@triedotdev/mcp 1.0.29 → 1.0.31

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.
Files changed (2) hide show
  1. package/README.md +66 -12
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -88,6 +88,16 @@ claude mcp add Trie --scope user -- npx @triedotdev/mcp
88
88
 
89
89
  **Restart Claude Code after adding the MCP server.**
90
90
 
91
+ ### Other MCP-Compatible Tools
92
+
93
+ Trie works with any MCP-compatible AI tool (OpenCode, Windsurf, etc.). Configure your tool to run:
94
+
95
+ ```bash
96
+ npx @triedotdev/mcp
97
+ ```
98
+
99
+ Trie auto-detects which tool is running and adapts its output format accordingly.
100
+
91
101
  ---
92
102
 
93
103
  ## Usage
@@ -120,14 +130,11 @@ Trie works in two modes:
120
130
 
121
131
  **Enable AI mode:**
122
132
 
123
- ```bash
124
- # Environment variable
125
- export ANTHROPIC_API_KEY=sk-ant-...
133
+ **For MCP usage (Cursor/Claude Code):**
126
134
 
127
- # Or add it to your project (recommended for CLI usage)
128
- echo 'ANTHROPIC_API_KEY=sk-ant-...' >> .env.local
135
+ Add the API key to your MCP configuration:
129
136
 
130
- # Or in MCP config (Cursor / MCP tools)
137
+ ```json
131
138
  {
132
139
  "mcpServers": {
133
140
  "Trie": {
@@ -141,8 +148,28 @@ echo 'ANTHROPIC_API_KEY=sk-ant-...' >> .env.local
141
148
  }
142
149
  ```
143
150
 
144
- > **Important:** The `env` you set in Cursor’s MCP config is only inherited by the **MCP server process** that Cursor launches.
145
- > It does **not** automatically apply to standalone terminal commands like `trie-agent scan` unless your shell/project environment also has `ANTHROPIC_API_KEY`.
151
+ **For CLI usage (terminal/CI):**
152
+
153
+ Add the API key to your project's `.env.local` file (in your project root):
154
+
155
+ ```bash
156
+ echo 'ANTHROPIC_API_KEY=sk-ant-...' >> .env.local
157
+ ```
158
+
159
+ Then load it before running CLI commands:
160
+
161
+ ```bash
162
+ # Load environment variables
163
+ set -a; source .env.local; set +a
164
+
165
+ # Now run CLI commands
166
+ trie-agent scan
167
+ ```
168
+
169
+ > **Important:**
170
+ > - **MCP config** (`env` in mcp.json) only applies to the MCP server process launched by Cursor/Claude Code
171
+ > - **CLI commands** (`trie-agent scan`, `trie-agent watch`) need the key in your shell environment (via `.env.local` or `export`)
172
+ > - The MCP server and CLI are separate processes with separate environments
146
173
 
147
174
  When AI is enabled, you'll see:
148
175
  - `AI-powered analysis enabled` in output
@@ -153,27 +180,54 @@ When AI is enabled, you'll see:
153
180
 
154
181
  ## CLI
155
182
 
156
- Trie includes a powerful CLI for terminal-based scanning.
183
+ Trie includes a CLI for terminal-based scanning and CI/CD integration. The CLI generates reports with actionable issues—it does not auto-fix code. Use Cursor or Claude Code to apply fixes based on the reports.
184
+
185
+ > **Note:** The CLI is separate from MCP tools. Use MCP tools (`trie_scan`, `trie_watch`) when working inside Cursor/Claude Code. Use the CLI (`trie-agent scan`, `trie-agent watch`) for terminal/CI usage.
157
186
 
158
187
  ### Commands
159
188
 
160
189
  ```bash
161
- # Basic scan
190
+ # Basic scan (generates report and exits)
162
191
  trie-agent scan
163
192
 
164
- # Watch for changes
193
+ # Watch for changes (continuously scans and reports)
165
194
  trie-agent watch
166
195
 
167
196
  # Scan specific directory
168
- trie-agent scan --directory ./src
197
+ trie-agent scan --dir ./src
169
198
 
170
199
  # Scan specific files
171
200
  trie-agent scan --files "src/api.ts,src/auth.ts"
172
201
 
173
202
  # Run specific agents
174
203
  trie-agent scan --agents security,privacy,bugs
204
+
205
+ # Output JSON report
206
+ trie-agent scan --format json --output report.json
175
207
  ```
176
208
 
209
+ ### CLI vs MCP Tools
210
+
211
+ | Use Case | Tool | When to Use |
212
+ |----------|------|-------------|
213
+ | **Interactive coding** | MCP tools (`trie_scan`, `trie_watch`) | Working inside Cursor/Claude Code |
214
+ | **Terminal/CI** | CLI (`trie-agent scan`, `trie-agent watch`) | Running from terminal, CI pipelines, scripts |
215
+ | **VS Code** | VS Code extension | Using VS Code (not Cursor/Claude Code) |
216
+
217
+ Both generate the same reports—they're just different interfaces to the same scanning engine.
218
+
219
+ ---
220
+
221
+ ## How It Works
222
+
223
+ Trie generates **actionable reports** with high-confidence issues. It does not auto-fix code. Instead:
224
+
225
+ 1. **Trie scans** your code and generates a report with prioritized issues
226
+ 2. **You review** the issues in the report (or share with Cursor/Claude Code)
227
+ 3. **You (or Cursor/Claude Code)** apply fixes based on Trie's recommendations
228
+
229
+ This keeps you in control while providing comprehensive issue detection. Trie focuses on **finding and reporting** issues—you decide how to fix them.
230
+
177
231
  ---
178
232
 
179
233
  ## CI/CD Integration
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@triedotdev/mcp",
3
- "version": "1.0.29",
3
+ "version": "1.0.31",
4
4
  "description": "Intelligent Agent Orchestration for AI Coding Tools",
5
5
  "main": "dist/index.js",
6
6
  "type": "module",