ForgeCraft
NPM · FORGECRAFT-MCP
Production engineering standards for AI coding assistants. Setup once, remove when done.
Available components
Last scanned (1 hour ago)
Scores higher than 35% of npm servers
Category Developer Tools
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. How we score → Why this is hard to score →
Supply Chain Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 30 of 95 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 146 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability43
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 2583 tokens (~1291/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 2 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 +1
- Stability: 0.97 → pass security
- 2 Nov 26 −1
- Stability: pass → 0.93 functional
- 27 Oct 26 +1
- Stability: 0.97 → pass security
- 26 Oct 26 −1
- Stability: pass → 0.97 functional
- 24 Oct 26 −5
- CVE-2023-54404 affects this package: high ▼ security
- Known CVEs: pass → fail ▼ security
- 20 Oct 26 0
- Stability: 0.97 → pass security
- 19 Oct 26 0
- Stability: pass → 0.97 functional
- 17 Oct 26 +2
- Stability: 0.87 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed npm/forgecraft-mcp@1.0.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 95 packages
| Packages resolved | 95 |
|---|---|
| Stale | 30 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
forgecraft ~45
Setup-time tool for engineering standards. Diagnoses project state. Remove this MCP server after setup is complete to save tokens.
| Name | Type | Req | Description |
|---|---|---|---|
| project_dir | string | yes | Absolute path to project root. |
No output schema declared.
No examples provided.
forgecraft_actions ~2,538
Full ForgeCraft action suite. Use action='setup_project' to onboard, 'check_cascade' to verify GS steps, 'generate_session_prompt' for a bound prompt, 'audit' for compliance score. Remove after setup to save tokens.
| Name | Type | Req | Description |
|---|---|---|---|
| acceptance_criteria | array | – | Checkable acceptance criteria. Used by: generate_session_prompt. If omitted, defaults are generated. |
| action | string | yes | Operation to perform. Available actions: setup_project — onboard a new or existing project (two-phase: analyze then calibrate) scaffold — generate project structure files (.clau… |
| add_tags | array | – | Tags to add during refresh. |
| adr_alternatives | array | – | List of alternatives considered and why each was rejected. Used by: generate_adr. |
| adr_consequences | string | – | Positive and negative consequences of the decision — what becomes easier, harder, or constrained. Used by: generate_adr. |
| adr_context | string | – | The situation that forced this decision — constraints, requirements, forces at play. Used by: generate_adr. |
| adr_decision | string | – | What was decided and why this option was chosen over alternatives. Used by: generate_adr. |
| adr_title | string | – | Short imperative title of the architectural decision (e.g. 'Use PostgreSQL for primary storage'). Used by: generate_adr. |
| apply | boolean | – | Apply changes (vs preview). Used by: refresh. Default: false. |
| auto_approve_tools | boolean | – | Auto-approve MCP tool calls. Used by: configure_mcp. Default: true. |
| cascade_decided_by | string | – | Who made this cascade decision. Used by: set_cascade_requirement. Defaults to 'assistant'. |
| cascade_rationale | string | – | Why was this cascade decision made? Required for: set_cascade_requirement. |
| cascade_required | boolean | – | Whether the cascade step must pass before implementation begins. Used by: set_cascade_requirement. |
| cascade_step | string | – | Which cascade step to configure. Used by: set_cascade_requirement. |
| cnt_concern | string | – | Concern name within a CNT domain. Lowercase kebab-case. E.g. 'routing', 'auth'. Used by: cnt_add_node. |
| cnt_content | string | – | Markdown content for a CNT leaf node (≤30 lines). If omitted, a placeholder is generated. Used by: cnt_add_node. |
| cnt_domain | string | – | Domain prefix for a CNT leaf node. Lowercase kebab-case. E.g. 'tools', 'shared'. Used by: cnt_add_node. |
| compact | boolean | – | Strip explanatory tail clauses and deduplicate bullet lines (~20-40% smaller output). Used by: generate, scaffold, refresh. |
| coverage_dir | string | – | Path to existing coverage report directory. Used by: metrics. Defaults to coverage/ relative to project_dir. |
| custom_servers | object | – | Custom MCP servers. Used by: configure_mcp. |
| deployment_url | string | – | Override deployment URL for smoke test. Used by: start_hardening. Default: read from forgecraft.yaml or 'http://localhost:3000'. |
| description | string | – | Natural language description. Used by: classify. |
| dry_run | boolean | – | Preview without writing files. Used by: scaffold. |
| force | boolean | – | Overwrite existing files. Used by: scaffold. |
| has_consumers | boolean | – | Phase 2 answer: true = existing users or downstream consumers (behavioral contracts required), false = no consumers yet. Used by: setup_project (phase 2). |
| include_anti_patterns | boolean | – | Scan for anti-patterns. Used by: audit. Default: true. |
| include_mutation | boolean | – | Run Stryker mutation testing (slow, opt-in). Used by: metrics. Default: false. |
| include_remote | boolean | – | Query remote MCP registry. Used by: configure_mcp. Default: false. |
| item_description | string | – | Roadmap item description for this session. Used by: generate_session_prompt. Should include actor, behavior, and postcondition. |
| language | string | – | Programming language. Used by: scaffold, add_module. Default: typescript. |
| max_servers | integer | – | Max MCP servers to configure. Used by: configure_mcp. |
