Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

ForgeCraft

NPM · FORGECRAFT-MCP · SCANNED AUG 3

Production engineering standards for AI coding assistants. Setup once, remove when done.

Available components

npm · forgecraft-mcp 59
+19 this week 59 Trust /100
Trust breakdown (6 categories)

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 →

Supply Chain Security87
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (97 of 101), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (97 of 101), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability23
  • AI-judged instruction clarity (fair).Partial
  • 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 Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · forgecraft-mcp

# add to Claude Code
claude mcp add jghiringhelli-forgecraft -- npx -y forgecraft-mcp
# add to Codex CLI
codex mcp add jghiringhelli-forgecraft -- npx -y forgecraft-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jghiringhelli-forgecraft": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "forgecraft-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add jghiringhelli-forgecraft --command npx --arg -y --arg forgecraft-mcp
# ~/.hermes/config.yaml
mcp_servers:
  jghiringhelli-forgecraft:
    command: "npx"
    args: ["-y", "forgecraft-mcp"]
// mcp.json
{
  "mcpServers": {
    "jghiringhelli-forgecraft": {
      "command": "npx",
      "args": [
        "-y",
        "forgecraft-mcp"
      ]
    }
  }
}
Changelog

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.

  • 3 Aug 26 +39
    • Provenance: unverified → fail ▼ security
    • Install scripts: unverified → pass ▲ security
    • Known CVEs: unverified → partial ▲ security
    • Security disclosure: unverified → fail ▼ functional
    • Tool coverage: unverified → 100 ▲ functional
    • License: unverified → pass ▲ functional
    • Schema quality: unverified → fair ▲ functional
    • Dependency health: unverified → partial ▲ functional
    • Maintenance: unverified → pass ▲ functional
    • Stability: unverified → 0.27 ▲ functional
    • MCP protocol: unverified → pass ▲ functional
    • Licence: MIT functional
  • 2 Aug 26 +4
    • Malware scan: unverified → pass ▲ security
    • Security disclosure: fail → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
  • 31 Jul 26 −24
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 +16
    • Tool coverage: unverified → 100 ▲ functional
  • 28 Jul 26 −16
    • Tool coverage: 100 → unverified ▼ functional
    • First check of Schema quality: unverified functional
  • 27 Jul 26 40

    First indexed and scored.

Diagnostics

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 3 Aug 2026 · Analysed npm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 97 packages

97 packages in the resolved dependency tree · 97 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 2 exposed · ~2,583 tokens

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.

Tool Tokens
forgecraft ~45

Setup-time tool for engineering standards. Diagnoses project state. Remove this MCP server after setup is complete to save tokens.

NameTypeReqDescription
project_dirstringyesAbsolute 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.

