memory-journal-mcp 6.2.1 → 7.0.0
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 +157 -95
- package/dist/{chunk-BI4ZNSKA.js → chunk-2BJHLTYP.js} +1406 -446
- package/dist/chunk-ARLH46WS.js +1659 -0
- package/dist/{chunk-N6EBIDN7.js → chunk-SBNQ7MXZ.js} +631 -1793
- package/dist/cli.js +40 -3
- package/dist/github-integration-PDRLXKGM.js +1 -0
- package/dist/index.d.ts +28 -0
- package/dist/index.js +3 -2
- package/dist/tools-FFFGXIKN.js +3 -0
- package/package.json +15 -14
- package/dist/tools-WPRY5MJ6.js +0 -2
package/README.md
CHANGED
|
@@ -10,9 +10,10 @@
|
|
|
10
10
|
[](https://registry.modelcontextprotocol.io/v0/servers?search=io.github.neverinfamous/memory-journal-mcp)
|
|
11
11
|
[](SECURITY.md)
|
|
12
12
|
[](https://github.com/neverinfamous/memory-journal-mcp)
|
|
13
|
-
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
[](https://github.com/neverinfamous/memory-journal-mcp/actions/workflows/gatekeeper.yml)
|
|
16
17
|
|
|
17
18
|
🎯 **AI Context + Project Intelligence:** Bridge disconnected AI sessions with persistent project memory and **automatic session handoff** — with full GitHub workflow integration.
|
|
18
19
|
|
|
@@ -27,14 +28,15 @@
|
|
|
27
28
|
|
|
28
29
|
### What Sets Us Apart
|
|
29
30
|
|
|
30
|
-
**61 MCP Tools** · **
|
|
31
|
+
**61 MCP Tools** · **17 Workflow Prompts** · **38 Resources** · **10 Tool Groups** · **Code Mode** · **GitHub Commander** (Issue Triage, PR Review, Milestone Sprints, Security/Quality/Perf Audits) · **GitHub Integration** (Issues, PRs, Actions, Kanban, Milestones, Insights) · **Team Collaboration** (Shared DB, Vector Search, Cross-Project Insights)
|
|
31
32
|
|
|
32
33
|
| Feature | Description |
|
|
33
34
|
| ----------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
34
|
-
| **Session Intelligence** | Agents auto-query project history, create entries at checkpoints, and hand off context between sessions via `/session-summary`
|
|
35
|
+
| **Session Intelligence** | Agents auto-query project history, create entries at checkpoints, and hand off context between sessions via `/session-summary` and `team-session-summary` |
|
|
35
36
|
| **GitHub Integration** | 16 tools for Issues, PRs, Actions, Kanban, Milestones (%), Copilot Reviews, and 14-day Insights |
|
|
37
|
+
| **Dynamic Project Routing** | Seamlessly switch contexts and access CI/Issue tracking across multiple repositories using a single server instance via `PROJECT_REGISTRY` |
|
|
36
38
|
| **Knowledge Graphs** | 8 relationship types linking specs → implementations → tests → PRs with Mermaid visualization |
|
|
37
|
-
| **
|
|
39
|
+
| **Hybrid Search** | Reciprocal Rank Fusion combining FTS5 keywords, semantic vector similarity, auto-heuristics, and date-range filters |
|
|
38
40
|
| **Code Mode** | Execute multi-step operations in a secure sandbox — up to 90% token savings via `mj.*` API |
|
|
39
41
|
| **Configurable Briefing** | 12 env vars / CLI flags control `memory://briefing` content — entries, team, GitHub detail, skills awareness |
|
|
40
42
|
| **Reports & Analytics** | Standups, retrospectives, PR summaries, digests, period analyses, and milestone tracking |
|
|
@@ -43,8 +45,6 @@
|
|
|
43
45
|
| **Security & Transport** | OAuth 2.1 (RFC 9728/8414, JWT/JWKS, scopes), Streamable HTTP + SSE, rate limiting, CORS, SQL injection prevention, non-root Docker |
|
|
44
46
|
| **Structured Error Handling** | Every tool returns `{success, error, code, category, suggestion, recoverable}` — agents get classification, remediation hints, and recoverability signals |
|
|
45
47
|
