@danielmarbach/mnemonic-mcp 0.4.1 → 0.5.0
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/CHANGELOG.md +7 -0
- package/README.md +20 -3
- package/build/index.js +369 -90
- package/build/index.js.map +1 -1
- package/build/structured-content.d.ts +273 -1312
- package/build/structured-content.d.ts.map +1 -1
- package/build/structured-content.js +1 -1
- package/build/structured-content.js.map +1 -1
- package/package.json +2 -2
package/CHANGELOG.md
CHANGED
|
@@ -4,6 +4,13 @@ All notable changes to `mnemonic` will be documented in this file.
|
|
|
4
4
|
|
|
5
5
|
The format is loosely based on Keep a Changelog and uses semver-style version headings.
|
|
6
6
|
|
|
7
|
+
## [0.5.0] - 2026-03-12
|
|
8
|
+
|
|
9
|
+
### Changed
|
|
10
|
+
|
|
11
|
+
- **Self-describing tools — no system prompt required.** All 22 MCP tools now include detailed descriptions with "use when" / "do not use when" decision boundaries, follow-up tool hints, and side-effect documentation. Tool-level `annotations` (`readOnlyHint`, `destructiveHint`, `idempotentHint`, `openWorldHint`) are set on every tool. Parameter descriptions are enriched with semantics, examples, and guidance (e.g. `lifecycle`, `summary`, `cwd`, `scope`). The 141-line `SYSTEM_PROMPT.md` has been replaced by a one-liner fallback — models discover correct behavior from tool metadata alone.
|
|
12
|
+
- Upgraded `zod` to `^4.3.6` and aligned schema declarations with Zod v4's stricter `z.record` signature to keep MCP structured-output validation and type-checking consistent.
|
|
13
|
+
|
|
7
14
|
## [0.4.1] - 2026-03-11
|
|
8
15
|
|
|
9
16
|
### Added
|
package/README.md
CHANGED
|
@@ -77,9 +77,11 @@ Override the vault location:
|
|
|
77
77
|
VAULT_PATH=/path/to/your-vault docker compose run --rm mnemonic
|
|
78
78
|
```
|
|
79
79
|
|
|
80
|
-
## Installing
|
|
80
|
+
## Installing
|
|
81
81
|
|
|
82
|
-
|
|
82
|
+
### npm
|
|
83
|
+
|
|
84
|
+
Published to the public npm registry. No authentication required.
|
|
83
85
|
|
|
84
86
|
```bash
|
|
85
87
|
# Latest stable release
|
|
@@ -89,6 +91,17 @@ npm install @danielmarbach/mnemonic-mcp
|
|
|
89
91
|
npm install @danielmarbach/mnemonic-mcp@0.2.0
|
|
90
92
|
```
|
|
91
93
|
|
|
94
|
+
### Docker Hub
|
|
95
|
+
|
|
96
|
+
Pre-built images for `linux/amd64` and `linux/arm64`:
|
|
97
|
+
|
|
98
|
+
```bash
|
|
99
|
+
docker pull danielmarbach/mnemonic-mcp:latest
|
|
100
|
+
|
|
101
|
+
# Or a specific version
|
|
102
|
+
docker pull danielmarbach/mnemonic-mcp:0.5.0
|
|
103
|
+
```
|
|
104
|
+
|
|
92
105
|
## MCP client config
|
|
93
106
|
|
|
94
107
|
### Claude Desktop / Cursor (native)
|
|
@@ -454,4 +467,8 @@ build/ Compiled JavaScript output
|
|
|
454
467
|
|
|
455
468
|
## Agent instructions
|
|
456
469
|
|
|
457
|
-
|
|
470
|
+
No system prompt required. Mnemonic's tools are self-describing — each includes "use when" / "do not use when" guidance, behavioral annotations, and typed schemas. Models will use them correctly from tool metadata alone.
|
|
471
|
+
|
|
472
|
+
If your model isn't picking up the tools proactively, add this one-liner to your AGENT.md or system prompt:
|
|
473
|
+
|
|
474
|
+
> You have access to a long-term memory system via the `mnemonic` MCP server. Use it proactively — don't wait to be asked.
|