NameTypeReqDescription
acceptance_criteriaarray—Checkable acceptance criteria. Used by: generate_session_prompt. If omitted, defaults are generated.
actionstringyesOperation to perform. Available actions: setup_project — onboard a new or existing project (two-phase: analyze then calibrate) scaffold — generate project structure files (.clau…
add_tagsarray—Tags to add during refresh.
adr_alternativesarray—List of alternatives considered and why each was rejected. Used by: generate_adr.
adr_consequencesstring—Positive and negative consequences of the decision — what becomes easier, harder, or constrained. Used by: generate_adr.
adr_contextstring—The situation that forced this decision — constraints, requirements, forces at play. Used by: generate_adr.
adr_decisionstring—What was decided and why this option was chosen over alternatives. Used by: generate_adr.
adr_titlestring—Short imperative title of the architectural decision (e.g. 'Use PostgreSQL for primary storage'). Used by: generate_adr.
applyboolean—Apply changes (vs preview). Used by: refresh. Default: false.
auto_approve_toolsboolean—Auto-approve MCP tool calls. Used by: configure_mcp. Default: true.
cascade_decided_bystring—Who made this cascade decision. Used by: set_cascade_requirement. Defaults to 'assistant'.
cascade_rationalestring—Why was this cascade decision made? Required for: set_cascade_requirement.
cascade_requiredboolean—Whether the cascade step must pass before implementation begins. Used by: set_cascade_requirement.
cascade_stepstring—Which cascade step to configure. Used by: set_cascade_requirement.
cnt_concernstring—Concern name within a CNT domain. Lowercase kebab-case. E.g. 'routing', 'auth'. Used by: cnt_add_node.
cnt_contentstring—Markdown content for a CNT leaf node (≤30 lines). If omitted, a placeholder is generated. Used by: cnt_add_node.
cnt_domainstring—Domain prefix for a CNT leaf node. Lowercase kebab-case. E.g. 'tools', 'shared'. Used by: cnt_add_node.
compactboolean—Strip explanatory tail clauses and deduplicate bullet lines (~20-40% smaller output). Used by: generate, scaffold, refresh.
coverage_dirstring—Path to existing coverage report directory. Used by: metrics. Defaults to coverage/ relative to project_dir.
custom_serversobject—Custom MCP servers. Used by: configure_mcp.
deployment_urlstring—Override deployment URL for smoke test. Used by: start_hardening. Default: read from forgecraft.yaml or 'http://localhost:3000'.
descriptionstring—Natural language description. Used by: classify.
dry_runboolean—Preview without writing files. Used by: scaffold.
forceboolean—Overwrite existing files. Used by: scaffold.
has_consumersboolean—Phase 2 answer: true = existing users or downstream consumers (behavioral contracts required), false = no consumers yet. Used by: setup_project (phase 2).
include_anti_patternsboolean—Scan for anti-patterns. Used by: audit. Default: true.
include_mutationboolean—Run Stryker mutation testing (slow, opt-in). Used by: metrics. Default: false.
include_remoteboolean—Query remote MCP registry. Used by: configure_mcp. Default: false.
item_descriptionstring—Roadmap item description for this session. Used by: generate_session_prompt. Should include actor, behavior, and postcondition.
languagestring—Programming language. Used by: scaffold, add_module. Default: typescript.
max_serversinteger—Max MCP servers to configure. Used by: configure_mcp.
mergeboolean—Merge with existing instruction files. Used by: generate. Default: true.
mvpboolean—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).
namestring—Item name. Used by: add_hook (hook name), add_module (module name).
notesstring—Evidence or justification for a verification decision. Used by: record_verification.
output_targetsarray—AI assistant targets (claude, cursor, copilot, windsurf, cline, aider). Used by: scaffold, generate, refresh.
pass_thresholdinteger—Minimum §4.3 GS score (0–14, 7 properties × 2) required for overall pass. Used by: verify. Default: 11.
phase_idstring—Verification phase ID containing the step (e.g., 'contract-definition'). Used by: record_verification.
project_dirstring—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_namestring—Human-readable project name. Used by: scaffold, generate.
project_type_overridestring—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_bystring—Who recorded this decision (e.g., 'claude-sonnet-4-5', 'human', CI name). Used by: record_verification. Defaults to 'unknown'.
release_phasestring—Current release cycle phase. Controls which test gates are shown as required vs. advisory. Used by: setup, generate, refresh. Default: development.
remote_registry_urlstring—Remote MCP registry URL override. Used by: configure_mcp.
remove_tagsarray—Tags to remove during refresh.
resourcestring—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_depthstring—Analysis depth. Used by: convert. Default: quick.
scopestring—Review scope. Used by: review. Default: comprehensive.
scope_completeboolean—Phase 2 answer: true = scope is finalized (proceed with full cascade), false = scope still evolving (lighter cascade). Used by: setup_project (phase 2).
scope_notestring—Explicit out-of-scope statement — what this session must NOT touch. Used by: generate_session_prompt.
sentinelboolean—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_typestring—Conventional commit type for session output. Used by: generate_session_prompt. Default: feature.
show_pending_onlyboolean—Show only pending/failed steps. Used by: verification_status. Default: false.
skip_load_testboolean—Skip load test phase (HARDEN-003). Used by: start_hardening. Default: true (skip when no load gates defined).
spec_pathstring—Path to an existing spec file (markdown, txt, OpenAPI). Used by: setup_project (phase 1).
spec_textstring—Paste spec text directly (markdown prose, OpenAPI description, etc.). Used by: setup_project (phase 1).
step_idstring—Verification step ID to record an acceptance decision for (e.g., 'write-hurl-spec'). Used by: record_verification.
step_statusstring—Acceptance decision for the verification step: pass | fail | skipped. Used by: record_verification.
strategy_tagstring—Tag whose verification strategy the step belongs to (e.g., 'API', 'GAME'). Used by: record_verification.
tagstring—Single tag filter. Used by: add_hook.
tagsarray—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_commandstring—Test command override. Used by: verify. Default: npm test.
tierstring—Content depth: core, recommended, optional. Used by: refresh.
timeout_msinteger—Test suite timeout in ms. Used by: verify. Default: 120000.
uncertainty_levelstring—Filter verification strategies by uncertainty level. Used by: get_verification_strategy.

No output schema declared.

No examples provided.