What this MCP does
Evaluates and benchmarks startup and product ideas before development.
Tools
Input schema
{'type': 'object', 'allOf': [{'if': {'required': ['evaluation_mode'], 'properties': {'evaluation_mode': {'const': 'official'}}}, 'then': {'required': ['official_authorization']}}, {'if': {'anyOf': [{'required': ['evaluation_mode'], 'properties': {'evaluation_mode': {'const': 'preview'}}}, {'not': {'required': ['evaluation_mode']}}]}, 'then': {'properties': {'official_authorization': False}}}], 'required': ['canonical_payload', 'submitted_scoring', 'metadata', 'session_id'], 'properties': {'metadata': {'type': 'object', 'required': ['submission_source'], 'properties': {'company_id': {'type': ['string', 'null'], 'maxLength': 120, 'description': 'Optional company identifier when known; null otherwise.'}, 'idea_title': {'type': ['string', 'null'], 'maxLength': 160, 'description': 'Optional display title for official evaluation Markdown (IMPL-26 Phase 3).'}, 'user_segment': {'type': ['string', 'null'], 'maxLength': 120, 'description': 'Optional analytics segment label; null if unknown.'}, 'subscriber_id': {'type': ['string', 'null'], 'maxLength': 120, 'description': 'Optional subscriber identifier when known; null otherwise.'}, 'submission_source': {'enum': ['user', 'seed', 'internal_test'], 'type': 'string', 'description': 'Who originated the submission: user, seed, or internal test.'}, 'conversation_depth': {'type': 'integer', 'minimum': 0, 'description': 'Count of substantive conversation turns before submission.'}, 'linkedin_connected': {'type': 'boolean', 'description': 'Whether the submitter has LinkedIn connected for profile enrichment.'}, 'template_completion_score': {'type': 'number', 'maximum': 1, 'minimum': 0, 'description': '0–1 completeness of structured template fields before submit.'}}, 'description': 'Submission provenance and optional display metadata.', 'additionalProperties': False}, 'session_id': {'type': 'string', 'maxLength': 80, 'minLength': 1, 'description': 'Opaque evaluate session from context or evaluate-session package read (IMPL-45). Required for user submissions.'}, 'evaluation_mode': {'enum': ['preview', 'official'], 'type': 'string', 'default': 'preview', 'description': 'preview: lens percentiles only, no LLM or baseline write (default). official: full verification path for end-of-ideation standing.'}, 'idempotency_key': {'type': ['string', 'null'], 'maxLength': 160, 'description': 'Optional key to dedupe retries of the same submission; null if unused.'}, 'canonical_payload': {'type': 'object', 'required': ['problem', 'target_customer', 'solution', 'why_now', 'industry', 'category', 'stage'], 'properties': {'stage': {'enum': ['idea', 'prototype', 'mvp', 'pilot', 'early-traction', 'production'], 'type': 'string', 'description': 'Current maturity of the idea or product.'}, 'problem': {'type': 'string', 'maxLength': 1000, 'minLength': 20, 'description': 'Customer problem being solved; concrete pain, not a feature list.'}, 'why_now': {'type': 'string', 'maxLength': 500, 'minLength': 10, 'description': 'Why this is timely now versus earlier attempts.'}, 'category': {'enum': ['b2b-saas', 'vertical-saas', 'b2c-app', 'marketplace', 'developer-tool', 'workflow-automation', 'ai-agent', 'data-product', 'api-infrastructure', 'commerce-enablement', 'managed-service', 'open-source', 'community-product', 'hardware-enabled', 'other'], 'type': 'string', 'description': 'Product or business-model category for segmentation and benchmarks.'}, 'industry': {'enum': ['fintech', 'healthtech', 'edtech', 'ecommerce', 'cybersecurity', 'climate-tech', 'energy', 'proptech', 'logistics', 'mobility', 'manufacturing', 'agriculture-and-food', 'consumer-internet', 'media-and-creator', 'enterprise-it', 'other'], 'type': 'string', 'description': 'Primary industry taxonomy label for segmentation and benchmarks.'}, 'solution': {'type': 'string', 'maxLength': 1000, 'minLength': 20, 'description': 'What you build and how it addresses the stated problem.'}, 'target_customer': {'type': 'string', 'maxLength': 500, 'minLength': 10, 'description': 'Who feels the pain and would buy or adopt; a segment, not everyone.'