# io.github.CloudCorpRecords/specforge (npm · @reneturcios/specforge)

Spec-driven development locally: specs, constitutions, plans, tasks, git and quality checks.

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@reneturcios/specforge`: 69/100 (this document), [markdown](https://verifymcp.io/servers/cloudcorprecords-specforge/reneturcios-specforge.md), [page](https://verifymcp.io/servers/cloudcorprecords-specforge/reneturcios-specforge)
- oci · `ghcr.io/cloudcorprecords/specforge`: 41/100, [markdown](https://verifymcp.io/servers/cloudcorprecords-specforge/ghcr-io-cloudcorprecords-specforge.md), [page](https://verifymcp.io/servers/cloudcorprecords-specforge/ghcr-io-cloudcorprecords-specforge)

## Channel facts

- Registry: `npm`
- Package: `@reneturcios/specforge`
- Version: `0.1.0`
- 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 2026-11-05.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 92 dependencies flagged as unhealthy.
- **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 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 902 tokens (~41/item across 22 items; 22 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 22 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 22 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **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

### How do I install the io.github.CloudCorpRecords/specforge MCP server?

io.github.CloudCorpRecords/specforge runs locally as an npm package, launched with npx -y @reneturcios/specforge. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add cloudcorprecords-specforge -- npx -y @reneturcios/specforge
```

### Cursor

```json
{
  "mcpServers": {
    "cloudcorprecords-specforge": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/specforge"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "cloudcorprecords-specforge": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/specforge"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add cloudcorprecords-specforge -- npx -y @reneturcios/specforge
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cloudcorprecords-specforge": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@reneturcios/specforge"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add cloudcorprecords-specforge --command npx --arg -y --arg @reneturcios/specforge
```

### Hermes

```yaml
mcp_servers:
  cloudcorprecords-specforge:
    command: "npx"
    args: ["-y", "@reneturcios/specforge"]
```

### Netclaw

```json
{
  "McpServers": {
    "cloudcorprecords-specforge": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@reneturcios/specforge"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add cloudcorprecords-specforge -t stdio -c npx -a -y @reneturcios/specforge
```

### Other

