{"id":498963,"name":"MCP Analytics","description":"The statistical analyst in your AI chat: bring a dataset and a question, get back a citable, re-runnable report with its method named.","card_url":"https://mcpanalytics.ai/.well-known/agent.json","endpoint":"https://api.mcpanalytics.ai/auth0","protocol_version":"0.3.0","first_seen":"2026-10-28T14:57:09.657870+00:00","last_verified":"2026-10-28T14:57:09.657870+00:00","card":{"url":"https://api.mcpanalytics.ai/auth0","name":"MCP Analytics","skills":[{"id":"account_link","name":"account link","description":"Direct link to the right account page for anything not doable in chat: billing, browser upload, report management. Hand the user the link and guide them."},{"id":"about","name":"about","description":"Platform documentation and info: how it works, tiers, usage."},{"id":"agent_advisor","name":"agent advisor","description":"AI help desk: which analysis fits your question, interpreting results, fixing errors. Multi-turn."},{"id":"datasets_upload","name":"datasets upload","description":"Get your data in. Pass `data` as an array of row objects to create the dataset immediately and get a dataset_ref ready for create_analysis; omit it to get an upload link for a file only the user can reach. Add replace_ref (uuid://ID:KEY) with data to REFRESH an existing dataset in place; schedules and tools holding that reference read the new data on their next run."},{"id":"datasets_list","name":"datasets list","description":"List and search your uploaded datasets, with fuzzy matching on name, description, and tags. Returns each dataset's uuid:// reference for use in create_analysis and run_analysis."},{"id":"discover_tools","name":"discover tools","description":"Browse the analyses you can run: the ones you commissioned plus the platform Standard Library (prebuilt tools; each result tagged source:'own' or 'standard_library'). Plain-language match; no query lists everything, your own first. Nothing fits? Commission it with create_analysis."},{"id":"tools_schema","name":"tools schema","description":"Get an analysis's parameter schema. ALWAYS call before run_analysis."},{"id":"run_analysis","name":"run analysis","description":"Run an analysis on your data. Returns a shareable interactive report URL with statistics you can cite, re-run and share, and the method named."},{"id":"create_analysis","name":"create analysis","description":"Commission a NEW analysis built for your question. tier is REQUIRED. The user picks. Easiest: fuzzy_request (plain language) + dataset_ref + tier. Snapshot = instant automated report (~2-10 min). JSON = a fast computed answer, numbers + method, re-runnable tool you own (~5 min). Brief = the computed answer on a one-page report: chart, numbers, method (~7 min). Deck = commissioned deep analysis, a durable re-runnable module you own (30-45 min). Failed builds are never billed."},{"id":"modify_analysis","name":"modify analysis","description":"Modify an EXISTING analysis into a new version: reword the question, swap the method, or add a variable. Pass tool_name + changes (plain language). Rebuilds on the analysis's own dataset by default; the original stays put. Returns pipeline tracking. Follow with build_status."},{"id":"request_estimate","name":"request estimate","description":"START HERE for a new question: free, ~30 s. A rough answer over a sample plus the layout of the complete package, every place named with the question it will answer, and a page link. Then review_estimate with the user."},{"id":"review_estimate","name":"review estimate","description":"The estimate as you review it WITH the user: the question as understood, the estimated answer (sample, marked), every place and its question, the page link, a review checklist. Before order_analytics_package."},{"id":"adjust_estimate","name":"adjust estimate","description":"Apply the user's layout wishes to the estimate's page through the layout agent; a new named arrangement, nothing overwritten, no number changes."},{"id":"answer_now","name":"answer now","description":"A read of the data (average, count, total, highest/lowest by group, a value in a month) answered in this response, in seconds. Not a read -> immediate=false with the reason; continue with decide_path."},{"id":"decide_path","name":"decide path","description":"Step 0 for a new question: which path answers it on this data. One record: route (reuse | answer | package | ask | none), a score with its reason for each of answer, package, ask and none, the compiled read plan when it is a read, the method family and the library's tool fit when it is a package, and the one question to ask when something is missing. Deterministic, read-only."},{"id":"find_precedent","name":"find precedent","description":"Before estimating: how did we answer this objective before, on this data or any data? Prior packages and library runs with their tools, mappings, bespoke module names, method and verdicts. Platform-wide, read-only."},{"id":"check_tool_fit","name":"check tool fit","description":"Before naming a library tool: does it fit THIS dataset for THIS question? Column mapping, missing required inputs, method-fit verdict, the places it delivers. Read-only."