Chat with AI via CLI - An interactive AI chat interface powered by Pi agent framework
This MCP server has critical definition quality gaps. Two tools are defined with only names and minimal descriptions (both under 20 characters, triggering hard score caps). No input schemas are visible in the provided source code. Tool names ('tools', 'testTool') are generic and non-standard (camelCase instead of snake_case verb_noun pattern). No parameter descriptions or structured output schemas are documented. The server appears to be primarily a CLI chat application that exposes basic MCP functionality, but the tool definitions lack the rigor required for LLM integration.
Execute a skill within the main conversation. <skills_instructions> When users ask you to perform tasks, check if any of the available skills below can help complete the task more effectively. Skills provide specialized capabilities and domain knowledge. How to use skills: - Invoke a skill by passing its name as the "command" parameter, e.g. {"command": "readlink"} - The response includes the skill's base directory, a list of files inside the skill, and the SKILL.md content - To read a specific file inside a skill, use {"command": "<skill-name>:<relative-file-path>"}, e.g. {"command": "readlink:clean_markdown.lua"} - Only use skills listed in <available_skills> below </skills_instructions>
No input schemas visible for any tool. Cannot verify parameter types, constraints, or validation rules.
Tool descriptions are trivial (< 20 chars: 'List available MCP tools', 'Test MCP tools'). Descriptions must explain WHAT, WHEN, and WHY, not just name the action.
Tool names violate verb_noun convention. 'tools' and 'testTool' are not action verbs (should be list_tools, test_tools in snake_case). Generic names like 'tools' and non-standard camelCase reduce discoverability for LLMs.
No output schema documented. LLMs cannot plan follow-up actions without knowing what fields are returned or their types.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-22 | F | 11 | 2026-07-28+ | v2 |
| 2026-03-09 | F | 9 | - | v1 |
No parameter descriptions or types visible. Even if parameters exist, they are not self-documenting for LLMs.
No error handling guidance. No recovery hints, categorization, or actionable error messages documented.