| **Agent Collaboration** | IDE agents and Copilot share context; review findings become searchable knowledge; agents suggest reusable rules and skills ([setup](docs/copilot-setup.md)) |
|
|
46
|
-
| **Strict TypeScript** | 100% type-safe with strict mode, typed error classes, and no `eslint-disable` pragmas |
|
|
47
|
-
| **MCP 2025-03-26 Compliant** | Tool safety annotations, resource priorities, and progress notifications |
|
|
48
48
|
| **GitHub Commander** | Skills for issue triage, PR reviews, sprint milestones, and security/quality/performance audits with journal trails ([docs](skills/github-commander/SKILL.md)) |
|
|
49
49
|
|
|
50
50
|
---
|
|
@@ -85,10 +85,11 @@ flowchart TB
|
|
|
85
85
|
Link["Link Entries"]
|
|
86
86
|
end
|
|
87
87
|
|
|
88
|
-
subgraph Search["🔍
|
|
89
|
-
FTS["
|
|
88
|
+
subgraph Search["🔍 Hybrid Search"]
|
|
89
|
+
FTS["Keyword (FTS5)"]
|
|
90
90
|
Semantic["Semantic (Vector)"]
|
|
91
91
|
DateRange["Date Range"]
|
|
92
|
+
RRF["Reciprocal Rank Fusion"]
|
|
92
93
|
end
|
|
93
94
|
|
|
94
95
|
subgraph GitHub["🐙 GitHub Integration"]
|
|
@@ -114,17 +115,28 @@ flowchart TB
|
|
|
114
115
|
|
|
115
116
|
---
|
|
116
117
|
|
|
117
|
-
|
|
118
|
-
|
|
119
|
-
|
|
120
|
-
|
|
121
|
-
|
|
122
|
-
|
|
123
|
-
|
|
124
|
-
|
|
125
|
-
-
|
|
126
|
-
|
|
127
|
-
**
|
|
118
|
+
Suggested Rule (Add to AGENTS.md, GEMINI.md, etc):
|
|
119
|
+
|
|
120
|
+
🛑 MANDATORY SESSION START ROUTINE
|
|
121
|
+
|
|
122
|
+
Execute BEFORE fulfilling any user request in a new session:
|
|
123
|
+
|
|
124
|
+
1. **TARGET**: Infer `repo_name` from the active workspace context or user prompt. If the task is not associated with a specific project, fallback to using the generic resource without a repo name (which defaults to the first registered workspace).
|
|
125
|
+
2. **FETCH**: Use the MCP `read_resource` tool (Server: `memory-journal-mcp`) to read `memory://briefing/{repo_name}` (or `memory://briefing` if falling back).
|
|
126
|
+
- **RESTRICTION**: Do NOT use `execute_code` for this step.
|
|
127
|
+
3. **RENDER TABLE**: Extract `userMessage` and output it EXCLUSIVELY as a vertical Markdown Table (2 columns: Field and Value).
|
|
128
|
+
- **RESTRICTION**: NO bulleted lists. NO truncation of arrays or lists.
|
|
129
|
+
- **REQUIRED MAP**: Output all data comprehensively. Map these fields to the "Field" column:
|
|
130
|
+
- Application / Project
|
|
131
|
+
- Journal Entries
|
|
132
|
+
- Team DB Entries
|
|
133
|
+
- Latest Entry (Journal)
|
|
134
|
+
- Latest Entry (Team)
|
|
135
|
+
- GitHub (Include Repo, Branch, CI Status, Issues, PRs, Insights on separate lines in the Value column)
|
|
136
|
+
- Milestone Progress
|
|
137
|
+
- Template Resources (Output count only, not URLs)
|
|
138
|
+
- Registered Workspaces (Output FULL list of project names)
|
|
139
|
+
- Available Extensions (Rules, Skills, Workflows)
|
|
128
140
|
|
|
129
141
|
---
|
|
130
142
|
|
|
@@ -173,7 +185,7 @@ Control which tools are exposed via `MEMORY_JOURNAL_MCP_TOOL_FILTER` (or CLI: `-
|
|
|
173
185
|
|
|
174
186
|
**[Complete tools reference →](https://github.com/neverinfamous/memory-journal-mcp/wiki/Tools)**
|
|
175
187
|
|
|
176
|
-
### 🎯 **
|
|
188
|
+
### 🎯 **17 Workflow Prompts**
|
|
177
189
|
|
|
178
190
|
- `find-related` - Discover connected entries via semantic similarity
|
|
179
191
|
- `prepare-standup` - Daily standup summaries
|
|
@@ -191,14 +203,15 @@ Control which tools are exposed via `MEMORY_JOURNAL_MCP_TOOL_FILTER` (or CLI: `-
|
|
|
191
203
|
- `project-milestone-tracker` - Milestone progress tracking
|
|
192
204
|
- `confirm-briefing` - Acknowledge session context to user
|
|
193
205
|
- `session-summary` - Create a session summary entry with accomplishments, pending items, and next-session context
