{"apiVersion":"v1","directorySlug":"heatscope-mcp-30dbbbb486","title":"HeatScope｜城市热环境 Spatial AI","description":"HeatScope：基于真实空间数据、模型与规划知识的城市热环境 Spatial AI Agent。","pageUrl":"https://www.mcpbundles.com/skills/heatscope-mcp-30dbbbb486","connectPath":"importable","connectAction":"import_server","catalogListing":false,"bundleSlug":null,"listingKind":"remote_mcp","kind":"provider","transportUrl":"https://heatscope.cloud/mcp","hostedMcpUrl":null,"toolCount":12,"toolInventoryStatus":"observed","refreshedAt":"2026-11-03T13:26:00.516172+00:00","registryName":"cloud.heatscope/heatscope-mcp-30dbbbb486","registryVersion":"2026.11.3","registryEligible":true,"tools":[{"name":"query","description":"Execute a read-only SQL query against the pre-loaded Tokyo LST dataset.","inputSchema":{"type":"object","required":["sql_query"],"properties":{"sql_query":{"type":"string"}},"additionalProperties":false},"logicalName":"query","displayName":"query","title":"query","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"get_stac_details","description":"Return the schema (column names, types, sample values) and parquet path\nfor the Tokyo LST dataset. Call before writing SQL.","inputSchema":{"type":"object","properties":{"collection":{"type":"object","default":null,"additionalProperties":true},"dataset_id":{"type":"string","default":"tokyo-lst"}},"additionalProperties":false},"logicalName":"get_stac_details","displayName":"get_stac_details","title":"get_stac_details","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"search_policy_knowledge","description":"Search Japanese/English policy chunks after optional structured filters.","inputSchema":{"type":"object","required":["query"],"properties":{"query":{"type":"string"},"top_k":{"type":"integer","default":5},"scenario":{"type":"string","default":null},"include_text":{"type":"boolean","default":true},"min_confidence":{"type":"string","default":"low"},"document_status":{"type":"array","items":{},"default":null},"knowledge_types":{"type":"array","items":{},"default":null},"intervention_ids":{"type":"array","items":{},"default":null}},"additionalProperties":false},"logicalName":"search_policy_knowledge","displayName":"search_policy_knowledge","title":"search_policy_knowledge","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"filter_policy_interventions","description":"Filter structured policy interventions without applying GIS causal rules.","inputSchema":{"type":"object","properties":{"limit":{"type":"integer","default":50},"scenario":{"type":"string","default":null},"categories":{"type":"array","items":{},"default":null},"policy_logic":{"type":"array","items":{},"default":null},"min_confidence":{"type":"string","default":"low"},"document_status":{"type":"array","items":{},"default":null},"include_details":{"type":"boolean","default":false},"intervention_ids":{"type":"array","items":{},"default":null}},"additionalProperties":false},"logicalName":"filter_policy_interventions","displayName":"filter_policy_interventions","title":"filter_policy_interventions","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"get_policy_evidence","description":"Return one complete policy chunk and citation-ready provenance.","inputSchema":{"type":"object","required":["chunk_id"],"properties":{"chunk_id":{"type":"string"}},"additionalProperties":false},"logicalName":"get_policy_evidence","displayName":"get_policy_evidence","title":"get_policy_evidence","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"local_moran","description":"Calculate Local Moran's I (spatial autocorrelation) for a column of the\nTokyo 200 m LST grid.","inputSchema":{"type":"object","properties":{"column":{"type":"string","default":"day_lst"},"permutations":{"type":"integer","default":999}},"additionalProperties":false},"logicalName":"local_moran","displayName":"local_moran","title":"local_moran","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"create_sql_result","description":"Run a read-only SQL query whose result is a set of grid cells with\nderived attributes, and register it as an Analysis Result (so it can be\nshown as an independent Result Layer, without touching the raw Day/Night\nLST layers).","inputSchema":{"type":"object","required":["sql_query","display_name"],"properties":{"sql_query":{"type":"string"},"display_name":{"type":"string"},"visualization":{"type":"object","default":null,"additionalProperties":true}},"additionalProperties":false},"logicalName":"create_sql_result","displayName":"create_sql_result","title":"create_sql_result","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"list_analysis_results","description":"List