{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_6nkq6njfmmhu","handle":"vibedasher-mcp","url":"https://wellknown.network/agents/vibedasher-mcp","links":{"self":"https://wellknown.network/agents/vibedasher-mcp/record.json","html":"https://wellknown.network/agents/vibedasher-mcp","markdown":"https://wellknown.network/agents/vibedasher-mcp/record.md","api":"https://wellknown.network/api/v1/agents/vibedasher-mcp","status":"https://wellknown.network/api/v1/agents/vibedasher-mcp/status","claim":"https://wellknown.network/agents/vibedasher-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/vibedasher-mcp/claim.json","badge":"https://wellknown.network/agents/vibedasher-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:vibedasher-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"vibedasher-mcp","summary":"MCP server exposing the Vibedasher data engine (datasets, query, viz) to a customer's AI.","description":"# vibedasher-mcp\n\nAn [MCP](https://modelcontextprotocol.io) server that exposes the **Vibedasher data\nengine** — datasets, CSV upload + ETL, headless SQL query, and dashboard (viz)\nmanagement — as tools a customer's AI (Claude Code, Cursor, ...) can drive directly.\n\nThis is the **control plane** (VD-601, PIVOT/PLAN.md EP-6). It wraps the published\n[`vibedasher` Python SDK](https://pypi.org/project/vibedasher/) and calls only the public, metered `/api/v1/*`\nAPI.\n\n**Install:** `pip install 'vibedasher-mcp>=0.6.0'`, then `vibedasher login` — no API\nkey to mint. Live on PyPI since 2026-08-09, as are\n`vibedasher` (PyPI) and `@vibedasher/client` (npm).\n\nThe **eject tools (VD-602) ship in this package**, not separately: `eject_viz`,\n`eject_viz_files`, `eject_instructions` and `get_viz_files` are registered by\n`register_eject_tools()` in `eject.py`. They pull a viz's code plus an SDK-wiring\nmanifest so your AI can recreate the dashboard natively in your stack.\n\n## Tools\n\n| Tool | What it does |\n|------|--------------|\n| `list_datasets` | List datasets the key can read (id, name, `cleanSQLName`, status). |\n| `get_dataset(dataset_id)` | One dataset's metadata + column schema. |\n| `upload_dataset(name, csv_content, ...)` | Create a CSV dataset, upload, load, poll to READY. |\n| `run_query(sql, dataset_ids, params, type)` | **Explore.** Inline alias-only SQL across your datasets (plural, joins allowed) → typed columns + rows in the response. `type=\"wasm\"` returns a plan of presigned Parquet URLs instead of rows — the credential-free data lane for a standalone build, and the only call that builds a dataset's wasm extract. |\n| `run_query_to_file(sql, output_path, dataset_ids, params, format, overwrite)` | **Extract.** Same query, but the rows are written to a local CSV/JSONL file and never enter the response — you get back `path`, `rowCount`, `columns`, `bytes`, `truncated`. stdio only; absolute paths only; never clobbers without `overwrite=True`. |\n| `list_vizzes(include_unpubli…","publisher":{"name":"Vibedasher","url":null},"homepage":"https://vibedasher.com","repository":"https://github.com/JulienGdnr/vibedasher","version":"0.6.1","license":"MIT","protocols":["mcp"],"tags":["analytics","bi","eject","mcp","model-context-protocol","vibedasher"],"pricing":null,"endpoints":[{"url":"pypi:vibedasher-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":1,"provenance":"derived"},{"slug":"data.database","name":"Databases","confidence":0.733,"provenance":"derived"}],"categories":["data","dev"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"vibedasher-mcp","registry":"pypi","observedAt":"2026-09-10T15:25:09.963Z","publishedAt":"2026-09-07T08:10:21.605252Z","latestVersion":"0.6.1"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"vibedasher-mcp","url":"https://pypi.org/project/vibedasher-mcp/","firstSeenAt":"2026-09-10T15:23:27.614Z","fetchedAt":"2026-09-10T15:23:27.614Z","normalizedAt":"2026-09-10T15:23:27.614Z"}]},"firstSeenAt":"2026-09-10T15:23:27.614Z","updatedAt":"2026-09-10T15:25:09.963Z"}