|
|
206
|
+
- `team-session-summary` - Create a retrospective team session summary entry securely isolated to the team database
|
|
194
207
|
|
|
195
208
|
**[Complete prompts guide →](https://github.com/neverinfamous/memory-journal-mcp/wiki/Prompts)**
|
|
196
209
|
|
|
197
|
-
### 📡 **
|
|
210
|
+
### 📡 **38 Resources** (25 Static + 13 Template)
|
|
198
211
|
|
|
199
212
|
**Static Resources** (appear in resource lists):
|
|
200
213
|
|
|
201
|
-
- `memory://briefing` - **Session initialization**: compact context for AI agents (~300 tokens)
|
|
214
|
+
- `memory://briefing` / `memory://briefing/{repo}` - **Session initialization**: compact context for AI agents (~300 tokens)
|
|
202
215
|
- `memory://instructions` - **Behavioral guidance**: complete server instructions for AI agents
|
|
203
216
|
- `memory://recent` - 10 most recent entries
|
|
204
217
|
- `memory://significant` - Significant milestones and breakthroughs
|
|
@@ -218,9 +231,18 @@ Control which tools are exposed via `MEMORY_JOURNAL_MCP_TOOL_FILTER` (or CLI: `-
|
|
|
218
231
|
- `memory://team/statistics` - Team entry counts, types, and author breakdown
|
|
219
232
|
- `memory://help` - Tool group index with descriptions and tool counts
|
|
220
233
|
- `memory://help/gotchas` - Field notes, edge cases, and critical usage patterns
|
|
234
|
+
- `memory://metrics/summary` - Aggregate tool call metrics since server start (calls, errors, token estimates, duration) — HIGH priority
|
|
235
|
+
- `memory://metrics/tokens` - Per-tool token usage breakdown sorted by output token cost — MEDIUM priority
|
|
236
|
+
- `memory://metrics/system` - Process-level metrics: memory (MB), uptime (s), Node.js version, platform — MEDIUM priority
|
|
237
|
+
- `memory://metrics/users` - Per-user call counts (populated when OAuth user identifiers are present) — LOW priority
|
|
238
|
+
- `memory://audit` - Last 50 write/admin tool call entries from the JSONL audit log (requires `AUDIT_LOG_PATH`)
|
|
221
239
|
|
|
222
240
|
**Template Resources** (require parameters, fetch directly by URI):
|
|
223
241
|
|
|
242
|
+
- `memory://github/status/{repo}` - Repository status targeted by repo
|
|
243
|
+
- `memory://github/insights/{repo}` - Repository insights targeted by repo
|
|
244
|
+
- `memory://github/milestones/{repo}` - Open milestones targeted by repo
|
|
245
|
+
- `memory://milestones/{repo}/{number}` - Milestone detail targeted by repo
|
|
224
246
|
- `memory://projects/{number}/timeline` - Project activity timeline
|
|
225
247
|
- `memory://issues/{issue_number}/entries` - Entries linked to issue
|
|
226
248
|
- `memory://prs/{pr_number}/entries` - Entries linked to PR
|
|
@@ -294,6 +316,8 @@ npm run build
|
|
|
294
316
|
|
|
295
317
|
Add this to your `~/.cursor/mcp.json`, Claude Desktop config, or equivalent:
|
|
296
318
|
|
|
319
|
+
### Basic Configuration
|
|
320
|
+
|
|
297
321
|
```json
|
|
298
322
|
{
|
|
299
323
|
"mcpServers": {
|
|
@@ -301,7 +325,40 @@ Add this to your `~/.cursor/mcp.json`, Claude Desktop config, or equivalent:
|
|
|
301
325
|
"command": "memory-journal-mcp",
|
|
302
326
|
"env": {
|
|
303
327
|
"GITHUB_TOKEN": "ghp_your_token_here",
|
|
304
|
-
"
|
|
328
|
+
"PROJECT_REGISTRY": "{\"my-repo\":{\"path\":\"/path/to/your/git/repo\",\"project_number\":1}}"
|
|
329
|
+
}
|
|
330
|
+
}
|
|
331
|
+
}
|
|
332
|
+
}
|
|
333
|
+
```
|
|
334
|
+
|
|
335
|
+
### Advanced Configuration (Recommended)
|
|
336
|
+
|
|
337
|
+
Showcasing the full power of the server, including Multi-Project Routing, Team Collaboration, Copilot awareness, and Context Injections.
