mcp-adr-analysis-server 2.14.6 → 2.14.8
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 +15 -12
- package/package.json +6 -3
package/README.md
CHANGED
|
@@ -7,17 +7,17 @@
|
|
|
7
7
|
[](https://www.typescriptlang.org/)
|
|
8
8
|
[](https://github.com/tosin2013/mcp-adr-analysis-server/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22)
|
|
9
9
|
|
|
10
|
-
> **
|
|
10
|
+
> **Your ADRs are lying to you.** This MCP server catches it — live drift detection validates architectural decisions against your actual code. Plus content safety, decision memory, and 64 tools powered by your host LLM via CE-MCP.
|
|
11
11
|
|
|
12
12
|
## What is MCP?
|
|
13
13
|
|
|
14
|
-
The **Model Context Protocol (MCP)** is an open standard that enables seamless integration between AI assistants and external tools and data sources. Think of it as a universal adapter that lets AI assistants like Claude, Cline, and Cursor connect to specialized
|
|
14
|
+
The **Model Context Protocol (MCP)** is an open standard that enables seamless integration between AI assistants and external tools and data sources. Think of it as a universal adapter that lets AI assistants like Claude, Cline, and Cursor connect to specialized servers. This server gives your AI assistant the ability to detect ADR drift against live code, mask sensitive content before it leaks, and remember architectural decisions across conversations.
|
|
15
15
|
|
|
16
16
|
## TL;DR
|
|
17
17
|
|
|
18
|
-
**What:** MCP server
|
|
18
|
+
**What:** MCP server that validates architectural decisions against your actual code — drift detection, content safety, and decision memory
|
|
19
19
|
**Who:** AI coding assistants (Claude, Cline, Cursor, Windsurf), enterprise architects, development teams
|
|
20
|
-
**Why:**
|
|
20
|
+
**Why:** Catch stale ADRs before they cause production incidents — live validation against code evidence, no API key required
|
|
21
21
|
**How:** `npm install -g mcp-adr-analysis-server` → Add to your MCP client → Start analyzing
|
|
22
22
|
|
|
23
23
|
**Key Features:** Tree-sitter AST analysis • Security content masking • Drift detection • CE-MCP orchestration directives • Deployment readiness validation
|
|
@@ -29,7 +29,7 @@ The **Model Context Protocol (MCP)** is an open standard that enables seamless i
|
|
|
29
29
|
| -------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
|
30
30
|
| **ADR** | **Architectural Decision Record** — A document that captures an important architectural decision along with its context, alternatives considered, and consequences. |
|
|
31
31
|
| **MCP** | **Model Context Protocol** — An open standard enabling AI assistants to connect to external tools and data sources. |
|
|
32
|
-
| **CE-MCP** | **Claude-Enriched MCP** — Execution mode where tools return orchestration directives for the host LLM instead of making their own AI calls. Default since v2.14.
|
|
32
|
+
| **CE-MCP** | **Claude-Enriched MCP** — Execution mode where tools return orchestration directives for the host LLM instead of making their own AI calls. Default since v2.14. |
|
|
33
33
|
| **Tree-sitter** | An incremental parsing library that provides AST (Abstract Syntax Tree) analysis for 50+ languages. Used for semantic code understanding, extracting function signatures, and identifying architectural patterns. |
|
|
34
34
|
| **Session & Tool-Usage Tracker** | Project-local tracking of session intents, tool executions, and ADR registrations, with keyword-scored retrieval over JSON snapshots. Supports workflow continuity and tool-usage evidence — not a graph database. |
|
|
35
35
|
| **Smart Code Linking** | Discovery of code files related to ADRs and architectural decisions, using keyword extraction and ripgrep search. |
|
|
@@ -125,8 +125,11 @@ That's it. The server runs in **CE-MCP mode** by default — your host LLM (Clau
|
|
|
125
125
|
| **Claude Desktop (macOS)** | `~/Library/Application Support/Claude/claude_desktop_config.json` |
|
|
126
126
|
| **Claude Desktop (Windows)** | `%APPDATA%\Claude\claude_desktop_config.json` |
|
|
127
127
|
| **Cline (VS Code)** | VS Code Settings → Cline → MCP Servers (or `.vscode/cline_mcp_settings.json`) |
|
|
128
|
+
| **VS Code (native MCP)** | `.vscode/mcp.json` in workspace root |
|
|
128
129
|
| **Cursor** | Cursor Settings → MCP → Add Server |
|
|
129
130
|
|
|
131
|
+
📖 **[VS Code Integration Guide →](docs/how-to-guides/vscode-integration.md)** — step-by-step setup for Cline, Continue, and VS Code native MCP with example configs.