}}, 'description': 'Normalized idea fields used for scoring and verification.', 'additionalProperties': False}, 'submitted_scoring': {'type': 'object', 'required': ['dimension_scores', 'deviations', 'verdict_hints', 'score_rationale'], 'properties': {'deviations': {'type': 'object', 'required': ['strongest', 'weakest'], 'properties': {'weakest': {'enum': ['problem_urgency', 'customer_clarity', 'insight_strength', 'distribution_potential', 'market_potential', 'timing', 'moat_potential'], 'type': 'string', 'description': 'Dimension that most limits standing; coach here first after evaluation.'}, 'strongest': {'enum': ['problem_urgency', 'customer_clarity', 'insight_strength', 'distribution_potential', 'market_potential', 'timing', 'moat_potential'], 'type': 'string', 'description': 'Dimension the idea is relatively strongest on.'}}, 'description': 'Strongest and weakest dimensions in the submitted profile.', 'additionalProperties': False}, 'overall_score': {'type': 'integer', 'maximum': 100, 'minimum': 0, 'description': 'Optional overall score 0–100; server may recompute per contract.'}, 'verdict_hints': {'type': 'array', 'items': {'type': 'string', 'maxLength': 200, 'minLength': 1}, 'maxItems': 2, 'description': 'Up to two short hints summarizing the scoring stance.'}, 'score_rationale': {'type': 'object', 'required': ['problem_urgency', 'customer_clarity', 'insight_strength', 'distribution_potential', 'market_potential', 'timing', 'moat_potential'], 'properties': {'timing': {'type': 'string', 'maxLength': 600, 'minLength': 1, 'description': 'Evidence-backed rationale for the timing score.'}, 'moat_potential': {'type': 'string', 'maxLength': 600, 'minLength': 1, 'description': 'Evidence-backed rationale for the moat_potential score.'}, 'problem_urgency': {'type': 'string', 'maxLength': 600, 'minLength': 1, 'description': 'Evidence-backed rationale for the problem_urgency score.'}, 'customer_clarity': {'type': 'string', 'maxLength': 600, 'minLength': 1, 'description': 'Evidence-backed rationale for the customer_clarity score.'}, 'insight_strength': {'type': 'string', 'maxLength': 600, 'minLength': 1, 'description': 'Evidence-backed rationale for the insight_strength score.'}, 'market_potential': {'type': 'string', 'maxLength': 600, 'minLength': 1, 'description': 'Evidence-backed rationale for the market_potential score.'}, 'distribution_potential': {'type': 'string', 'maxLength': 600, 'minLength': 1, 'description': 'Evidence-backed rationale for the distribution_potential score.'}}, 'description': 'Per-dimension rationale text supporting each score.', 'additionalProperties': False}, 'dimension_scores': {'type': 'object', 'required': ['problem_urgency', 'customer_clarity', 'insight_strength', 'distribution_potential', 'market_potential', 'timing', 'moat_potential'], 'properties': {'timing': {'type': 'integer', 'maximum': 100, 'minimum': 0, 'description': 'How favorable current market and timing conditions are (0–100).'}, 'moat_potential': {'type': 'integer', 'maximum': 100, 'minimum': 0, 'description': 'How durable competitive advantage could become (0–100).'}, 'problem_urgency': {'type': 'integer', 'maximum': 100, 'minimum': 0, 'description': 'How painful and time-sensitive the problem is for the target customer (0–100).'}, 'customer_clarity': {'type': 'integer', 'maximum': 100, 'minimum': 0, 'description': 'How clearly the primary buyer/user and use case are defined (0–100).'}, 'insight_strength': {'type': 'integer', 'maximum': 100, 'minimum': 0, 'description': 'How non-obvious and defensible the insight or wedge is (0–100).'}, 'market_potential': {'type': 'integer', 'maximum': 100, 'minimum': 0, 'description': 'How large and reachable the opportunity looks (0–100).'}, 'distribution_potential': {'type': 'integer', 'maximum': 100, 'minimum': 0, 'description': 'How realistically the idea can reach customers (0–100).'