|
|
338
|
+
|
|
339
|
+
```json
|
|
340
|
+
{
|
|
341
|
+
"mcpServers": {
|
|
342
|
+
"memory-journal-mcp": {
|
|
343
|
+
"command": "memory-journal-mcp",
|
|
344
|
+
"env": {
|
|
345
|
+
"DB_PATH": "/path/to/your/memory_journal.db",
|
|
346
|
+
"TEAM_DB_PATH": "/path/to/shared/team.db",
|
|
347
|
+
"GITHUB_TOKEN": "ghp_your_token_here",
|
|
348
|
+
"PROJECT_REGISTRY": "{\"my-repo\":{\"path\":\"/path/to/repo\",\"project_number\":1},\"other-repo\":{\"path\":\"/path/to/other\",\"project_number\":5}}",
|
|
349
|
+
"AUTO_REBUILD_INDEX": "true",
|
|
350
|
+
"MEMORY_JOURNAL_MCP_TOOL_FILTER": "codemode",
|
|
351
|
+
"BRIEFING_ENTRY_COUNT": "3",
|
|
352
|
+
"BRIEFING_INCLUDE_TEAM": "true",
|
|
353
|
+
"BRIEFING_ISSUE_COUNT": "1",
|
|
354
|
+
"BRIEFING_PR_COUNT": "1",
|
|
355
|
+
"BRIEFING_PR_STATUS": "true",
|
|
356
|
+
"BRIEFING_WORKFLOW_COUNT": "1",
|
|
357
|
+
"BRIEFING_WORKFLOW_STATUS": "true",
|
|
358
|
+
"BRIEFING_COPILOT_REVIEWS": "true",
|
|
359
|
+
"RULES_FILE_PATH": "/path/to/your/RULES.md",
|
|
360
|
+
"SKILLS_DIR_PATH": "/path/to/your/skills",
|
|
361
|
+
"MEMORY_JOURNAL_WORKFLOW_SUMMARY": "/deploy: prod deployment | /audit: security scan"
|
|
305
362
|
}
|
|
306
363
|
}
|
|
307
364
|
}
|
|
@@ -414,69 +471,74 @@ Each job is error-isolated — a failure in one job won't affect the others. Sch
|
|
|
414
471
|
|
|
415
472
|
### GitHub Integration Configuration
|
|
416
473
|
|
|
417
|
-
The GitHub tools (`get_github_issues`, `get_github_prs`, etc.) auto-detect the repository from your git context when `
|
|
418
|
-
|
|
419
|
-
| Environment Variable
|
|
420
|
-
|
|
|
421
|
-
| `DB_PATH`
|
|
422
|
-
| `TEAM_DB_PATH`
|
|
423
|
-
| `TEAM_AUTHOR`
|
|
424
|
-
| `GITHUB_TOKEN`
|
|
425
|
-
|
|
426
|
-
| `DEFAULT_PROJECT_NUMBER`
|
|
427
|
-
| `
|
|
428
|
-
| `
|
|
429
|
-
| `
|
|
430
|
-
| `
|
|
431
|
-
| `
|
|
432
|
-
| `
|
|
433
|
-
| `
|
|
434
|
-
| `
|
|
435
|
-
| `
|
|
436
|
-
| `
|
|
437
|
-
| `
|
|
438
|
-
| `
|
|
439
|
-
| `
|
|
440
|
-
| `
|
|
441
|
-
| `
|
|
442
|
-
| `
|
|
443
|
-
| `
|
|
444
|
-
| `
|
|
445
|
-
| `
|
|
446
|
-
| `
|
|
447
|
-
| `
|
|
448
|
-
| `
|
|
449
|
-
| `
|
|
450
|
-
| `
|
|
451
|
-
| `
|
|
452
|
-
| `
|
|
453
|
-
| `
|
|
454
|
-
| `
|
|
455
|
-
| `
|
|
456
|
-
| `
|
|
457
|
-
| `
|
|
458
|
-
| `
|
|
459
|
-
| `
|
|
460
|
-
|
|
461
|
-
|
|
462
|
-
|
|
463
|
-
|
|
464
|
-
|
|
465
|
-
|
|
466
|
-
|
|
467
|
-
|
|
468
|
-
|
|
469
|
-
|
|
470
|
-
|
|
471
|
-
|
|
472
|
-
|
|
473
|
-
|
|
474
|
-
|
|
475
|
-
|
|
476
|
-
|
|
477
|
-
|
|
478
|
-
|
|
479
|
-
|
|
474
|
+
The GitHub tools (`get_github_issues`, `get_github_prs`, etc.) auto-detect the repository from your git context when `PROJECT_REGISTRY` is configured or the MCP server is run inside a git repository.
