vaspera-pm 2.5.0 → 2.10.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +51 -1
- package/dist/cli.js +5000 -617
- package/dist/cli.js.map +1 -1
- package/dist/server.d.ts +57 -1
- package/dist/server.js +5069 -750
- package/dist/server.js.map +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -39,6 +39,15 @@ VasperaPM is an MCP (Model Context Protocol) server that brings AI-powered produ
|
|
|
39
39
|
- **Test Cases** - Create detailed test plans and acceptance criteria
|
|
40
40
|
- **PM Tool Sync** - Export to Jira, Linear, GitHub, and Azure DevOps
|
|
41
41
|
|
|
42
|
+
### What's New in v2.10
|
|
43
|
+
|
|
44
|
+
All 18 core tools now at **5-star quality** with:
|
|
45
|
+
- Error flow analysis and quality assessments
|
|
46
|
+
- Context-aware scoring and evidence-based confidence
|
|
47
|
+
- Industry-specific compliance checks
|
|
48
|
+
- Interactive setup validation and runnable checklists
|
|
49
|
+
- Three-tier severity classification for PRD reviews
|
|
50
|
+
|
|
42
51
|
---
|
|
43
52
|
|
|
44
53
|
## Quick Start (Zero Friction)
|
|
@@ -92,7 +101,40 @@ npx vaspera-pm install
|
|
|
92
101
|
|
|
93
102
|
---
|
|
94
103
|
|
|
95
|
-
##
|
|
104
|
+
## MCP 2025 Features
|
|
105
|
+
|
|
106
|
+
VasperaPM supports the latest MCP 2025 specification features:
|
|
107
|
+
|
|
108
|
+
### Tool Annotations
|
|
109
|
+
All tools include behavioral metadata hints for better client UX:
|
|
110
|
+
- `readOnlyHint` - Indicates if tool modifies state
|
|
111
|
+
- `destructiveHint` - Warns about destructive operations
|
|
112
|
+
- `idempotentHint` - Whether repeated calls are safe
|
|
113
|
+
- `openWorldHint` - If tool accesses external systems
|
|
114
|
+
|
|
115
|
+
### Structured Outputs
|
|
116
|
+
Key tools return `structuredContent` alongside markdown for programmatic use:
|
|
117
|
+
- `validate_implementation` - Coverage reports with requirements status
|
|
118
|
+
- `explode_backlog` - Array of user stories with estimates
|
|
119
|
+
- `dependency_audit` - Vulnerability findings
|
|
120
|
+
|
|
121
|
+
### Async Tasks (Experimental)
|
|
122
|
+
Long-running tools support async execution with progress tracking:
|
|
123
|
+
|
|
124
|
+
```bash
|
|
125
|
+
# Request async execution with _task: true
|
|
126
|
+
# Tool returns task ID immediately
|
|
127
|
+
# Use tasks_status, tasks_result, tasks_list, tasks_cancel to manage
|
|
128
|
+
|
|
129
|
+
# Async-capable tools:
|
|
130
|
+
# - run_pipeline
|
|
131
|
+
# - verify_docs_code
|
|
132
|
+
# - generate_complete_backlog
|
|
133
|
+
```
|
|
134
|
+
|
|
135
|
+
---
|
|
136
|
+
|
|
137
|
+
## Available Tools (30+ Total)
|
|
96
138
|
|
|
97
139
|
Once installed, these tools are available in Claude Code:
|
|
98
140
|
|
|
@@ -149,6 +191,14 @@ Once installed, these tools are available in Claude Code:
|
|
|
149
191
|
|------|-------------|
|
|
150
192
|
| `run_pipeline` | Orchestrate multi-tool workflows |
|
|
151
193
|
|
|
194
|
+
### Task Management (MCP 2025)
|
|
195
|
+
| Tool | Description |
|
|
196
|
+
|------|-------------|
|
|
197
|
+
| `tasks_status` | Get status of a running task |
|
|
198
|
+
| `tasks_result` | Get result of a completed task |
|
|
199
|
+
| `tasks_list` | List all tasks with filtering |
|
|
200
|
+
| `tasks_cancel` | Cancel a pending or running task |
|
|
201
|
+
|
|
152
202
|
---
|
|
153
203
|
|
|
154
204
|
## API Keys
|