|
|
132
|
+
|
|
130
133
|
</details>
|
|
131
134
|
|
|
132
135
|
<details>
|
|
@@ -178,13 +181,13 @@ Get your API key at [adraggregator.com](https://adraggregator.com)
|
|
|
178
181
|
|
|
179
182
|
### Execution Modes
|
|
180
183
|
|
|
181
|
-
|
|
|
182
|
-
|
|
|
183
|
-
| **Requires API key?**
|
|
184
|
-
| **Returns**
|
|
185
|
-
| **Set via**
|
|
186
|
-
| **Best for**
|
|
187
|
-
| **Tools available**
|
|
184
|
+
| | **CE-MCP (default)** | **Full Mode (legacy)** | **Prompt-Only** |
|
|
185
|
+
| --------------------- | ---------------------------------------------------- | ------------------------------------------ | ----------------------------------------------------------------- |
|
|
186
|
+
| **Requires API key?** | No | Yes (`OPENROUTER_API_KEY`) | No |
|
|
187
|
+
| **Returns** | Orchestration directives for the host LLM to execute | Server-side AI analysis results | Prompts you can paste into any AI chat |
|
|
188
|
+
| **Set via** | Default (no env var needed) | `EXECUTION_MODE=full` | `EXECUTION_MODE=prompt-only` |
|
|
189
|
+
| **Best for** | All users — recommended | Legacy workflows with dedicated API budget | Offline exploration |
|
|
190
|
+
| **Tools available** | All 64 tools with annotated MCP metadata | All 64 tools | Analysis prompts, templates, local file operations, ADR discovery |
|
|
188
191
|
|
|
189
192
|
**What are CE-MCP directives?** When a tool is called, it returns a structured orchestration directive that tells your host LLM what to analyze, what data to gather, and how to format results. The host LLM (e.g. Claude in Claude Desktop, or GPT in Cursor) executes the directive using its existing context window. This means **zero additional API costs** and **better results** because the LLM already has your conversation context.
|
|
190
193
|
|
package/package.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "mcp-adr-analysis-server",
|
|
3
3
|
"mcpName": "io.github.tosin2013/mcp-adr-analysis-server",
|
|
4
|
-
"version": "2.14.
|
|
5
|
-
"description": "MCP server
|
|
4
|
+
"version": "2.14.8",
|
|
5
|
+
"description": "MCP server with live ADR drift detection, content safety, and decision memory — validates architectural decisions against your actual code",
|
|
6
6
|
"main": "dist/src/index.js",
|
|
7
7
|
"type": "module",
|
|
8
8
|
"engines": {
|
|
@@ -96,8 +96,11 @@
|
|
|
96
96
|
"mcp",
|
|
97
97
|
"architectural-decision-records",
|
|
98
98
|
"adr",
|
|
99
|
+
"drift-detection",
|
|
100
|
+
"content-safety",
|
|
101
|
+
"ce-mcp",
|
|
99
102
|
"architecture",
|
|
100
|
-
"analysis",
|
|
103
|
+
"code-analysis",
|
|
101
104
|
"typescript",
|
|
102
105
|
"model-context-protocol"
|
|
103
106
|
],
|