{"apiVersion":"v1","directorySlug":"webrobot-mcp-ba31a50335","title":"WebRobot Ltd → Agentic ETL AI Big-data Science Automation In","description":"Agentic ETL AI-based, data pipeline-assisted, scalable infrastructure for data science automation, mining, analytics, LLM fine-tuning, and data-driven companies","pageUrl":"https://www.mcpbundles.com/skills/webrobot-mcp-ba31a50335","connectPath":"importable","connectAction":"import_server","catalogListing":false,"bundleSlug":null,"listingKind":"remote_mcp","kind":"provider","transportUrl":"https://mcp.webrobot.eu/mcp","hostedMcpUrl":null,"toolCount":21,"toolInventoryStatus":"observed","refreshedAt":"2026-11-03T13:26:00.516172+00:00","registryName":"eu.webrobot/webrobot-mcp-ba31a50335","registryVersion":"2026.11.3","registryEligible":true,"tools":[{"name":"cleanupStaleByocSecrets","description":"Executes POST /webrobot/api/demo/agentic/byoc/cleanup-stale-secrets","inputSchema":{"type":"object","required":[],"properties":{"X-Cleanup-Secret":{"type":"string"}}},"logicalName":"cleanupStaleByocSecrets","displayName":"cleanupStaleByocSecrets","title":"cleanupStaleByocSecrets","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"executionDetail","description":"Executes GET /webrobot/api/demo/agentic/executions/{eid}","inputSchema":{"type":"object","required":["eid"],"properties":{"eid":{"type":"string"}}},"logicalName":"executionDetail","displayName":"executionDetail","title":"executionDetail","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"listDemos","description":"Executes GET /webrobot/api/demo/agentic/list","inputSchema":{"type":"object","required":[],"properties":{}},"logicalName":"listDemos","displayName":"listDemos","title":"listDemos","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"runDemo","description":"Executes POST /webrobot/api/demo/agentic/run/{profile-name}","inputSchema":{"type":"object","required":["profile-name"],"properties":{"body":{"type":"object","additionalProperties":true},"profile-name":{"type":"string"}}},"logicalName":"runDemo","displayName":"runDemo","title":"runDemo","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"validateHetznerToken","description":"Executes POST /webrobot/api/demo/agentic/byoc/validate-hetzner-token","inputSchema":{"type":"object","required":[],"properties":{"body":{"type":"object","additionalProperties":true}}},"logicalName":"validateHetznerToken","displayName":"validateHetznerToken","title":"validateHetznerToken","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"answerForm","description":"Executes GET /webrobot/api/demo/hitl/{id}/answer","inputSchema":{"type":"object","required":["id"],"properties":{"t":{"type":"string"},"id":{"type":"integer","format":"int64"}}},"logicalName":"answerForm","displayName":"answerForm","title":"answerForm","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"submitAnswer","description":"Executes POST /webrobot/api/demo/hitl/{id}/answer","inputSchema":{"type":"object","required":["id"],"properties":{"t":{"type":"string"},"id":{"type":"integer","format":"int64"},"answer":{"type":"string"}}},"logicalName":"submitAnswer","displayName":"submitAnswer","title":"submitAnswer","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"uploadDataset","description":"Upload a CSV dataset via JSON (NOT multipart) and create a demo input\ndataset. Pass the raw CSV text in `csv` (first line = header). Returns\n{datasetId, name, ...}; pass the returned datasetId to executeDemo /\nsaveGeneratedPipeline as the pipeline input.","inputSchema":{"type":"object","required":["name","csv"],"properties":{"csv":{"type":"string"},"name":{"type":"string"}}},"logicalName":"uploadDataset","displayName":"uploadDataset","title":"uploadDataset","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"generatePipeline","description":"Generate a pipeline manifest from a natural-language description.