PxDCA - LogicMCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PXDCA_TRANSPORT | No | Glama uses stdio behind mcp-proxy. | stdio |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_requirementsA | 需求書唯一入口。新工作提供 q0；Server 產生並持久化 Q1..Qn。續答提供 session_id 與 answer；只提供 session_id 可在中斷或隔天後查詢並接續。內部生成、驗證、狀態轉移與文件渲染皆為封閉流程。 |
| generate_architectureB | 架構書唯一入口。使用已完成需求書的 session_id；Server 內部完成技術規劃、需求對齊驗證與架構文件渲染。 |
| run_auditB | 稽核唯一入口。使用已完成需求書與架構書的 session_id；Server 內部完成一致性、覆蓋、追溯與風險稽核並產生報告。 |
| generate_skillA | 產生可選的 PxDCA SKILL.md。template 模式輸出 Server canonical 模板；optimized 模式透過 Client LLM Sampling 附加情境化指引，但固定保留兩種 PDCA差異、前三個 Tool 的用途與 session_id 接續規則。此 Tool 不建立需求 session。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool targets a distinct workflow stage: requirements generation, architecture generation, audit, and skill generation. The descriptions explicitly mark each as the unique entry point for its stage, leaving no ambiguity.
All names use a consistent snake_case verb_noun pattern (generate_requirements, generate_architecture, run_audit, generate_skill). The single 'run_' verb for audit is semantically appropriate rather than inconsistent.
Four tools map cleanly onto the PxDCA pipeline stages, with each tool earning its place. The count is well-scoped and not bloated or thin for the stated purpose.
The surface covers the core lifecycle: requirements → architecture → audit, plus an optional skill generator. Minor gaps like no explicit session listing/deletion or document revision tools after completion exist, but the core workflow is complete.