},{"id":"order_analytics_package","name":"order analytics package","description":"Order what the estimate promised after reviewing it: library tools that fit, a bespoke build, or both, computed on the whole dataset; one reviewed page delivered. Credits per tool run; failed runs never billed."},{"id":"package_status","name":"package status","description":"Read an analytics package back: status, every run under it, the report link once delivered."},{"id":"rerun_package","name":"rerun package","description":"Run a delivered package again, on its own data or new data: the same tools, the same curated objects, the same layout, as a new package with its own link."},{"id":"my_objects","name":"my objects","description":"List and search the objects you own across every question: the curated charts, tables and figures of each delivered package, grouped by objective."},{"id":"build_status","name":"build status","description":"Check a commissioned build in-chat: stage progress, queue position, rejection reason if the data didn't match the objective, honest ETA, report link when delivered."},{"id":"ask_library","name":"ask library","description":"Ask a question across all your delivered analyses: a synthesized answer with citations back to specific reports."},{"id":"reports_list","name":"reports list","description":"Your report library: every analysis delivered, with status and links. Pass semantic_query to search report content in plain language."},{"id":"warehouse","name":"warehouse","description":"Query your org's data warehouse free: browse the catalog (tables with column roles + computed metrics), semantically find data, plain-language ask, or named templates. Requires warehouse enablement (business plans)."},{"id":"schedules","name":"schedules","description":"Standing re-runs of analyses you own: action='create' (weekly/monthly against a re-runnable data reference, connector:// or an https:// link; report emailed after each run), 'list', or 'cancel'."},{"id":"reports_view","name":"reports view","description":"Get a shareable browser link for a report, viewable without authentication."},{"id":"report_cards","name":"report cards","description":"Browse a delivered report's individual cards (charts, tables, insights) inline in chat."}],"version":"1.0.5","provider":{"url":"https://mcpanalytics.ai","organization":"MCP Analytics"},"_generated":{"by":"scripts/generate-agent-manifests.py","from":["https://api.mcpanalytics.ai/.well-known/mcp/server-card.json","https://api.mcpanalytics.ai/.well-known/mcp.json"],"note":"Derived from the canonical MCP documents; do not hand-edit."},"description":"The statistical analyst in your AI chat: bring a dataset and a question, get back a citable, re-runnable report with its method named.","authentication":{"note":"Authentication required for tool execution. Tool discovery is public via /mcp/discover.","schemes":["oauth2","api-key"],"oauthMetadata":"https://api.mcpanalytics.ai/.well-known/oauth-authorization-server"},"documentationUrl":"https://mcpanalytics.ai/docs/quickstart","defaultInputModes":["application/json"],"defaultOutputModes":["application/json"]},"status":"verified","publisher_domain":"mcpanalytics.ai","signature_status":"unsigned","signature_detail":"No card signature supplied","signature_key_url":null,"signature_checked_at":"2026-10-28T14:57:09.657870+00:00","domain_claimed_at":null,"domain_proof_checked_at":null,"source_name":"Publisher Agent Card","source_url":"https://mcpanalytics.ai/.well-known/agent.json","last_check":{"checked_at":"2026-10-28T14:57:09.65787+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"also_published_at":[],"history_urls":["https://mcpanalytics.ai/.well-known/agent.json"],"skills":[{"skill_id":"about","name":"about","description":"Platform documentation and info: how it works, tiers, usage.","tags":[],"quality_warning":false},{"skill_id":"account_link","name":"account link","description":"Direct link to the right account page for anything not doable in chat: billing, browser upload, report management. Hand the user the link and guide them.","tags":[],"quality_warning":false},{"skill_id":"adjust_estimate","name":"adjust estimate","description":"Apply the user's layout wishes to the estimate's page through the layout agent; a new named arrangement, nothing overwritten, no number changes.","tags":[],"quality_warning":false},{"skill_id":"agent_advisor","name":"agent advisor","description":"AI help desk: which analysis fits your question, interpreting results, fixing errors. Multi-turn.","tags":[],"quality_warning":false},{"skill_id":"answer_now","name":"answer now","description":"A read of the data (average, count, total, highest/lowest by group, a value in a month) answered in this response, in seconds. Not a read -> immediate=false with the reason; continue with decide_path.","tags":[],"quality_warning":false},{"skill_id":"ask_library","name":"ask library","description":"Ask a question across all your delivered analyses: a synthesized answer with citations back to specific reports.","tags":[],"quality_warning":false},{"skill_id":"build_status","name":"build