DataForSEO MCP wrapper: searchable API docs plus normalized calls to the official server. 4 tools.
This server wraps an external DataForSEO MCP dependency (dataforseo-mcp-server v3.1.1) and exposes 4 tools via STDIO. Tool definitions are generated dynamically from the child process and stored in tool-manifest.json, but the actual schema details are not visible in the provided source code. All 4 tools have extremely minimal descriptions (4-12 chars), far below the 10-1024 char baseline. Parameter descriptions are missing or trivial. No input validation, error recovery guidance, or output schema documentation is evident. The server acts as a transparent proxy with normalization logic, but tool quality is severely compromised by lack of descriptive metadata.
API request
Docs index
Docs sections
Docs search
All tool descriptions are under 20 characters ('API request', 'Docs index', 'Docs sections', 'Docs search'). LLMs cannot determine when/why to select these tools.
docs_index and docs_list_sections have empty input schemas (no properties). Agents cannot understand what these tools accept.
api_request parameter 'data' lacks a type definition (only 'description' present). Agents cannot validate input structure.
No parameter descriptions for 'method' (api_request), 'path' (api_request), or 'url' (docs_search). Agents must guess what values are valid. Missing dependency hints (e.g., 'Call docs_index first to discover available endpoints').
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 33 | 2025-06-18+ | v2 |
No output schema documentation. Agents do not know what fields to expect from api_request, docs_index, docs_list_sections, or docs_search. Breaks downstream tool chaining and forces agents to guess response structure.