\nReturns {pipeline_name, pipeline_yaml}.","inputSchema":{"type":"object","required":["prompt"],"properties":{"prompt":{"type":"string"}}},"logicalName":"generatePipeline","displayName":"generatePipeline","title":"generatePipeline","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"saveGeneratedPipeline","description":"Save a pipeline (upsert by name as 'Generated: <name>'). execute=True also\nruns it; dataset_id attaches a pre-uploaded input dataset.","inputSchema":{"type":"object","required":["pipeline_name","pipeline_yaml"],"properties":{"execute":{"type":"boolean","default":false},"dataset_id":{"anyOf":[{"type":"integer"},{"type":"null"}],"default":null},"pipeline_name":{"type":"string"},"pipeline_yaml":{"type":"string"}}},"logicalName":"saveGeneratedPipeline","displayName":"saveGeneratedPipeline","title":"saveGeneratedPipeline","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"wizardValidate","description":"VALIDATE a pipeline YAML on Camoufox (dry-run) and return sample rows.\nNB the field is `yaml` (full pipeline YAML), not pipeline_yaml. session_id\nreuses a live designer session. Returns {valid, records, record_count, steps}.","inputSchema":{"type":"object","required":["yaml"],"properties":{"yaml":{"type":"string"},"session_id":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null}}},"logicalName":"wizardValidate","displayName":"wizardValidate","title":"wizardValidate","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"executeDemo","description":"Run a saved demo pipeline. limit clamped 5–10. execution_mode 'shared'\n(default) or 'byoc' (needs hetzner_api_key → runs on the user's Hetzner VMs).\n`engine`: set to \"scrapy\" to run a SMALL ingestion-only pipeline (fetch/wget/visit/\nexplore/join/flatSelect/extract — NO analytics/LLM/intelligent stages) on the\nlightweight Scrapy engine (Ray, no code-gen) instead of the default distributed\nSpark engine; rejected (with the unsupported stages) if the pipeline needs analytics.\nOmit `engine` for the d","inputSchema":{"type":"object","required":["pipeline_name"],"properties":{"limit":{"type":"integer","default":10},"engine":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null},"dataset_id":{"anyOf":[{"type":"integer"},{"type":"null"}],"default":null},"pipeline_name":{"type":"string"},"execution_mode":{"type":"string","default":"shared"},"hetzner_api_key":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null}}},"logicalName":"executeDemo","displayName":"executeDemo","title":"executeDemo","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"inferVariables","description":"Detect templatizable variables (keywords in url/selectors) to bind to a\ndataset column for a per-row sweep. Returns {variables:[...]}.","inputSchema":{"type":"object","required":["pipeline_yaml"],"properties":{"pipeline_yaml":{"type":"string"},"dataset_columns":{"anyOf":[{"type":"array","items":{"type":"string"}},{"type":"null"}],"default":null}}},"logicalName":"inferVariables","displayName":"inferVariables","title":"inferVariables","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"applyVariables","description":"Persist a templatized pipeline (rewrites + saves the parameterized YAML).","inputSchema":{"type":"object","required":["pipeline_name","pipeline_yaml"],"properties":{"pipeline_name":{"type":"string"},"pipeline_yaml":{"type":"string"}}},"logicalName":"applyVariables","displayName":"applyVariables","title":"applyVariables","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"cmfOpen","description":"Open a URL in a fresh Camoufox designer session (returns session_id +\nrewritten html). country = ISO-2 geo (DataImpulse __cr.<country> proxy).","inputSchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string"},"country":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null}}},"logicalName":"cmfOpen","displayName":"cmfOpen","title":"cmfOpen","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"wizardInferSelector","description":"Infer a CSS selector for `intent` on a page (pass url OR pre-rendered html).","inputSchema":{"type":"object","required":["intent"],"properties":{"url":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null},"html":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null},"intent":{"type":"string"},"stage_name":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null}}},"logicalName":"wizardInferSelector","displayName":"wizardInferSelector","title":"wizardInferSelector","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"wizardInferFields","description":"Infer field selectors (comma-list `intent`) within an optional\ncontainer_selector (flatSelect segment → relative