all registered analysis results (metadata only: analysis_id,\ndisplay_name, analysis_type, visualization, n). Use to discover results the\nagent may display with create_result_layer().","inputSchema":{"type":"object","properties":{},"additionalProperties":false},"logicalName":"list_analysis_results","displayName":"list_analysis_results","title":"list_analysis_results","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"get_analysis_result","description":"Return metadata for one analysis result (visualization, tooltip fields,\ndata URL) so create_result_layer() can render it.","inputSchema":{"type":"object","required":["analysis_id"],"properties":{"analysis_id":{"type":"string"}},"additionalProperties":false},"logicalName":"get_analysis_result","displayName":"get_analysis_result","title":"get_analysis_result","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"run_python","description":"Execute a short Python snippet for ad-hoc analysis on the Tokyo LST grid\n(e.g. a quick temporary regression).","inputSchema":{"type":"object","required":["code"],"properties":{"code":{"type":"string"},"timeout":{"type":"integer","default":30}},"additionalProperties":false},"logicalName":"run_python","displayName":"run_python","title":"run_python","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"rf_predict","description":"Predict daytime/nighttime LST (land surface temperature, °C) for grid\nparameters using the trained Random Forest models.","inputSchema":{"type":"object","properties":{"model":{"type":"string","default":"both"},"grid_id":{"type":"integer","default":null},"grid_ids":{"type":"array","items":{},"default":null},"overrides":{"type":"object","default":null,"additionalProperties":true},"parameters":{"type":"object","default":null,"additionalProperties":true}},"additionalProperties":false},"logicalName":"rf_predict","displayName":"rf_predict","title":"rf_predict","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"simulate_feature_curve","description":"Calculate a trustworthy RF local-scenario curve for one urban-form feature.","inputSchema":{"type":"object","required":["feature","values"],"properties":{"target":{"type":"string","default":"day"},"values":{"type":"array","items":{}},"area_id":{"type":"string","default":null},"feature":{"type":"string"},"grid_id":{"type":"integer","default":null},"grid_ids":{"type":"array","items":{},"default":null},"area_label":{"type":"string","default":null},"min_points":{"type":"integer","default":15},"context_mode":{"type":"string","default":"grid"}},"additionalProperties":false},"logicalName":"simulate_feature_curve","displayName":"simulate_feature_curve","title":"simulate_feature_curve","annotations":{"untrustedContentHint":true,"readOnlyHint":true}}],"toolSource":"directory_preview","agentAction":"both","installLinks":[{"id":"cursor","label":"Cursor","href":"cursor://anysphere.cursor-deeplink/mcp/install?name=HeatScope-Spatial-AI&config=eyJ1cmwiOiAiaHR0cHM6Ly9oZWF0c2NvcGUuY2xvdWQvbWNwIn0%3D"},{"id":"vscode","label":"VS Code","href":"vscode:mcp/install?%7B%22name%22%3A%22HeatScope-Spatial-AI%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fheatscope.cloud%2Fmcp%22%7D"},{"id":"vscode-insiders","label":"VS Code Insiders","href":"vscode-insiders:mcp/install?%7B%22name%22%3A%22HeatScope-Spatial-AI%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fheatscope.cloud%2Fmcp%22%7D"},{"id":"claude-web","label":"Claude.ai","href":"https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=HeatScope%EF%BD%9C%E5%9F%8E%E5%B8%82%E7%83%AD%E7%8E%AF%E5%A2%83+Spatial+AI&connectorUrl=https%3A%2F%2Fheatscope.cloud%2Fmcp"},{"id":"codex","label":"Codex","copyText":"codex mcp add \"HeatScope-Spatial-AI\" --url \"https://heatscope.cloud/mcp\""},{"id":"chatgpt","label":"ChatGPT","href":"https://www.mcpbundles.com/docs/integrations/chatgpt"}],"catalogUrl":"https://www.mcpbundles.com/api/directory/v1/servers/heatscope-mcp-30dbbbb486","callUrl":"https://www.mcpbundles.com/api/directory/v1/servers/heatscope-mcp-30dbbbb486/tools/{tool}","mcpServerUrl":"https://heatscope.cloud/mcp","liveCatalogUrl":"https://www.mcpbundles.com/api/directory/v1/servers/heatscope-mcp-30dbbbb486?live=1"}