mindforge-mcp-server 11.5.1
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 +58 -0
- package/dist/index.js +22152 -0
- package/package.json +57 -0
package/README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
1
|
+
# mindforge-mcp-server
|
|
2
|
+
|
|
3
|
+
> Read the MindForge engine — knowledge graph, project health, and audit log — from Claude Code or any MCP host, over stdio.
|
|
4
|
+
|
|
5
|
+
[](https://www.npmjs.com/package/mindforge-mcp-server)
|
|
6
|
+
[](https://opensource.org/licenses/MIT)
|
|
7
|
+
|
|
8
|
+
A self-contained Model Context Protocol (MCP) server that exposes the [MindForge](https://github.com/sairam0424/MindForge) engine to AI agents: query the SQLite-backed knowledge graph, find related memory, check project health, and read the tamper-evident audit log — plus one guarded write to persist new knowledge. Zero runtime dependencies (the server and its deps are bundled into a single file), so it runs on a clean install, offline, and on first session.
|
|
9
|
+
|
|
10
|
+
## Install
|
|
11
|
+
|
|
12
|
+
```bash
|
|
13
|
+
claude mcp add mindforge -- npx -y mindforge-mcp-server
|
|
14
|
+
```
|
|
15
|
+
|
|
16
|
+
Or add it manually to your MCP host config (Claude Desktop, Cursor, VS Code):
|
|
17
|
+
|
|
18
|
+
```json
|
|
19
|
+
{
|
|
20
|
+
"mcpServers": {
|
|
21
|
+
"mindforge": {
|
|
22
|
+
"command": "npx",
|
|
23
|
+
"args": ["-y", "mindforge-mcp-server"],
|
|
24
|
+
"env": { "CLAUDE_PROJECT_DIR": "${workspaceFolder}" }
|
|
25
|
+
}
|
|
26
|
+
}
|
|
27
|
+
}
|
|
28
|
+
```
|
|
29
|
+
|
|
30
|
+
> The server scopes every operation to `CLAUDE_PROJECT_DIR` (the project containing `.mindforge/` and `.planning/`). If unset, it falls back to the current working directory. Every tool degrades gracefully with an actionable message when MindForge is not initialized in the project — it never throws.
|
|
31
|
+
|
|
32
|
+
## Tools
|
|
33
|
+
|
|
34
|
+
| Tool | Access | Description |
|
|
35
|
+
| --- | --- | --- |
|
|
36
|
+
| `mindforge_health` | read-only | Run a MindForge health check on the current project (config, state, knowledge graph, audit chain). |
|
|
37
|
+
| `mindforge_status` | read-only | Read current project status: whether MindForge is initialized, active phase, and handoff state. |
|
|
38
|
+
| `mindforge_memory_query` | read-only | Search the knowledge graph (architectural decisions, patterns, preferences) by topic, tags, and type. |
|
|
39
|
+
| `mindforge_memory_stats` | read-only | Report knowledge-graph statistics: total/active entries, types, and tag distribution. |
|
|
40
|
+
| `mindforge_memory_find_related` | read-only | Given free text, find related knowledge entries via hybrid (FTS5 + graph-traversal) retrieval. |
|
|
41
|
+
| `mindforge_audit_log` | read-only | Read entries from the tamper-evident audit log (`.planning/AUDIT.jsonl`), optionally filtered by event. |
|
|
42
|
+
| `mindforge_memory_remember` | **write** (guarded) | Persist a new knowledge entry (decision, pattern, or preference) into the graph. |
|
|
43
|
+
|
|
44
|
+
All tools are annotated with `readOnlyHint` / `destructiveHint` so MCP hosts can enforce the right trust boundary; only `mindforge_memory_remember` writes, and it is append-only.
|
|
45
|
+
|
|
46
|
+
## Transport & security
|
|
47
|
+
|
|
48
|
+
- **Transport:** stdio JSON-RPC (single embedded client).
|
|
49
|
+
- **Scope:** read/append only within `CLAUDE_PROJECT_DIR`; no shell execution, no network egress.
|
|
50
|
+
- **Self-contained:** the SDK and Zod are bundled into `dist/index.js`; no `node_modules` are needed at runtime.
|
|
51
|
+
|
|
52
|
+
## Part of MindForge
|
|
53
|
+
|
|
54
|
+
This server ships standalone (npm + MCP registries) **and** bundled inside the [MindForge Claude Code plugin](https://github.com/sairam0424/MindForge). For the full framework — slash commands, subagents, governance, and cost-aware model routing — see the [main repository](https://github.com/sairam0424/MindForge).
|
|
55
|
+
|
|
56
|
+
## License
|
|
57
|
+
|
|
58
|
+
MIT © MindForge Team
|