{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_evsjcuy24rt7","handle":"ds-workspace-mcp","url":"https://wellknown.network/agents/ds-workspace-mcp","links":{"self":"https://wellknown.network/agents/ds-workspace-mcp/record.json","html":"https://wellknown.network/agents/ds-workspace-mcp","markdown":"https://wellknown.network/agents/ds-workspace-mcp/record.md","api":"https://wellknown.network/api/v1/agents/ds-workspace-mcp","status":"https://wellknown.network/api/v1/agents/ds-workspace-mcp/status","claim":"https://wellknown.network/agents/ds-workspace-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/ds-workspace-mcp/claim.json","badge":"https://wellknown.network/agents/ds-workspace-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/ds-workspace-mcp/history","tools":"https://wellknown.network/api/v1/agents/ds-workspace-mcp/tools"},"ard":{"identifier":"urn:air::server:ds-workspace-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"ds-workspace-mcp","summary":"A Model Context Protocol server for safely inspecting and profiling local analytical datasets.","description":"# Data Science Workspace MCP Server\n\n![CI](https://github.com/DiogoRibeiro7/ds-workspace-mcp/actions/workflows/ci.yml/badge.svg)\n![Python](https://img.shields.io/badge/python-3.11%20%7C%203.12-blue)\n![License](https://img.shields.io/badge/license-MIT-green)\n![Release](https://img.shields.io/github/v/release/DiogoRibeiro7/ds-workspace-mcp?include_prereleases)\n\nA local-first **Model Context Protocol (MCP)** server for data science workspaces.\n\n`ds-workspace-mcp` gives MCP-compatible assistants structured access to analytical data\nwithout handing them arbitrary filesystem or database control. It exposes a guarded local\nworkspace where an assistant can discover datasets, inspect schemas, profile columns, run\nbounded read-only queries, evaluate baseline modeling readiness, and create reusable\nmarkdown modeling reports.\n\nThe project is built as a practical reference implementation for AI-assisted data tooling:\ntyped Python, bounded outputs, path traversal protection, read-only SQL guardrails,\nrelease metadata, Docker support, and CI-backed documentation.\n\n## At a glance\n\n| Area | What this server provides |\n| --- | --- |\n| Dataset access | Safe reads for CSV, Parquet, JSON, Excel, SQLite, and DuckDB-backed CSV queries |\n| Exploration | Preview, profiling, missingness summaries, categorical summaries, correlations, and issue detection |\n| Modeling readiness | Target suggestions, feature review, leakage checks, time-series validation, forecast baselines, and dummy baselines |\n| Report workflow | Generate, save, search, preview, compare, copy, rename, delete, and extract markdown report sections |\n| MCP integration | Resources, tools, prompts, stdio transport, Streamable HTTP transport, and runnable client examples |\n| Safety controls | Configured data/report roots, path traversal rejection, size limits, row limits, query length limits, and SQL timeouts |\n\n## Current scope\n\nToday the repository covers five practical workflows:\n\n- Safe local dataset access for CSV, Parquet, …","publisher":{"name":"Diogo Ribeiro","url":null},"homepage":"https://github.com/DiogoRibeiro7/ds-workspace-mcp#readme","repository":"https://github.com/DiogoRibeiro7/ds-workspace-mcp/blob/main/CHANGELOG.md","version":"1.3.0","license":null,"protocols":["mcp"],"tags":["mcp","model-context-protocol","data-science","analytics","python"],"pricing":null,"endpoints":[{"url":"pypi:ds-workspace-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"data.database","name":"Databases","confidence":1,"provenance":"derived"},{"slug":"dev.filesystem","name":"Filesystem","confidence":0.882,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.825,"provenance":"derived"},{"slug":"documents.spreadsheets","name":"Spreadsheets","confidence":0.733,"provenance":"derived"}],"categories":["data","dev","documents"],"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":"ds-workspace-mcp","registry":"pypi","observedAt":"2026-11-05T21:26:37.587Z","publishedAt":"2026-10-28T14:36:55.981869Z","latestVersion":"1.3.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"ds-workspace-mcp","url":"https://pypi.org/project/ds-workspace-mcp/","firstSeenAt":"2026-10-30T19:25:20.420Z","fetchedAt":"2026-11-05T21:25:12.379Z","normalizedAt":"2026-11-05T21:25:12.379Z"}]},"firstSeenAt":"2026-10-30T19:25:20.420Z","updatedAt":"2026-11-05T21:26:37.587Z"}