dev.realitygraph/verification-tools

Est-ce que dev.realitygraph/verification-tools est sûr ?

Au dernier audit MCP Hub, le serveur MCP « dev.realitygraph/verification-tools » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 10 outils

• calculate_verification_capacity≈ 308 tokens

  Calculate weekly review demand, utilization, capacity gap, supported change throughput, and changes lacking evidence from measured team inputs. No cost model, benchmark, or hidden industry assumption is applied; the output shows the arithmetic and a concrete balancing action.

  Paramètres, retour & exemple (6)

  Paramètres

  • lang · string · optionnel · en | de
    Response language (default: en)
  • ai_changes_per_week · integer · requis
  • two_week_churn_percent · number · optionnel
  • evidence_coverage_percent · number · requis
  • available_reviewer_hours_per_week · number · requis
  • average_review_minutes_per_change · number · requis

  Exemple d'appel

  {"name": "calculate_verification_capacity", "arguments": {"ai_changes_per_week": 1, "evidence_coverage_percent": 1, "available_reviewer_hours_per_week": 1, "average_review_minutes_per_change": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• check_release_readiness≈ 635 tokens

  Return GO, CONDITIONAL, or NO_GO from supplied acceptance-criterion results, check evidence, rollback, monitoring, limitations, and independent review. The verdict is deliberately based only on supplied evidence; this tool does not inspect code, CI, or a deployment.

  Paramètres, retour & exemple (13)

  Paramètres

  • lang · string · optionnel · en | de
    Response language (default: en)
  • checks · array · requis
  • rollback · string · requis · automatic | documented | manual | none | unknown
    Current rollback or recovery state
  • blast_radius · string · requis · single_component | service | multi_service | customer_data | production_wide
    Largest expected impact boundary
  • change_types · array · requis
    Technical and risk-relevant change types
  • change_summary · string · requis
    Plain-language summary of the change
  • rollback_ready · boolean · requis
  • monitoring_ready · boolean · requis
  • independent_review · boolean · requis
  • acceptance_criteria_failed · integer · requis
  • acceptance_criteria_passed · integer · requis
  • known_limitations_recorded · boolean · requis
  • acceptance_criteria_not_run · integer · requis

  Exemple d'appel

  {"name": "check_release_readiness", "arguments": {"checks": [], "rollback": "automatic", "blast_radius": "single_component", "change_types": [], "change_summary": "texte", "rollback_ready": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• check_verification_debt≈ 963 tokens

  Estimate a software team's verification debt from team parameters. Computes the four published metrics (generation-to-verification ratio, review depth, unverified-merge rate, two-week churn) and an annual cost estimate, with the full calculation path, labeled assumptions, thresholds, and sources (GitClear, Sonar, Faros, Veracode). Deterministic arithmetic from published models - no benchmark claims. Only team_size is required; every additional parameter refines the estimate. Set lang='de' for a German report.

  Paramètres, retour & exemple (16)

  Paramètres

  • lang · string · optionnel · en | de
    Report language (default: en)
  • team_size · integer · requis
    Number of developers on the team (required)
  • prs_per_month · integer · optionnel
    Total merged PRs per month (default: team_size x prs_per_engineer_per_month)
  • hourly_rate_eur · number · optionnel
    Loaded cost per engineer hour in EUR (default: 75, assumption)
  • ai_share_percent · number · optionnel
    Share of merges that are AI-assisted, in percent (default: 60, assumption)
  • ai_merges_per_month · integer · optionnel
    AI-assisted merges per month (enables the unverified-merge rate)
  • merged_loc_per_week · number · optionnel
    Merged changed lines of code per week (enables the GVR and review-depth metrics)
  • rework_rate_percent · number · optionnel
    Share of AI-assisted changes reworked for a defect within 14 days, in percent (default: 2, the illustrative rate from /cost-of-verification-debt - replace it with your own reason-coded rate)
  • two_week_churn_percent · number · optionnel
    Share of new lines revised or reverted within 14 days, in percent. A warning signal in the metrics block; it never enters the cost model, because it measures lines and the cost model counts changes
  • reviewer_hours_per_week · number · optionnel
    Reviewer hours actually spent per week (enables the GVR metric)
  • hours_per_reworked_change · number · optionnel
    Average hours per reworked change (default: 6, assumption)
  • prs_per_engineer_per_month · number · optionnel
    Merged PRs per engineer per month (default: 20, derived from the published worked report on /measure-verification-debt)
  • incident_allowance_eur_per_year · number · optionnel
    Annual incident allowance in EUR (default: 0; add one only when you have a locally defined incident class, frequency and expected-loss method)
  • ai_merges_with_evidence_per_month · integer · optionnel
    AI-assisted merges per month with recorded validation evidence (enables the unverified-merge rate)
  • review_reconstruction_hours_per_pr · number · optionnel
    Average reviewer hours spent reconstructing intent per AI-assisted PR (default: 0.5, assumption)
  • substantive_review_comments_per_week · number · optionnel
    Substantive review comments per week, excluding bots and nitpicks (enables the review-depth metric)

  Exemple d'appel

  {"name": "check_verification_debt", "arguments": {"team_size": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• fetch≈ 271 tokens

