MCP-Server
Reality Graph Verification Tools
dev.realitygraph/verification-tools
Was dieses MCP kann
Provides deterministic tools for writing and validating software task contracts, verification plans, release readiness, and coding-change evidence.
Funktionen
Tools
10
Tools
calculate_verification_capacity
Calculate verification capacity
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.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['ai_changes_per_week', 'average_review_minutes_per_change', 'available_reviewer_hours_per_week', 'evidence_coverage_percent'], 'properties': {'lang': {'enum': ['en', 'de'], 'type': 'string', 'description': 'Response language (default: en)'}, 'ai_changes_per_week': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'two_week_churn_percent': {'type': 'number', 'maximum': 100, 'minimum': 0}, 'evidence_coverage_percent': {'type': 'number', 'maximum': 100, 'minimum': 0}, 'available_reviewer_hours_per_week': {'type': 'number', 'maximum': 100000, 'minimum': 0}, 'average_review_minutes_per_change': {'type': 'number', 'maximum': 10000, 'minimum': 0.1}}}
check_release_readiness
Check release readiness
Return GO, CONDITIONAL, or NO_GO from supplied acceptance-criterion results, check evidence, rollback, monitoring, limitations, and independent review. The verdict is deliberately based only on supplied evidence; this tool does not inspect code, CI, or a deployment.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['change_summary', 'change_types', 'blast_radius', 'rollback', 'acceptance_criteria_passed', 'acceptance_criteria_failed', 'acceptance_criteria_not_run', 'checks', 'rollback_ready', 'monitoring_ready', 'known_limitations_recorded', 'independent_review'], 'properties': {'lang': {'enum': ['en', 'de'], 'type': 'string', 'description': 'Response language (default: en)'}, 'checks': {'type': 'array', 'items': {'type': 'object', 'required': ['kind', 'status'], 'properties': {'kind': {'enum': ['build', 'lint', 'typecheck', 'unit', 'integration', 'e2e', 'accessibility', 'security', 'migration', 'manual'], 'type': 'string'}, 'name': {'type': 'string', 'maxLength': 200, 'minLength': 1}, 'status': {'enum': ['pass', 'fail', 'not_run'], 'type': 'string'}, 'evidence': {'type': 'string', 'maxLength': 1000}}}, 'maxItems': 100}, 'rollback': {'enum': ['automatic', 'documented', 'manual', 'none', 'unknown'], 'type': 'string', 'description': 'Current rollback or recovery state'}, 'blast_radius': {'enum': ['single_component', 'service', 'multi_service', 'customer_data', 'production_wide'], 'type': 'string', 'description': 'Largest expected impact boundary'}, 'change_types': {'type': 'array', 'items': {'enum': ['ui', 'api', 'auth', 'database', 'payments', 'personal_data', 'dependency', 'infrastructure', 'public_api', 'compliance'], 'type': 'string'}, 'maxItems': 10, 'minItems': 1, 'description': 'Technical and risk-relevant change types'}, 'change_summary': {'type': 'string', 'maxLength': 2000, 'minLength': 10, 'description': 'Plain-language summary of the change'}, 'rollback_ready': {'type': 'boolean'}, 'monitoring_ready': {'type': 'boolean'}, 'independent_review': {'type': 'boolean'}, 'acceptance_criteria_failed': {'type': 'integer', 'maximum': 10000, 'minimum': 0}, 'acceptance_criteria_passed': {'type': 'integer', 'maximum': 10000, 'minimum': 0}, 'known_limitations_recorded': {'type': 'boolean'}, 'acceptance_criteria_not_run': {'type': 'integer', 'maximum': 10000, 'minimum': 0}}}
check_verification_debt
Check verification debt
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.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['team_size'], 'properties': {'lang': {'enum': ['en', 'de'], 'type': 'string', 'description': 'Report language (default: en)'}, 'team_size': {'type': 'integer', 'maximum': 500, 'minimum': 1, 'description': 'Number of developers on the team (required)'}, 'prs_per_month': {'type': 'integer', 'maximum': 100000, 'minimum': 1, 'description': 'Total merged PRs per month (default: team_size x prs_per_engineer_per_month)'}, 'hourly_rate_eur': {'type': 'number', 'maximum': 1000, 'minimum': 1, 'description': 'Loaded cost per engineer hour in EUR (default: 75, assumption)'}, 'ai_share_percent': {'type': 'number', 'maximum': 100, 'minimum': 0, 'description': 'Share of merges that are AI-assisted, in percent (default: 60, assumption)'}, 'ai_merges_per_month': {'type': 'integer', 'maximum': 100000, 'minimum': 0, 'description': 'AI-assisted merges per month (enables the unverified-merge rate)'}, 'merged_loc_per_week': {'type': 'number', 'maximum': 100000000, 'minimum': 0, 'description': 'Merged changed lines of code per week (enables the GVR and review-depth metrics)'}, 'rework_rate_percent': {'type': 'number', 'maximum': 100, 