MCP server for OpenServ agent development assistance, providing tools for no-code, SDK, and API-based agent development with documentation and resource access
OpenServ MCP exhibits severe definition quality gaps across all 10 tools. All tools lack parameter descriptions entirely, even the single-parameter 'agentDevelopmentAssistant' provides no guidance on what 'method' or 'language' mean to an LLM. Nine of ten tools have empty input schemas (no properties), making them non-functional for agent reasoning. Descriptions are present but generic (10 - 50 chars), below the 50 - 200 char baseline for LLM-optimized tools. No output schemas are documented. Tool names lack action verbs (e.g., 'mainDocumentation' vs 'get_documentation'). No error handling, validation, or recovery guidance. This server would require substantial rework before production use.
Assist with OpenServ agent development based on user requirements
Provides documentation for the Agent Starter SDK
Provides the OpenServ API documentation
Provides examples of using the OpenServ API in Python and TypeScript
Provides the API tutorial for OpenServ
Provides the main documentation for OpenServ
Provides information about the No-Code Builder for OpenServ
Nine of ten tools have empty input schemas (properties: {}). LLMs cannot reason about parameters or constraints when schemas are absent. Tools become non-functional for agent planning.
All tool names lack action verbs. 'mainDocumentation', 'sdk', 'apiDocs' do not convey what action occurs when called. LLMs infer intent from verb-noun naming (get_*, list_*, fetch_*). Current names are noun-only and ambiguous.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 27 | 2026-07-28+ | v2 |
Provides the OpenServ SDK repository
Provides examples of OpenServ agents built with the SDK in TypeScript and Python
Get the Agent Starter template repository in TypeScript for OpenServ
No parameter descriptions provided. 'agentDevelopmentAssistant' has 'method' and 'language' parameters with no descriptions explaining what values are valid, when to use each, or what they control. LLMs cannot infer parameter semantics from names alone.
No output schemas documented. Tools return unstructured content (text blobs from crawled URLs). LLMs cannot plan downstream tool calls or extract structured data without knowing response field names and types.
Tool descriptions are generic and under 50 characters (baseline 50 - 200 chars for LLM optimization). E.g., 'Provides the main documentation for OpenServ' (45 chars) lacks context on when to call this vs other doc tools or what structure is returned.