  Fetch a document from the Reality Graph knowledge base by id (as returned by search, e.g. '/verification-debt') or by full realitygraph.dev URL. Returns the document's summary, definitions, key facts, FAQ, and sources as text, plus the canonical URL.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    Document id from search results, or a realitygraph.dev URL

  Exemple d'appel

  {"name": "fetch", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "url": "texte", "text": "texte", "title": "texte", "metadata": {}}}

• get_task_contract_template≈ 260 tokens

  Returns Reality Graph's free fill-in template (v0) for a verifiable task contract: goal, non-goals, boundaries (may change / must not change / forbidden), 3-7 yes/no acceptance criteria, validation plan, expected evidence, assumptions, open questions — with a filled example and fill-in guidance. Write the contract before an AI agent runs; verify the result against it after. format='json' returns a machine-fillable JSON structure; default is a compact markdown skeleton. Set lang='de' for German. Static content, nothing stored.

  Paramètres, retour & exemple (2)

  Paramètres

  • lang · string · optionnel · en | de
    Language (default: en)
  • format · string · optionnel · markdown | json
    Template format (default: markdown)

  Exemple d'appel

  {"name": "get_task_contract_template", "arguments": {"lang": "en", "format": "markdown"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_verification_report_template≈ 242 tokens

  Returns the free fill-in template (v0) for a verification report — the artifact you write right after an AI-assisted run: task recap, files changed AND files confirmed untouched, validation results per acceptance criterion (not authored by the generating model), what was skipped, limitations, and the explicit decision. format='json' for a machine-fillable structure; default is a compact markdown file. Static content, nothing stored. lang='de' for German.

  Paramètres, retour & exemple (2)

  Paramètres

  • lang · string · optionnel · en | de
    Language (default: en)
  • format · string · optionnel · markdown | json
    Template format (default: markdown)

  Exemple d'appel

  {"name": "get_verification_report_template", "arguments": {"lang": "en", "format": "markdown"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• lint_task_spec≈ 278 tokens

  Check whether a free-text work order for an AI coding agent is verifiable BEFORE handing it over. Heuristic, deterministic lint of the task's form against the four building blocks of a checkable task (goal, boundaries, acceptance criteria, validation plan) plus rule checks (vague adjectives without numbers, unnamed unhappy paths, missing file anchors). Returns a status table with evidence, the concrete questions that close each gap, and a fill-in skeleton. It checks form, not content — no LLM, nothing stored. Set lang='de' for a German report.

  Paramètres, retour & exemple (2)

  Paramètres

  • lang · string · optionnel · en | de
    Report language (default: en)
  • task · string · requis
    The work order / task text you intend to give an AI coding agent (English or German)

  Exemple d'appel

  {"name": "lint_task_spec", "arguments": {"task": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• plan_change_verification≈ 374 tokens

  Turn explicit change characteristics into a risk tier, required automated checks, manual scenarios, evidence, release blockers, role handoff, and canonical Reality Graph guidance. Use before implementation or review. It does not inspect code and never invents a confidence score.

  Paramètres, retour & exemple (5)

  Paramètres

  • lang · string · optionnel · en | de
    Response language (default: en)
  • rollback · string · requis · automatic | documented | manual | none | unknown
    Current rollback or recovery state
  • blast_radius · string · requis · single_component | service | multi_service | customer_data | production_wide
    Largest expected impact boundary
  • change_types · array · requis
    Technical and risk-relevant change types
  • change_summary · string · requis
    Plain-language summary of the change

  Exemple d'appel

  {"name": "plan_change_verification", "arguments": {"rollback": "automatic", "blast_radius": "single_component", "change_types": [], "change_summary": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search≈ 344 tokens

  Full-text search over the Reality Graph knowledge base on AI coding verification: 40+ glossary definitions, 700+ FAQ answers, sourced statistics, and article summaries on verification debt, AI code review, spec-vs-implementation checking, EU compliance (EU AI Act, GDPR, NIS2), and AI coding governance — in English and German. Returns matching documents with title, URL, and snippet. Use fetch to read a result.

  Paramètres, retour & exemple (2)

  Paramètres

  • lang · string · optionnel · en | de
    Restrict results to one language (default: both)
  • query · string · requis
    Search query (English or German)

  Exemple d'appel

  {"name": "search", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"results": []}}

• validate_task_contract≈ 282 tokens

  Deterministically validates a FILLED task contract (the JSON structure from get_task_contract_template): completeness of goal/non-goals/boundaries, decidability of each acceptance criterion (vague words, missing measurable markers), automated checks in the validation plan, expected evidence, and leftover placeholders. Returns a verdict (PASS / PASS WITH WARNINGS / FAIL), four dimension scores, and a concrete fix per finding. Validates form and completeness, not correctness. No LLM, nothing stored. lang='de' for German.

  Paramètres, retour & exemple (2)

  Paramètres

  • lang · string · optionnel · en | de
    Report language (default: en)
  • contract · string · requis
    The filled task contract as a JSON string (structure from get_task_contract_template, format='json')

  Exemple d'appel

  {"name": "validate_task_contract", "arguments": {"contract": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://realitygraph.dev/api/mcp