```json
{
  "mcpServers": {
    "cloudcorprecords-specforge": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/specforge"
      ]
    }
  }
}
```

## 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.

### 2026-11-03 (score 69, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-02 (score 54)

First indexed and scored.

## MCP tools (22)

### `specify_start` (~62 tokens)

Start a new feature: create the next numbered feature directory with a spec template, a contracts directory and a research file.

Input parameters:

- `agent` (string): Agent name recorded with the feature, when given.
- `projectName` (string, required): Project name for the new feature.

### `specify_describe` (~40 tokens)

Write a feature description into the current feature's spec user-story section.

Input parameters:

- `description` (string, required): Feature description text written into the spec user-story section.

### `constitution_create` (~57 tokens)

Write a constitution for the current feature from principles, with optional constraints and preferences.

Input parameters:

- `constraints` (array): Optional list of constraints.
- `preferences` (array): Optional list of preferences.
- `principles` (array, required): List of constitution principles.

### `clarify_add` (~45 tokens)

Add a clarification question to the current feature's clarifications list.

Input parameters:

- `context` (string): Optional context for the question.
- `question` (string, required): Clarification question to add.

### `clarify_resolve` (~44 tokens)

Resolve a clarification by id with a resolution.

Input parameters:

- `clarificationId` (string, required): Id of the clarification to resolve.
- `resolution` (string, required): Resolution text for the clarification.

### `spec_validate` (~39 tokens)

Validate the current feature's spec for presence and completeness, returning per-check results.

Input parameters:

- `checks` (object): Optional checks object selecting which validations to run.

### `research_append` (~32 tokens)

Append content to the current feature's research file.

Input parameters:

- `content` (string, required): Content to append to the research file.

### `plan_create` (~34 tokens)

Create a plan for the current feature from constraint text.

Input parameters:

- `constraintsText` (string, required): Constraint text the plan is created from.

### `spec_refine` (~50 tokens)

Refine a named section of the current feature's spec with new content.

Input parameters:

- `changes` (string, required): New content for the section.
- `section` (string, required): Name of the spec section to refine.

### `artifacts_analyze` (~34 tokens)

Report presence and size for named artifacts of the current feature.

Input parameters:

- `artifacts` (array, required): Names of the artifacts to analyze.

### `tasks_generate` (~36 tokens)

Generate a numbered checkbox task list for the current feature from its spec.

Input parameters:

- `scope` (string): Optional scope limiting which tasks are generated.

### `tasks_tick` (~36 tokens)

Mark a task as done in the current feature's task list.

Input parameters:

- `taskId` (string, required): Id of the task to mark done.

### `tasks_tick_range` (~38 tokens)

Mark several tasks as done in the current feature's task list.

Input parameters:

- `taskIds` (array, required): Ids of the tasks to mark done.

### `tasks_filter` (~48 tokens)

List actionable tasks from the current feature, optionally by preset and limit.

Input parameters:

- `limit` (integer): Maximum number of tasks to list.
- `preset` (string): Optional preset selecting the task filter.

### `tasks_search` (~46 tokens)

Search task text in the current feature's task list.

Input parameters:

- `fuzzy` (boolean): When true, use fuzzy matching.
- `query` (string, required): Text to search for in task text.

### `tasks_visualize` (~36 tokens)

Render the current feature's task list as text or mermaid.

Input parameters:

- `format` (string): Output format: text or mermaid.

### `tasks_stats` (~51 tokens)

Report done and pending task counts for the current feature.

Input parameters:

- `groupBy` (string): Grouping key for the task counts.
- `includeCharts` (boolean): When true, include chart data in the report.

### `git_create_branch` (~34 tokens)

Create a git branch in the workspace using git.

Input parameters:

- `branchName` (string, required): Name of the git branch to create.

### `quality_format` (~33 tokens)

Run the formatter check, optionally fixing formatting.

Input parameters:

- `fix` (boolean): When true, fix formatting instead of only checking.

### `quality_lint` (~37 tokens)

Run the linter, optionally fixing lint issues.

Input parameters:

- `fix` (boolean): When true, fix lint issues instead of only reporting them.

### `quality_test` (~33 tokens)

Run the test suite, optionally with coverage.

Input parameters:

- `coverage` (boolean): When true, run the test suite with coverage.

### `quality_security_audit` (~37 tokens)

Run a dependency security audit, optionally fixing findings.

Input parameters:

- `fix` (boolean): When true, apply fixes for audit findings where possible.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/cloudcorprecords-specforge/reneturcios-specforge#diagnostics

## Score history

- 2026-11-05: 69
- 2026-11-04: 69
- 2026-11-03: 69
- 2026-11-02: 54

## Common questions

### What is the io.github.CloudCorpRecords/specforge MCP server?

io.github.CloudCorpRecords/specforge is an MCP server listed in the public MCP registry as io.github.CloudCorpRecords/specforge. Spec-driven development locally: specs, constitutions, plans, tasks, git and quality checks. This page covers its npm package (@reneturcios/specforge).

### Is the io.github.CloudCorpRecords/specforge MCP server safe to use?

io.github.CloudCorpRecords/specforge scores 69 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.CloudCorpRecords/specforge MCP server expose?

io.github.CloudCorpRecords/specforge exposes 22 tools: specify_start, specify_describe, constitution_create, clarify_add, clarify_resolve, and 17 more. Their descriptions and schemas cost roughly 902 tokens of context every time the server is loaded.

### Is the io.github.CloudCorpRecords/specforge MCP server still maintained?

io.github.CloudCorpRecords/specforge is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.CloudCorpRecords/specforge MCP server under?

io.github.CloudCorpRecords/specforge declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@reneturcios/specforge
- Socket report: https://socket.dev/npm/package/@reneturcios/specforge
- Repository: https://github.com/CloudCorpRecords/specforge
- Changelog RSS feed: https://verifymcp.io/servers/cloudcorprecords-specforge/reneturcios-specforge.xml
- Changelog JSON feed: https://verifymcp.io/servers/cloudcorprecords-specforge/reneturcios-specforge.json
- HTML version of this page: https://verifymcp.io/servers/cloudcorprecords-specforge/reneturcios-specforge