|
|
475
|
+
|
|
476
|
+
| Environment Variable | Description |
|
|
477
|
+
| -------------------- | ----------------------------------------------------------------------- |
|
|
478
|
+
| `DB_PATH` | Database file location (CLI: `--db`; default: `./memory_journal.db`) |
|
|
479
|
+
| `TEAM_DB_PATH` | Team database file location (CLI: `--team-db`) |
|
|
480
|
+
| `TEAM_AUTHOR` | Override author name for team entries (default: `git config user.name`) |
|
|
481
|
+
| `GITHUB_TOKEN` | GitHub personal access token for API access |
|
|
482
|
+
|
|
483
|
+
| `DEFAULT_PROJECT_NUMBER` | Default GitHub Project number for auto-assignment when creating issues |
|
|
484
|
+
| `GITHUB_REPO_PATH` | Path to a git repository for auto-detecting owner/repo |
|
|
485
|
+
| `PROJECT_REGISTRY` | JSON map of repos to `{ path, project_number }` for multi-project auto-detection and routing |
|
|
486
|
+
| `AUTO_REBUILD_INDEX` | Set to `true` to rebuild vector index on server startup |
|
|
487
|
+
| `MCP_HOST` | Server bind host (`0.0.0.0` for containers, default: `localhost`) |
|
|
488
|
+
| `MCP_AUTH_TOKEN` | Bearer token for HTTP transport authentication (CLI: `--auth-token`) |
|
|
489
|
+
| `MCP_CORS_ORIGIN` | Allowed CORS origins for HTTP transport, comma-separated (default: `*`) |
|
|
490
|
+
| `MCP_RATE_LIMIT_MAX` | Max requests per minute per client IP, HTTP only (default: `100`) |
|
|
491
|
+
| `LOG_LEVEL` | Log verbosity: `error`, `warn`, `info`, `debug` (default: `info`; CLI: `--log-level`) |
|
|
492
|
+
| `MCP_ENABLE_HSTS` | Enable HSTS security header on HTTP responses (CLI: `--enable-hsts`; default: `false`) |
|
|
493
|
+
| `OAUTH_ENABLED` | Set to `true` to enable OAuth 2.1 authentication (HTTP only) |
|
|
494
|
+
| `OAUTH_ISSUER` | OAuth issuer URL (e.g., `https://auth.example.com/realms/mcp`) |
|
|
495
|
+
| `OAUTH_AUDIENCE` | Expected JWT audience claim |
|
|
496
|
+
| `OAUTH_JWKS_URI` | JWKS endpoint for token signature verification |
|
|
497
|
+
| `BRIEFING_ENTRY_COUNT` | Journal entries in briefing (CLI: `--briefing-entries`; default: `3`) |
|
|
498
|
+
| `BRIEFING_INCLUDE_TEAM` | Include team DB entries in briefing (`true`/`false`; default: `false`) |
|
|
499
|
+
| `BRIEFING_ISSUE_COUNT` | Issues to list in briefing; `0` = count only (default: `0`) |
|
|
500
|
+
| `BRIEFING_PR_COUNT` | PRs to list in briefing; `0` = count only (default: `0`) |
|
|
501
|
+
| `BRIEFING_PR_STATUS` | Show PR status breakdown (open/merged/closed; default: `false`) |
|
|
502
|
+
| `BRIEFING_WORKFLOW_COUNT` | Workflow runs to list in briefing; `0` = status only (default: `0`) |
|
|
503
|
+
| `BRIEFING_WORKFLOW_STATUS` | Show workflow status breakdown in briefing (default: `false`) |
|
|
504
|
+
| `BRIEFING_COPILOT_REVIEWS` | Aggregate Copilot review state in briefing (default: `false`) |
|
|
505
|
+
| `RULES_FILE_PATH` | Path to user rules file for agent awareness (CLI: `--rules-file`) |
|
|
506
|
+
| `SKILLS_DIR_PATH` | Path to skills directory for agent awareness (CLI: `--skills-dir`) |