}}, 'description': 'Per-dimension scores 0–100 matching the evaluation rubric.', 'additionalProperties': False}}, 'description': 'Client-composed scores and rationales verified under CT-03.', 'additionalProperties': False}, 'client_runtime_sidecar': {'type': 'object', 'properties': {'visibility': {'type': 'string', 'const': 'runtime_only_not_llm', 'description': 'Marker that sidecar fields are runtime-only and not LLM-visible.'}, 'idea_revision_lineage': {'type': 'object', 'required': ['idea_lineage_id'], 'properties': {'idea_lineage_id': {'type': 'string', 'maxLength': 160, 'minLength': 1, 'description': 'Stable client id linking preview/official iterations of one idea.'}, 'revision_summary': {'type': ['string', 'null'], 'maxLength': 2000, 'description': 'Short summary of what changed since the previous evaluation.'}, 'revision_target_lens': {'oneOf': [{'enum': ['problem_urgency', 'customer_clarity', 'insight_strength', 'distribution_potential', 'market_potential', 'timing', 'moat_potential'], 'type': 'string', 'description': 'One of the seven Actwise evaluation dimensions.'}, {'type': 'null'}], 'description': 'Dimension this revision aimed to improve; null if none.'}, 'previous_evaluation_id': {'type': ['string', 'null'], 'maxLength': 160, 'description': 'Prior evaluation id to compare against; null on first revision.'}}, 'description': 'Optional iteration lineage for preview progress comparison.', 'additionalProperties': False}, 'coaching_style_profile_delta': {'type': 'object', 'required': ['changed', 'patch', 'source', 'confidence'], 'properties': {'patch': {'type': 'array', 'items': {'type': 'object'}, 'description': 'Opaque patch operations describing the coaching style delta.'}, 'source': {'enum': ['explicit', 'inferred', 'mixed', 'system_default'], 'type': 'string', 'description': 'How the delta was produced: explicit, inferred, mixed, or system_default.'}, 'changed': {'type': 'boolean', 'description': 'True when the coaching style profile changed in this turn.'}, 'confidence': {'enum': ['low', 'medium', 'high'], 'type': 'string', 'description': 'Client confidence in the coaching style delta.'}}, 'description': 'Optional coaching style delta; never forwarded to scoring LLM prompts.', 'additionalProperties': False}}, 'description': 'Runtime-only client envelope fields stripped before service-side LLM prompt construction.', 'additionalProperties': False}, 'official_authorization': {'type': 'object', 'required': ['basis'], 'properties': {'basis': {'enum': ['explicit_user_request', 'user_confirmed_after_quota_disclosure'], 'type': 'string', 'description': 'Why the client is authorized to consume official evaluation quota. Completing preview alone is not authorization.'}}, 'description': 'Required when evaluation_mode is official. Records why the user authorized quota consumption.', 'additionalProperties': False}}, 'x-actwise-schema-id': 'evaluate-idea', 'additionalProperties': False, 'x-actwise-schema-version': 'SCH-01.3'}
Input schema
{'type': 'object', 'required': ['uri'], 'properties': {'uri': {'type': 'string', 'pattern': '^actwise://', 'description': 'A registered Actwise runtime resource URI.'}, 'known_etag': {'type': ['string', 'null'], 'description': 'Optional ETag of this exact resource already loaded in the current conversation.'}}, 'additionalProperties': False}
Recent tool changes
Similar MCP servers
Propick Integration MCP
Synchronizes Dubai real-estate listings, resolves projects and responsible agents, and reports import runs and per-property outco…
Advisors AI — Route a Store Need to a Service
Matches store needs to published services, provides package details and pricing, and prepares request links.
One-Page Readiness Check — 10 Signals, Arabic or English
Checks a public store page for machine-readable readiness signals and returns one actionable finding with verification evidence.
Ambix
Provides AI-accessible shared strategic memory for product teams.
Aginera
Processes construction drawings into quantity takeoffs, measured routes, schedules, and cost estimates.
mcp
Helps Amazon sellers calculate per-unit profit from settlement data and prepare drafts for seller approval.
mcp
Discovers, verifies, and enriches company and contact data for business intelligence and prospecting.