status","description":"Check a commissioned build in-chat: stage progress, queue position, rejection reason if the data didn't match the objective, honest ETA, report link when delivered.","tags":[],"quality_warning":false},{"skill_id":"check_tool_fit","name":"check tool fit","description":"Before naming a library tool: does it fit THIS dataset for THIS question? Column mapping, missing required inputs, method-fit verdict, the places it delivers. Read-only.","tags":[],"quality_warning":false},{"skill_id":"create_analysis","name":"create analysis","description":"Commission a NEW analysis built for your question. tier is REQUIRED. The user picks. Easiest: fuzzy_request (plain language) + dataset_ref + tier. Snapshot = instant automated report (~2-10 min). JSON = a fast computed answer, numbers + method, re-runnable tool you own (~5 min). Brief = the computed answer on a one-page report: chart, numbers, method (~7 min). Deck = commissioned deep analysis, a durable re-runnable module you own (30-45 min). Failed builds are never billed.","tags":[],"quality_warning":false},{"skill_id":"datasets_list","name":"datasets list","description":"List and search your uploaded datasets, with fuzzy matching on name, description, and tags. Returns each dataset's uuid:// reference for use in create_analysis and run_analysis.","tags":[],"quality_warning":false},{"skill_id":"datasets_upload","name":"datasets upload","description":"Get your data in. Pass `data` as an array of row objects to create the dataset immediately and get a dataset_ref ready for create_analysis; omit it to get an upload link for a file only the user can reach. Add replace_ref (uuid://ID:KEY) with data to REFRESH an existing dataset in place; schedules and tools holding that reference read the new data on their next run.","tags":[],"quality_warning":false},{"skill_id":"decide_path","name":"decide path","description":"Step 0 for a new question: which path answers it on this data. One record: route (reuse | answer | package | ask | none), a score with its reason for each of answer, package, ask and none, the compiled read plan when it is a read, the method family and the library's tool fit when it is a package, and the one question to ask when something is missing. Deterministic, read-only.","tags":[],"quality_warning":false},{"skill_id":"discover_tools","name":"discover tools","description":"Browse the analyses you can run: the ones you commissioned plus the platform Standard Library (prebuilt tools; each result tagged source:'own' or 'standard_library'). Plain-language match; no query lists everything, your own first. Nothing fits? Commission it with create_analysis.","tags":[],"quality_warning":false},{"skill_id":"find_precedent","name":"find precedent","description":"Before estimating: how did we answer this objective before, on this data or any data? Prior packages and library runs with their tools, mappings, bespoke module names, method and verdicts. Platform-wide, read-only.","tags":[],"quality_warning":false},{"skill_id":"modify_analysis","name":"modify analysis","description":"Modify an EXISTING analysis into a new version: reword the question, swap the method, or add a variable. Pass tool_name + changes (plain language). Rebuilds on the analysis's own dataset by default; the original stays put. Returns pipeline tracking. Follow with build_status.","tags":[],"quality_warning":false},{"skill_id":"my_objects","name":"my objects","description":"List and search the objects you own across every question: the curated charts, tables and figures of each delivered package, grouped by objective.","tags":[],"quality_warning":false},{"skill_id":"order_analytics_package","name":"order analytics package","description":"Order what the estimate promised after reviewing it: library tools that fit, a bespoke build, or both, computed on the whole dataset; one reviewed page delivered. Credits per tool run; failed runs never billed.","tags":[],"quality_warning":false},{"skill_id":"package_status","name":"package status","description":"Read an analytics package back: status, every run under it, the report link once delivered.","tags":[],"quality_warning":false},{"skill_id":"report_cards","name":"report cards","description":"Browse a delivered report's individual cards (charts, tables, insights) inline in chat.","tags":[],"quality_warning":false},{"skill_id":"reports_list","name":"reports list","description":"Your report library: every analysis delivered, with status and links. Pass semantic_query to search report content in plain language.","tags":[],"quality_warning":false},{"skill_id":"reports_view","name":"reports view","description":"Get a shareable browser link for a report, viewable without authentication.","tags":[],"quality_warning":false},{"skill_id":"request_estimate","name":"request estimate","description":"START HERE for a new question: free, ~30 s. A rough answer over a sample plus the layout of the complete package, every place named with the question it will answer, and a page link. Then review_estimate with the user.","tags":[],"quality_warning":false},{"skill_id":"rerun_package","name":"rerun