|
|
507
|
+
| `MEMORY_JOURNAL_WORKFLOW_SUMMARY` | Free-text workflow summary for `memory://workflows` (CLI: `--workflow-summary`) |
|
|
508
|
+
| `INSTRUCTION_LEVEL` | Briefing depth: `essential`, `standard`, `full` (CLI: `--instruction-level`; default: `standard`) |
|
|
509
|
+
| `PROJECT_LINT_CMD` | Project lint command for GitHub Commander validation gates (default: `npm run lint`) |
|
|
510
|
+
| `PROJECT_TYPECHECK_CMD` | Project typecheck command (default: `npm run typecheck`; empty = skip) |
|
|
511
|
+
| `PROJECT_BUILD_CMD` | Project build command (default: `npm run build`; empty = skip) |
|
|
512
|
+
| `PROJECT_TEST_CMD` | Project test command (default: `npm run test`) |
|
|
513
|
+
| `PROJECT_E2E_CMD` | Project E2E test command (default: empty = skip) |
|
|
514
|
+
| `PROJECT_PACKAGE_MANAGER` | Package manager override: `npm`, `yarn`, `pnpm`, `bun` (default: auto-detect from lockfile) |
|
|
515
|
+
| `PROJECT_HAS_DOCKERFILE` | Enable Docker audit steps (default: auto-detect) |
|
|
516
|
+
| `COMMANDER_HITL_FILE_THRESHOLD` | Human-in-the-loop checkpoint if changes touch > N files (default: `10`) |
|
|
517
|
+
| `COMMANDER_SECURITY_TOOLS` | Override security tool auto-detection (comma-separated; default: auto-detect) |
|
|
518
|
+
| `COMMANDER_BRANCH_PREFIX` | Branch naming prefix for PRs (default: `fix`) |
|
|
519
|
+
| `AUDIT_LOG_PATH` | Path for the JSONL audit log of write/admin tool calls. Rotates at 10 MB (keeps 5 archives). Omit to disable audit logging. |
|
|
520
|
+
| `AUDIT_REDACT` | Set to `true` to omit tool arguments from audit log entries for privacy (default: `false`) |
|
|
521
|
+
| `AUDIT_READS` | Log read-scoped tool calls in addition to write/admin (CLI: `--audit-reads`; default: `false`) |
|
|
522
|
+
| `AUDIT_LOG_MAX_SIZE` | Maximum audit log file size in bytes before rotation (CLI: `--audit-log-max-size`; default: `10485760`) |
|
|
523
|
+
| `MCP_METRICS_ENABLED` | Set to `false` to disable in-memory tool call metrics accumulation (default: `true`) |
|
|
524
|
+
|
|
525
|
+
**Multi-Project Workflows**: For agents to seamlessly support multiple projects, provide **`PROJECT_REGISTRY`**.
|
|
526
|
+
|
|
527
|
+
#### Dynamic Context Resolution & Auto-Detection
|
|
528
|
+
|
|
529
|
+
When executing GitHub tools (issues, PRs, context, etc.), the server resolves repository context in this order:
|
|
530
|
+
|
|
531
|
+
1. **Dynamic Project Routing**: If the agent passes a `repo` string that matches a key in your `PROJECT_REGISTRY`, the server dynamically mounts the physical directory mapped to that project. It executes git commands locally and automatically infers the `owner`.
|
|
532
|
+
2. **Explicit Override**: If the agent provides both `owner` and `repo` explicitly, those values override auto-detection for API calls.
|
|
533
|
+
3. **Missing Context**: Without `PROJECT_REGISTRY` or explicit parameters, the server blocks execution and returns `{requiresUserInput: true}` to prompt the agent.
