable gaps if a call misbehaves.
Execute DataForSEO action (Step 3 (FINAL) of workflow).
REQUIRED: Complete these steps first using query_contexts:
request='accounts' - Get workspace_id, brand_id AND available_actions
request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] - Get detailed body structure for specific action(s) using actions from available_actions
IMPORTANT: Always call step 2 to see the exact body structure before executing.
Rely on info from steps 1-2 to construct the action body. Follow the schema exactly.
Inputs: body (required). Returns: object
Helper for planning InsightfulPipe DataForSEO data queries.
Step 1: request='accounts' – Retrieve workspace_id, brand_id, other source metadata, AND available_actions (all tables you can query).
Step 2: request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] – REQUIRED before querying. Replace with actions from available_actions to get the exact request body, required identifiers, fields, time ranges, and notes for each action.
Optional: request='available_actions' – Standalone call to list all available tables/actions (already included in accounts response).
Optional: request='brands' with brand_id + workspace_id to pull brand guidelines.
Inputs: request (required), actions, brand_id, platform, +1 more. Returns: object
Query DataForSEO data (Step 3 (FINAL) of workflow).
REQUIRED: Complete these steps first using query_contexts:
request='accounts' - Get workspace_id, brand_id AND available_actions
request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] - Get detailed body structure for specific action(s) using actions from available_actions
IMPORTANT: Always call step 2 to see the exact body structure before querying.
Rely on info from steps 1-2 to construct the query body. Follow the schema exactly.
Inputs: body (required). Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Hosted Google Ads MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Hosted Web Crawler MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Hosted Meta Ads MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Hosted WordPress MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Add one secure layer between your agents and this server.