'minimum': 0, 'description': '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': {'type': 'number', 'maximum': 100, 'minimum': 0, 'description': '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': {'type': 'number', 'maximum': 10000, 'minimum': 0, 'description': 'Reviewer hours actually spent per week (enables the GVR metric)'}, 'hours_per_reworked_change': {'type': 'number', 'maximum': 100, 'minimum': 0.1, 'description': 'Average hours per reworked change (default: 6, assumption)'}, 'prs_per_engineer_per_month': {'type': 'number', 'maximum': 500, 'minimum': 0.1, 'description': 'Merged PRs per engineer per month (default: 20, derived from the published worked report on /measure-verification-debt)'}, 'incident_allowance_eur_per_year': {'type': 'number', 'maximum': 10000000, 'minimum': 0, 'description': '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': {'type': 'integer', 'maximum': 100000, 'minimum': 0, 'description': 'AI-assisted merges per month with recorded validation evidence (enables the unverified-merge rate)'}, 'review_reconstruction_hours_per_pr': {'type': 'number', 'maximum': 20, 'minimum': 0, 'description': 'Average reviewer hours spent reconstructing intent per AI-assisted PR (default: 0.5, assumption)'}, 'substantive_review_comments_per_week': {'type': 'number', 'maximum': 1000000, 'minimum': 0, 'description': 'Substantive review comments per week, excluding bots and nitpicks (enables the review-depth metric)'}}}
fetch
Fetch a knowledge base document
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.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['id'], 'properties': {'id': {'type': 'string', 'maxLength': 300, 'minLength': 1, 'description': 'Document id from search results, or a realitygraph.dev URL'}}}
Ausgabeschema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['id', 'title', 'text', 'url'], 'properties': {'id': {'type': 'string'}, 'url': {'type': 'string'}, 'text': {'type': 'string'}, 'title': {'type': 'string'}, 'metadata': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'string'}}}, 'additionalProperties': False}
get_task_contract_template
Get the verifiable task contract template
Returns Reality Graph's free fill-in template (v0) for a verifiable task contract: goal, non-goals, boundaries (may change / must not change / forbidden), 3-7 yes/no acceptance criteria, validation plan, expected evidence, assumptions, open questions — with a filled example and fill-in guidance. Write the contract before an AI agent runs; verify the result against it after. format='json' returns a machine-fillable JSON structure; default is a compact markdown skeleton. Set lang='de' for German. Static content, nothing stored.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'lang': {'enum': ['en', 'de'], 'type': 'string', 'description': 'Language (default: en)'}, 'format': {'enum': ['markdown', 'json'], 'type': 'string', 'description': 'Template format (default: markdown)'}}}
get_verification_report_template
Get the verification report template
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.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'lang': {'enum': ['en', 'de'], 'type': 'string', 'description': 'Language (default: en)'}, 'format': {'enum': ['markdown', 'json'], 'type': 'string', 'description': 'Template format (default: markdown)'}}}
lint_task_spec
Lint a task specification
Check whether a free-text work order for an AI coding agent is verifiable BEFORE handing it over. Heuristic, deterministic lint of the task's form against the four building blocks of a checkable task (goal, boundaries, acceptance criteria, validation plan) plus rule checks (vague adjectives without numbers, unnamed unhappy paths, missing file anchors). Returns a status table with evidence, the concrete questions that close each gap, and a fill-in skeleton. It checks form, not content — no LLM, nothing stored. Set lang='de' for a German report.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['task'], 'properties': {'lang': {'enum': ['en', 'de'], 'type': 'string', 'description': 'Report language (default: en)'}, 'task': {'type': 'string', 'maxLength': 8000, 'minLength': 10, 'description': 'The work order / task text you intend to give an AI coding agent (English or German)'}}}
plan_change_verification
Plan verification for a change