package","description":"Run a delivered package again, on its own data or new data: the same tools, the same curated objects, the same layout, as a new package with its own link.","tags":[],"quality_warning":false},{"skill_id":"review_estimate","name":"review estimate","description":"The estimate as you review it WITH the user: the question as understood, the estimated answer (sample, marked), every place and its question, the page link, a review checklist. Before order_analytics_package.","tags":[],"quality_warning":false},{"skill_id":"run_analysis","name":"run analysis","description":"Run an analysis on your data. Returns a shareable interactive report URL with statistics you can cite, re-run and share, and the method named.","tags":[],"quality_warning":false},{"skill_id":"schedules","name":"schedules","description":"Standing re-runs of analyses you own: action='create' (weekly/monthly against a re-runnable data reference, connector:// or an https:// link; report emailed after each run), 'list', or 'cancel'.","tags":[],"quality_warning":false},{"skill_id":"tools_schema","name":"tools schema","description":"Get an analysis's parameter schema. ALWAYS call before run_analysis.","tags":[],"quality_warning":false},{"skill_id":"warehouse","name":"warehouse","description":"Query your org's data warehouse free: browse the catalog (tables with column roles + computed metrics), semantically find data, plain-language ask, or named templates. Requires warehouse enablement (business plans).","tags":[],"quality_warning":false}],"quality_flags":[],"check_history":{"checks":1,"passed":1},"recent_checks":[{"card_url":"https://mcpanalytics.ai/.well-known/agent.json","checked_at":"2026-10-28T14:57:09.657870+00:00","success":true,"http_status":200,"detail":"Agent Card validated"}],"endpoint_tls_check":{"checked_at":"2026-10-28T14:57:09.657870+00:00","success":true,"detail":"Valid TLS connection to advertised endpoint host; no A2A request sent"},"protocol_check":{"checked_at":"2026-10-28T14:57:09.657870+00:00","endpoint":"https://api.mcpanalytics.ai/auth0","protocol_binding":"JSONRPC","protocol_version":"0.3.0","state":"auth_required","http_status":401,"detail":"Endpoint requires authentication; A2A response not confirmed","request_diagnostics":{"requests":[{"path":"/auth0","allow":[],"method":"POST","status":401,"version_header":"0.3","protocol_method":"tasks/get","redirect_followed":false}],"capture_version":1}},"declared_primary_endpoint":"https://api.mcpanalytics.ai/auth0","selected_connection_interface":{"url":"https://api.mcpanalytics.ai/auth0","protocolBinding":"JSONRPC","protocolVersion":"0.3.0"},"protocol_interface_checks":[{"endpoint":"https://api.mcpanalytics.ai/auth0","protocol_binding":"JSONRPC","protocol_version":"0.3.0","selected":true,"state":"auth_required","checked_at":"2026-10-28T14:57:09.657870+00:00","http_status":401,"detail":"Endpoint requires authentication; A2A response not confirmed","binding_recorded":true}],"connection_selection_note":"The selected connection uses an address advertised in the publisher card. Read-only observations do not establish task quality or safety.","x402_price_check":null,"events":[],"relationships":[],"verification":{"agent_card_url":"https://mcpanalytics.ai/.well-known/agent.json","last_successful_card_check":"2026-10-28T14:57:09.657870+00:00","latest_card_check":{"checked_at":"2026-10-28T14:57:09.65787+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"signature_status":"unsigned","signature_checked_at":"2026-10-28T14:57:09.657870+00:00","task_endpoint_tested":true,"task_execution_tested":false,"endpoint_tls_checked_at":"2026-10-28T14:57:09.657870+00:00","endpoint_tls_reachable":true,"protocol_check_state":"auth_required","protocol_checked_at":"2026-10-28T14:57:09.657870+00:00","provider_identity_verified":false,"domain_claimed_at":null,"domain_proof_checked_at":null},"synthetic_capability_tests":{"agent_id":498963,"status":"not_tested","reason_code":"not_yet_tested","consent_status":"not_confirmed","latest_observation_status":null,"last_checked_at":null,"fixture_version":"1","reference_demonstration":false,"scope":"A publisher-authorized synthetic test of a dedicated free test endpoint. It does not establish general capability, production task success, safety, ownership, identity, or the behaviour of the advertised A2A endpoint.","methodology_url":"https://localmark.ai/capability-tests","history":[]},"repair_links":{"agent_repair_url":"https://localmark.ai/agents/498963/repair","publisher_report_url":"https://localmark.ai/publishers/mcpanalytics.ai/repair","diagnostics_json_url":"https://localmark.ai/publishers/mcpanalytics.ai/repair/diagnostics.json","diagnostics_csv_url":"https://localmark.ai/publishers/mcpanalytics.ai/repair/diagnostics.csv"},"_localmark":{"contribution":{"optional":true,"directory_access":"free","operator_authorization_required":true,"affects_rankings":false,"message":"LocalMark is free. Optional contributions help fund ongoing checks.","support_url":"https://localmark.ai/support","metadata_url":"https://localmark.ai/api/v1/support/contributions"}}}