| merge | boolean | – | Merge with existing instruction files. Used by: generate. Default: true. |
| mvp | boolean | – | Phase 2 answer: true = MVP stage (minimal ceremony, expect changes), false = production (full quality gates). Used by: setup_project (phase 2 — provide together with scope_complete and has_consumers). |
| name | string | – | Item name. Used by: add_hook (hook name), add_module (module name). |
| notes | string | – | Evidence or justification for a verification decision. Used by: record_verification. |
| output_targets | array | – | AI assistant targets (claude, cursor, copilot, windsurf, cline, aider). Used by: scaffold, generate, refresh. |
| pass_threshold | integer | – | Minimum §4.3 GS score (0–14, 7 properties × 2) required for overall pass. Used by: verify. Default: 11. |
| phase_id | string | – | Verification phase ID containing the step (e.g., 'contract-definition'). Used by: record_verification. |
| project_dir | string | – | Absolute path to the project root. Required for: setup_project, refresh, scaffold, generate, audit, add_hook, add_module, configure_mcp, convert, verify, metrics, record_verification, verification_st… |
| project_name | string | – | Human-readable project name. Used by: scaffold, generate. |
| project_type_override | string | – | Phase 2: override the inferred project type when ambiguities were reported in phase 1. Examples: "docs", "cli", "api", "library", "cli+library", "cli+api". Provide this when the AI detected conflicti… |
| recorded_by | string | – | Who recorded this decision (e.g., 'claude-sonnet-4-5', 'human', CI name). Used by: record_verification. Defaults to 'unknown'. |
| release_phase | string | – | Current release cycle phase. Controls which test gates are shown as required vs. advisory. Used by: setup, generate, refresh. Default: development. |
| remote_registry_url | string | – | Remote MCP registry URL override. Used by: configure_mcp. |
| remove_tags | array | – | Tags to remove during refresh. |
| resource | string | – | Sub-resource for list (tags|hooks|skills) and get_reference (nfr|design_patterns|playbook|guidance). Use 'guidance' to retrieve GS session-loop, context-loading, incremental-cascade, bound-roadmap, a… |
| scan_depth | string | – | Analysis depth. Used by: convert. Default: quick. |
| scope | string | – | Review scope. Used by: review. Default: comprehensive. |
| scope_complete | boolean | – | Phase 2 answer: true = scope is finalized (proceed with full cascade), false = scope still evolving (lighter cascade). Used by: setup_project (phase 2). |
| scope_note | string | – | Explicit out-of-scope statement — what this session must NOT touch. Used by: generate_session_prompt. |
| sentinel | boolean | – | Generate sentinel CLAUDE.md (~50 lines) + .claude/standards/ domain files instead of one large file. Default: true. Set to false for traditional monolithic CLAUDE.md. Used by: scaffold, refresh. |
| session_type | string | – | Conventional commit type for session output. Used by: generate_session_prompt. Default: feature. |
| show_pending_only | boolean | – | Show only pending/failed steps. Used by: verification_status. Default: false. |
| skip_load_test | boolean | – | Skip load test phase (HARDEN-003). Used by: start_hardening. Default: true (skip when no load gates defined). |
| spec_path | string | – | Path to an existing spec file (markdown, txt, OpenAPI). Used by: setup_project (phase 1). |
| spec_text | string | – | Paste spec text directly (markdown prose, OpenAPI description, etc.). Used by: setup_project (phase 1). |
| step_id | string | – | Verification step ID to record an acceptance decision for (e.g., 'write-hurl-spec'). Used by: record_verification. |
| step_status | string | – | Acceptance decision for the verification step: pass | fail | skipped. Used by: record_verification. |
| strategy_tag | string | – | Tag whose verification strategy the step belongs to (e.g., 'API', 'GAME'). Used by: record_verification. |
| tag | string | – | Single tag filter. Used by: add_hook. |
| tags | array | – | Project classification tags. Used by: scaffold, generate, audit, review, add_module, configure_mcp, get_reference (not needed for resource=guidance), convert, list (as filter). |
| test_command | string | – | Test command override. Used by: verify. Default: npm test. |
| tier | string | – | Content depth: core, recommended, optional. Used by: refresh. |
| timeout_ms | integer | – | Test suite timeout in ms. Used by: verify. Default: 120000. |
| uncertainty_level | string | – | Filter verification strategies by uncertainty level. Used by: get_verification_strategy. |
No output schema declared.
No examples provided.
How do I install the ForgeCraft MCP server?
ForgeCraft runs locally as an npm package, launched with npx -y forgecraft-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · forgecraft-mcp
claude mcp add jghiringhelli-forgecraft -- npx -y forgecraft-mcp
What is the ForgeCraft MCP server?
ForgeCraft is an MCP server listed in the public MCP registry as io.github.jghiringhelli/forgecraft. Production engineering standards for AI coding assistants. Setup once, remove when done. This page covers its npm package (forgecraft-mcp).
Is the ForgeCraft MCP server safe to use?
ForgeCraft scores 68 out of 100 on VerifyMCP. We recorded 1 known advisory against 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 ForgeCraft MCP server expose?
ForgeCraft exposes 2 tools: forgecraft, forgecraft_actions. Their descriptions and schemas cost roughly 2,583 tokens of context every time the server is loaded.
Is the ForgeCraft MCP server still maintained?
ForgeCraft 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 ForgeCraft MCP server under?
ForgeCraft declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.