{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"smithery_ezark-consulting-agentdesk-mcp","slug":"ezark-consulting-agentdesk-mcp","name":"AgentDesk MCP","type":"mcp","url":"https://smithery.ai/servers/ezark-consulting/agentdesk-mcp","page_url":"https://unfragile.ai/ezark-consulting-agentdesk-mcp","categories":["mcp-servers","testing-quality"],"tags":["mcp","model-context-protocol","smithery:ezark-consulting/agentdesk-mcp"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"smithery_ezark-consulting-agentdesk-mcp__cap_0","uri":"capability://safety.moderation.structured.quality.assessment.for.ai.outputs","name":"structured quality assessment for ai outputs","description":"This capability evaluates AI-generated outputs using a structured framework that includes single and dual reviewer modes. It employs a scoring system from 0 to 100, categorizing issues based on predefined criteria and providing evidence-based checklists for thoroughness. This structured approach ensures consistency and reliability in quality assurance, making it distinct from traditional review methods that often lack formalized metrics.","intents":["How can I ensure the quality of my AI agent's outputs before deployment?","What system can I use to categorize and score AI-generated content?","How do I implement a dual-review process for AI outputs?"],"best_for":["AI developers looking to implement quality gates in their agent workflows"],"limitations":["Requires both reviewers to be available for dual mode, which may delay assessments","Scoring is subjective and may vary based on reviewer interpretation"],"requires":["API access to AgentDesk MCP","Familiarity with structured review processes"],"input_types":["text","structured data"],"output_types":["structured data","reports"],"categories":["safety-moderation","quality-assurance"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_ezark-consulting-agentdesk-mcp__cap_1","uri":"capability://safety.moderation.evidence.based.checklist.generation","name":"evidence-based checklist generation","description":"This capability automatically generates checklists based on the specific requirements of the AI output being reviewed. It leverages predefined criteria and contextual information to create tailored checklists that guide reviewers through the evaluation process. This ensures that all relevant aspects are considered during the review, which is often overlooked in generic checklist systems.","intents":["How can I create a checklist for reviewing AI-generated content?","What tools can help ensure all quality aspects are covered during AI output review?","Can I customize review checklists based on different AI models?"],"best_for":["Quality assurance teams in AI development"],"limitations":["Checklists are only as good as the predefined criteria; poor criteria lead to ineffective reviews","Customization requires initial setup and understanding of the model's context"],"requires":["Access to the checklist generation API","Defined quality criteria for AI outputs"],"input_types":["text","structured data"],"output_types":["checklists","structured data"],"categories":["safety-moderation","quality-assurance"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"smithery_ezark-consulting-agentdesk-mcp__cap_2","uri":"capability://safety.moderation.dual.reviewer.mode.for.independent.verification","name":"dual reviewer mode for independent verification","description":"This capability allows for a dual reviewer mode where two independent reviewers can assess the same AI output simultaneously. It uses a collaborative interface that facilitates real-time feedback and scoring, ensuring that assessments are not biased by a single perspective. This mode is particularly useful for high-stakes applications where accuracy is critical.","intents":["How can I implement a dual-review process for my AI outputs?","What system supports independent verification of AI-generated content?","Can I have multiple reviewers assess the same output for better accuracy?"],"best_for":["Teams developing high-stakes AI applications requiring rigorous quality checks"],"limitations":["Requires coordination between reviewers, which can complicate scheduling","Potential for conflicting scores that need resolution"],"requires":["Access to dual reviewer mode API","Defined roles for reviewers"],"input_types":["text","structured data"],"output_types":["structured data","review reports"],"categories":["safety-moderation","quality-assurance"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":31,"verified":false,"data_access_risk":"moderate","permissions":["API access to AgentDesk MCP","Familiarity with structured review processes","Access to the checklist generation API","Defined quality criteria for AI outputs","Access to dual reviewer mode API","Defined roles for reviewers"],"failure_modes":["Requires both reviewers to be available for dual mode, which may delay assessments","Scoring is subjective and may vary based on reviewer interpretation","Checklists are only as good as the predefined criteria; poor criteria lead to ineffective reviews","Customization requires initial setup and understanding of the model's context","Requires coordination between reviewers, which can complicate scheduling","Potential for conflicting scores that need resolution","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.05,"quality":0.41,"ecosystem":0.49000000000000005,"match_graph":0.25,"freshness":0.5,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:26.346Z","last_scraped_at":"2026-05-03T15:19:15.094Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=ezark-consulting-agentdesk-mcp","compare_url":"https://unfragile.ai/compare?artifact=ezark-consulting-agentdesk-mcp"}},"signature":"iVZ2EII3tAH/O4JrJHAwzq3ciDk585dH5rUTsD5kxg8kjvBHCRYWTGaNfjfFfaf/A0gkaHPDPRpkuFDMnyznBg==","signedAt":"2026-06-22T13:58:28.621Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/ezark-consulting-agentdesk-mcp","artifact":"https://unfragile.ai/ezark-consulting-agentdesk-mcp","verify":"https://unfragile.ai/api/v1/verify?slug=ezark-consulting-agentdesk-mcp","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}