{"serverId":"mcp-registry/io.github.gingiris-1031/analook","tools":[{"name":"analyze_competitor","fixed":{"name":"analyze_competitor","description":"Submit a competitor analysis job.\n\n    Analyzes a competitor's website across 15+ data sources (SEO, traffic,\n    social, Product Hunt, GitHub, Wayback Machine history, AI-generated\n    insights, etc.) and returns a job_id. Use get_report_status(job_id) to\n    poll and get_report(job_id) to retrieve results when status='completed'.\n\n    Typical analysis takes 2-5 minutes. Requires authentication (deducts 1\n    credit from your Analook balance).\n\n    Args:\n        url: Competitor website URL (e.g","inputSchema":{"type":"object","title":"analyze_competitorArguments","required":["url","context","llm_model"],"properties":{"url":{"type":"string","title":"Url"},"lang":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Lang","default":null},"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"product_name":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Product Name","default":null},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":643,"tokensAfter":643},{"name":"browse_public_reports","fixed":{"name":"browse_public_reports","description":"Browse Analook's public competitor-intelligence report gallery.\n\n    Returns recently published public reports (product name, domain, category,\n    and a link). No authentication or credits required — a fast way to discover\n    existing analyses before spending a credit on a fresh one.\n\n    Args:\n        category: Optional filter, e.g. 'AI / Agents', 'Dev Tools',\n                  'Crypto / Web3', 'Marketing / SEO', 'SaaS / Other'\n    ","inputSchema":{"type":"object","title":"browse_public_reportsArguments","required":["context","llm_model"],"properties":{"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"category":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Category","default":null},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":589,"tokensAfter":589},{"name":"get_growth_audit","fixed":{"name":"get_growth_audit","description":"Fetch a Growth Audit's three reports (Executive Summary, Diagnosis,\n    Action Plan) as Markdown.\n\n    Args:\n        job_id: ID from run_growth_audit() (starts with 'ga-')\n\n    Returns:\n        {status, reports: {executive_summary, diagnosis_report, action_plan}}\n        while running, only {status, progress} is returned.\n    ","inputSchema":{"type":"object","title":"get_growth_auditArguments","required":["job_id","context","llm_model"],"properties":{"job_id":{"type":"string","title":"Job Id"},"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":545,"tokensAfter":545},{"name":"get_report","fixed":{"name":"get_report","description":"Fetch the full competitor analysis report as structured JSON.\n\n    Reports contain: website snapshot, Wayback Machine history, SEO/traffic\n    data (DataForSEO), social media presence, Product Hunt launches, GitHub\n    stats, pricing, funding, AI-generated business insights, growth\n    playbooks, and more.\n\n    Args:\n        job_id: ID from analyze_competitor(); status must be 'completed'\n\n    Returns:\n        The full report dict (nested structure), or {error} if not found / not ready.\n    ","inputSchema":{"type":"object","title":"get_reportArguments","required":["job_id","context","llm_model"],"properties":{"job_id":{"type":"string","title":"Job Id"},"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":589,"tokensAfter":589},{"name":"get_report_markdown","fixed":{"name":"get_report_markdown","description":"Fetch the competitor analysis report as human-readable Markdown.\n\n    Suitable for piping into agents that prefer text over structured JSON,\n    or for direct display to end users.\n\n    Args:\n        job_id: ID from analyze_competitor(); status must be 'completed'\n\n    Returns:\n        {markdown: str} or {error: str}\n    ","inputSchema":{"type":"object","title":"get_report_markdownArguments","required":["job_id","context","llm_model"],"properties":{"job_id":{"type":"string","title":"Job Id"},"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":546,"tokensAfter":546},{"name":"get_report_status","fixed":{"name":"get_report_status","description":"Poll an analysis job's status.\n\n    Args:\n        job_id: ID returned from analyze_competitor()\n\n    Returns:\n        {status: 'running'|'completed'|'failed', progress?: str, report_url?: str}\n    ","inputSchema":{"type":"object","title":"get_report_statusArguments","required":["job_id","context","llm_model"],"properties":{"job_id":{"type":"string","title":"Job Id"},"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":509,"tokensAfter":509},{"name":"list_my_reports","fixed":{"name":"list_my_reports","description":"List your recent competitor analysis reports (up to 50).\n\n    Requires authentication. Returns a lightweight list (id, url,\n    product_name, created_at, status) — use get_report(job_id) to fetch\n    the full report for any of them.\n\n    Returns:\n        {reports: [{id, url, product_name, created_at, status}, ...]}\n    ","inputSchema":{"type":"object","title":"list_my_reportsArguments","required":["context","llm_model"],"properties":{"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}},"annotations":{"readOnlyHint":true}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: true (inferred from the name).","verify":true}],"tokensBefore":528,"tokensAfter":528},{"name":"run_growth_audit","fixed":{"name":"run_growth_audit","description":"Run a full Growth Audit — three linked strategic reports for a product.\n\n    Unlike analyze_competitor (a single 15-signal intelligence snapshot), a\n    Growth Audit produces an Executive Summary + a Diagnosis Report + a 30-day\n    Action Plan, grounded in real channel/tactic playbooks. Best for 'how do I\n    grow THIS product' rather than 'what is this competitor doing'.\n\n    Takes ~4-6 minutes. Requires authentication and deducts 10 credits. Poll\n    with get_growth_audit(job_id) until status=","inputSchema":{"type":"object","title":"run_growth_auditArguments","required":["url","context","llm_model"],"properties":{"url":{"type":"string","title":"Url"},"lang":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Lang","default":null},"context":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"llm_model":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"product_name":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Product Name","default":null},"conversation_id":{"type":"string","description":"Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request."}}},"annotations":{"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false}},"changes":[{"kind":"annotations","detail":"Added readOnlyHint: false, destructiveHint: false, idempotentHint: false (inferred from the name).","verify":true}],"tokensBefore":641,"tokensAfter":641}],"toolsChanged":8,"tokensSaved":0,"todo":[{"tool":"analyze_competitor","params":["url","lang","product_name"]},{"tool":"browse_public_reports","params":["category"]},{"tool":"get_growth_audit","params":["job_id"]},{"tool":"get_report","params":["job_id"]},{"tool":"get_report_markdown","params":["job_id"]},{"tool":"get_report_status","params":["job_id"]},{"tool":"run_growth_audit","params":["url","lang","product_name"]}],"note":"Deterministic fixes. Changes marked verify need a human look before shipping (renames, inferred annotations, inferred types, removed text). Parameter descriptions in `todo` need to be written by someone who knows the API."}