|
|
534
|
+
|
|
535
|
+
#### Automatic Project Routing (Kanban / Issues)
|
|
536
|
+
|
|
537
|
+
When opening an issue or viewing/moving a Kanban card, the server needs a GitHub Project number. It determines this via:
|
|
538
|
+
|
|
539
|
+
1. Exploring the raw `project_number` argument passed by the agent.
|
|
540
|
+
2. Checking if the `repo` string precisely matches an entry in your **`PROJECT_REGISTRY`**, seamlessly mapping it to its pre-configured `project_number`.
|
|
541
|
+
3. Falling back to the globally defined `DEFAULT_PROJECT_NUMBER` if set.
|
|
480
542
|
|
|
481
543
|
### 🔐 OAuth 2.1 Authentication
|
|
482
544
|
|
|
@@ -521,7 +583,7 @@ memory-journal-mcp --transport http --port 3000
|
|
|
521
583
|
|
|
522
584
|
### 🔄 Session Management
|
|
523
585
|
|
|
524
|
-
1. **Session start** → agent reads `memory://briefing` and shows project context
|
|
586
|
+
1. **Session start** → agent reads `memory://briefing` (or `memory://briefing/{repo}`) and shows project context
|
|
525
587
|
2. **Session summary** → use `/session-summary` to capture progress and next-session context
|
|
526
588
|
3. Next session's briefing includes the previous summary — context flows seamlessly
|
|
527
589
|
|
|
@@ -569,8 +631,8 @@ flowchart TB
|
|
|
569
631
|
|
|
570
632
|
subgraph MCP["Memory Journal MCP Server"]
|
|
571
633
|
Tools["🛠️ 61 Tools"]
|
|
572
|
-
Resources["📡
|
|
573
|
-
Prompts["💬
|
|
634
|
+
Resources["📡 33 Resources"]
|
|
635
|
+
Prompts["💬 17 Prompts"]
|
|
574
636
|
end
|
|
575
637
|
|
|
576
638
|
subgraph Storage["Persistence Layer"]
|
|
@@ -597,7 +659,7 @@ flowchart TB
|
|
|
597
659
|
┌─────────────────────────────────────────────────────────────┐
|
|
598
660
|
│ MCP Server Layer (TypeScript) │
|
|
599
661
|
│ ┌─────────────────┐ ┌─────────────────┐ ┌─────────────┐ │
|
|
600
|
-
│ │ Tools (61) │ │ Resources (
|
|
662
|
+
│ │ Tools (61) │ │ Resources (38) │ │ Prompts (17)│ │
|
|
601
663
|
│ │ with Annotations│ │ with Annotations│ │ │ │
|
|
602
664
|
│ └─────────────────┘ └─────────────────┘ └─────────────┘ │
|
|
603
665
|
├─────────────────────────────────────────────────────────────┤
|
|
@@ -629,9 +691,9 @@ flowchart TB
|
|
|
629
691
|
|
|
630
692
|
Memory Journal is designed for extremely low overhead during AI task execution. We include a `vitest bench` suite to maintain these baseline guarantees:
|
|
631
693
|
|
|
632
|
-
- **Database Reads**: Operations execute in fractions of a millisecond. `calculateImportance` is ~
|
|
633
|
-
- **Vector Search Engine**: Both search (~220 ops/sec) and indexing (~1600+ ops/sec) are high-throughput via `sqlite-vec` with SQL-native KNN queries.
|
|
634
|
-
- **Core MCP Routines**: `getTools` uses cached O(1) dispatch (~
|
|
694
|
+
- **Database Reads**: Operations execute in fractions of a millisecond. `calculateImportance` is ~13-14x faster than retrieving 50 recent entries.
|
|
695
|
+
- **Vector Search Engine**: Both search (~140-220 ops/sec) and indexing (~1600-1900+ ops/sec) are high-throughput via `sqlite-vec` with SQL-native KNN queries.
|
|
696
|
+
- **Core MCP Routines**: `getTools` uses cached O(1) dispatch (~4800-7000x faster than `get_recent_entries`). `create_entry` and `search_entries` execute through the full MCP layer with sub-millisecond overhead.
|
|
635
697
|
|
|
636
698
|
To run the benchmarking suite locally:
|
|
637
699
|
|