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.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['change_summary', 'change_types', 'blast_radius', 'rollback'], 'properties': {'lang': {'enum': ['en', 'de'], 'type': 'string', 'description': 'Response language (default: en)'}, 'rollback': {'enum': ['automatic', 'documented', 'manual', 'none', 'unknown'], 'type': 'string', 'description': 'Current rollback or recovery state'}, 'blast_radius': {'enum': ['single_component', 'service', 'multi_service', 'customer_data', 'production_wide'], 'type': 'string', 'description': 'Largest expected impact boundary'}, 'change_types': {'type': 'array', 'items': {'enum': ['ui', 'api', 'auth', 'database', 'payments', 'personal_data', 'dependency', 'infrastructure', 'public_api', 'compliance'], 'type': 'string'}, 'maxItems': 10, 'minItems': 1, 'description': 'Technical and risk-relevant change types'}, 'change_summary': {'type': 'string', 'maxLength': 2000, 'minLength': 10, 'description': 'Plain-language summary of the change'}}}
search
Search the Reality Graph knowledge base
Full-text search over the Reality Graph knowledge base on AI coding verification: 40+ glossary definitions, 700+ FAQ answers, sourced statistics, and article summaries on verification debt, AI code review, spec-vs-implementation checking, EU compliance (EU AI Act, GDPR, NIS2), and AI coding governance — in English and German. Returns matching documents with title, URL, and snippet. Use fetch to read a result.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['query'], 'properties': {'lang': {'enum': ['en', 'de'], 'type': 'string', 'description': 'Restrict results to one language (default: both)'}, 'query': {'type': 'string', 'maxLength': 300, 'minLength': 2, 'description': 'Search query (English or German)'}}}
Ausgabeschema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['results'], 'properties': {'results': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'title', 'url', 'snippet'], 'properties': {'id': {'type': 'string'}, 'url': {'type': 'string'}, 'title': {'type': 'string'}, 'snippet': {'type': 'string'}}, 'additionalProperties': False}}}, 'additionalProperties': False}
validate_task_contract
Validate a filled task contract
Deterministically validates a FILLED task contract (the JSON structure from get_task_contract_template): completeness of goal/non-goals/boundaries, decidability of each acceptance criterion (vague words, missing measurable markers), automated checks in the validation plan, expected evidence, and leftover placeholders. Returns a verdict (PASS / PASS WITH WARNINGS / FAIL), four dimension scores, and a concrete fix per finding. Validates form and completeness, not correctness. No LLM, nothing stored. lang='de' for German.
Nur Lesen
Eingabeschema
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['contract'], 'properties': {'lang': {'enum': ['en', 'de'], 'type': 'string', 'description': 'Report language (default: en)'}, 'contract': {'type': 'string', 'maxLength': 16000, 'minLength': 20, 'description': "The filled task contract as a JSON string (structure from get_task_contract_template, format='json')"}}}
Verlauf
Letzte Tool-Änderungen
Hinzugefügt
calculate_verification_capacity
17. September 2026 12:39
Hinzugefügt
check_release_readiness
17. September 2026 12:39
Hinzugefügt
plan_change_verification
17. September 2026 12:39
Hinzugefügt
fetch
17. September 2026 12:39
Hinzugefügt
search
17. September 2026 12:39
Hinzugefügt
get_verification_report_template
17. September 2026 12:39
Hinzugefügt
validate_task_contract
17. September 2026 12:39
Hinzugefügt
get_task_contract_template
17. September 2026 12:39
Hinzugefügt
lint_task_spec
17. September 2026 12:39
Hinzugefügt
check_verification_debt
17. September 2026 12:39
Entdecken
Ähnliche MCP-Server
TinyFn
io.tinyfn/tinyfn
Offers deterministic utility functions for mathematics, conversions, validation, hashing, encoding, arrays, dates, colors, and pa…
hyperion
com.thetempleofdoom.hyperion/hyperion
Acts as a paid MCP tool marketplace and utility gateway with server discovery, HTTP and JavaScript tools, research, data conversi…
Andreax
io.github.moralito311-andr/andreax
Offers pay-per-call AI services for inference, agent and workflow design, OCR and transcription, code generation and review, clas…
Vee3
io.github.Vee3io/vee3
Manages Clerk authentication infrastructure, including users, organizations, domains, sessions, tokens, OAuth, SSO, machines, per…
Courier
io.github.trycourier/courier
Provides notification delivery infrastructure for users, tenants, lists, templates, preferences, journeys, automations, brands, a…
GripForge
io.github.gripforgeai/mcp
Generates, rigs, animates, analyzes, and packages game characters, weapons, armor, effects, environments, and engine-ready assets.
IA-QA — 130+ QA & Dev Tools for AI Agents
io.github.JcJamet/ia-qa-toolbox
Provides deterministic QA, evaluation, testing, code analysis, prompt and RAG checks, model comparison, and web security diagnost…
apis-io
io.apis/apis-io
Provides catalog search, comparison, scoring, enrichment, lists, and dataset exports for APIs, providers, specifications, workflo…