# io.github.sairam0424/mindforge (npm · mindforge-mcp-server)

Read the MindForge engine over MCP: knowledge graph, project health, and audit log.

- Trust score: 66/100 (medium)
- Change this week: +20
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `mindforge-mcp-server`: 66/100 (this document), [markdown](https://verifymcp.io/servers/sairam0424-mindforge/mindforge-mcp-server.md), [page](https://verifymcp.io/servers/sairam0424-mindforge/mindforge-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `mindforge-mcp-server`
- Version: `11.5.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 4 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 649 tokens (~92/item across 7 items; 7 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add sairam0424-mindforge -- npx -y mindforge-mcp-server
```

### Codex

```bash
codex mcp add sairam0424-mindforge -- npx -y mindforge-mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sairam0424-mindforge": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mindforge-mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sairam0424-mindforge --command npx --arg -y --arg mindforge-mcp-server
```

### Hermes

```yaml
mcp_servers:
  sairam0424-mindforge:
    command: "npx"
    args: ["-y", "mindforge-mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "sairam0424-mindforge": {
      "command": "npx",
      "args": [
        "-y",
        "mindforge-mcp-server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 66, +15)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional] Licence: MIT

### 2026-08-02 (score 51, +8)

- [security regression] Provenance: fail → unverified
- [security regression] Install scripts: pass → unverified
- [security improvement] Malware scan: unverified → pass
- [functional regression] License: pass → unverified
- [functional regression] Maintenance: pass → unverified
- [functional] Licence: MIT

### 2026-08-01 (score 43, −11)

- [security regression] Known CVEs: partial → unverified
- [functional regression] Dependency health: partial → unverified

### 2026-07-31 (score 54, +8)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 46, +22)

- [functional improvement] Tool coverage: unverified → 100

### 2026-07-28 (score 24, −22)

- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (7)

### `mindforge_health` (~54 tokens)

MindForge project health

Run a MindForge health check on the current project: verifies required planning/governance files exist, validates HANDOFF.json, and reports the audit-log size. Returns overallStatus (healthy|warning|error) with details.

### `mindforge_status` (~55 tokens)

MindForge project status

Read the current MindForge project status: whether the project is initialized, the raw STATE.md, the HANDOFF.json contents, and the autonomous-run auto-state.json if present. Use to understand where a MindForge project currently stands.

### `mindforge_memory_query` (~147 tokens)

Query MindForge knowledge base

Search the MindForge knowledge graph (architectural decisions, code/bug patterns, team preferences, domain knowledge) by topic text, tags, and type. Results are relevance-ranked. Use to recall prior decisions and patterns for the current project.

Input parameters:

- `includeGlobal` (boolean): Include the cross-project global knowledge base
- `limit` (integer): Max results (default 20)
- `minConfidence` (number): Minimum confidence (0-1, default 0.3)
- `tags` (array): Tags to match (boosts ranking)
- `topic` (string): Free-text topic to match against entries
- `type` (string): Restrict to one knowledge type

### `mindforge_memory_stats` (~57 tokens)

MindForge memory statistics

Report statistics for the MindForge knowledge graph: total/active/deprecated entries, breakdown by type, average confidence, plus graph metrics (nodes, edges, edges by type, orphan ratio). Use to gauge how much project memory exists.

### `mindforge_memory_find_related` (~98 tokens)

Find related MindForge knowledge

Given a free-text query, find related knowledge entries via keyword scoring plus graph traversal (multi-hop). Returns ranked entry ids with relevance scores. Use to surface connected decisions/patterns for a task description.

Input parameters:

- `maxHops` (integer): Graph traversal depth (default 2)
- `query` (string, required): The task or topic to find related knowledge for
- `topK` (integer): Max results (default 10)

### `mindforge_audit_log` (~106 tokens)

Read MindForge audit log

Read entries from the MindForge audit log (.planning/AUDIT.jsonl), optionally filtered by event type or phase. Use to review what the framework has recorded for this project (task completions, security findings, decisions).

Input parameters:

- `event` (string): Filter by event type (e.g. task_completed, security_finding)
- `limit` (integer): Max entries to return (default 50, newest last)
- `phase` (integer): Filter by phase number

### `mindforge_memory_remember` (~132 tokens)

Store a MindForge knowledge entry

Persist a new knowledge entry (decision, pattern, preference, or domain note) into the project knowledge graph so future sessions can recall it. Append-only and non-destructive — it never overwrites or deletes existing entries. Returns the new entry id.

Input parameters:

- `confidence` (number): Confidence 0-1 (default 0.7)
- `content` (string, required): The knowledge content to remember
- `tags` (array): Tags for later retrieval
- `topic` (string, required): Short topic/title (truncated to 80 chars)
- `type` (string, required): The kind of knowledge being stored

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/sairam0424-mindforge/mindforge-mcp-server#diagnostics

## Score history

- 2026-08-03: 66
- 2026-08-02: 51
- 2026-08-01: 43
- 2026-07-31: 54
- 2026-07-30: 46
- 2026-07-28: 24
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/mindforge-mcp-server
- Socket report: https://socket.dev/npm/package/mindforge-mcp-server
- Repository: https://github.com/sairam0424/MindForge
- Changelog RSS feed: https://verifymcp.io/servers/sairam0424-mindforge/mindforge-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/sairam0424-mindforge/mindforge-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/sairam0424-mindforge/mindforge-mcp-server