selectors).","inputSchema":{"type":"object","required":["intent"],"properties":{"url":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null},"html":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null},"intent":{"type":"string"},"stage_name":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null},"container_selector":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null}}},"logicalName":"wizardInferFields","displayName":"wizardInferFields","title":"wizardInferFields","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"wizardInferSegment","description":"Infer the repeating-row segment selector (PTA) for flatSelect. url OR html.","inputSchema":{"type":"object","properties":{"url":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null},"html":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null},"segmentation_prompt":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null}}},"logicalName":"wizardInferSegment","displayName":"wizardInferSegment","title":"wizardInferSegment","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"ragQuery","description":"Retrieve the top-k most relevant knowledge/style chunks from an external\nRAG index (LlamaCloud) to GROUND the answer in uploaded documents — pure\nretrieval, the agent itself reasons over the returned chunks.","inputSchema":{"type":"object","required":["question","index_name"],"properties":{"top_k":{"type":"integer","default":5},"filters":{"anyOf":[{"type":"object","additionalProperties":true},{"type":"null"}],"default":null},"question":{"type":"string"},"index_name":{"type":"string"},"project_name":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null}}},"logicalName":"ragQuery","displayName":"ragQuery","title":"ragQuery","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"webSearch","description":"Search the web (Google) to find pages/sites/context that SUPPORT setting\nup a scrape — locate a target listing/detail page, find docs, or verify a\nfact. Returns {results:[{title, link, snippet, source}]}. This is discovery\nonly; scrape the chosen URL with the WebRobot pipeline/Camoufox tools.","inputSchema":{"type":"object","required":["query"],"properties":{"num":{"type":"integer","default":5},"query":{"type":"string"}}},"logicalName":"webSearch","displayName":"webSearch","title":"webSearch","annotations":{"untrustedContentHint":true,"readOnlyHint":true}},{"name":"ragIndexStatus","description":"Indexing status of the documents in a RAG index (LlamaCloud parses +\nembeds asynchronously). Returns {total, indexed, ready, by_status,\nfiles:[{name,status}]}. Poll until ready=true before relying on ragQuery.","inputSchema":{"type":"object","required":["index_name"],"properties":{"index_name":{"type":"string"},"project_name":{"anyOf":[{"type":"string"},{"type":"null"}],"default":null}}},"logicalName":"ragIndexStatus","displayName":"ragIndexStatus","title":"ragIndexStatus","annotations":{"untrustedContentHint":true,"readOnlyHint":true}}],"toolSource":"directory_preview","agentAction":"both","installLinks":[{"id":"cursor","label":"Cursor","href":"cursor://anysphere.cursor-deeplink/mcp/install?name=WebRobot-Ltd-Agentic-ETL-AI-Big-data-Science-Automation-In&config=eyJ1cmwiOiAiaHR0cHM6Ly9tY3Aud2Vicm9ib3QuZXUvbWNwIn0%3D"},{"id":"vscode","label":"VS Code","href":"vscode:mcp/install?%7B%22name%22%3A%22WebRobot-Ltd-Agentic-ETL-AI-Big-data-Science-Automation-In%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.webrobot.eu%2Fmcp%22%7D"},{"id":"vscode-insiders","label":"VS Code Insiders","href":"vscode-insiders:mcp/install?%7B%22name%22%3A%22WebRobot-Ltd-Agentic-ETL-AI-Big-data-Science-Automation-In%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.webrobot.eu%2Fmcp%22%7D"},{"id":"claude-web","label":"Claude.ai","href":"https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=WebRobot+Ltd+%E2%86%92+Agentic+ETL+AI+Big-data+Science+Automation+In&connectorUrl=https%3A%2F%2Fmcp.webrobot.eu%2Fmcp"},{"id":"codex","label":"Codex","copyText":"codex mcp add \"WebRobot-Ltd-Agentic-ETL-AI-Big-data-Science-Automation-In\" --url \"https://mcp.webrobot.eu/mcp\""},{"id":"chatgpt","label":"ChatGPT","href":"https://www.mcpbundles.com/docs/integrations/chatgpt"}],"catalogUrl":"https://www.mcpbundles.com/api/directory/v1/servers/webrobot-mcp-ba31a50335","callUrl":"https://www.mcpbundles.com/api/directory/v1/servers/webrobot-mcp-ba31a50335/tools/{tool}","mcpServerUrl":"https://mcp.webrobot.eu/mcp","liveCatalogUrl":"https://www.mcpbundles.com/api/directory/v1/servers/webrobot-mcp-ba31a50335?live=1"}