{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_z6k8ehn34gr8","handle":"sciflow-mcp","url":"https://wellknown.network/agents/sciflow-mcp","links":{"self":"https://wellknown.network/agents/sciflow-mcp/record.json","html":"https://wellknown.network/agents/sciflow-mcp","markdown":"https://wellknown.network/agents/sciflow-mcp/record.md","api":"https://wellknown.network/api/v1/agents/sciflow-mcp","status":"https://wellknown.network/api/v1/agents/sciflow-mcp/status","claim":"https://wellknown.network/agents/sciflow-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/sciflow-mcp/claim.json","badge":"https://wellknown.network/agents/sciflow-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/sciflow-mcp/history","tools":"https://wellknown.network/api/v1/agents/sciflow-mcp/tools"},"ard":{"identifier":"urn:air::server:sciflow-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"sciflow-mcp","summary":"MCP server for building reproducible, interoperable scientific workflows on stamped data (time, depth, frequency, ...).","description":"# sciflow-mcp\n\nAn MCP server that lets scientists and their agents build **reproducible, interoperable analysis workflows** over stamped data: data positioned along time, cortical depth, frequency, or any other parametric axis.\n\nIt builds on three earlier pieces of work:\n\n- **[Collate](https://github.com/cardin-higley-lab/Collate)**: every array is paired with a stamp per sample, and multiple acquisition systems are aligned to one clock. Its `GeneralizedData` successor generalizes time to any parametric axis.\n- **[EventLogic](https://github.com/Claybarn/EventLogic)**: logical operations (AND, OR, NOT, merge, containment) on `[on, off]` intervals.\n- **The generalized analysis functions** from [Barnes et al. 2026](https://github.com/cardin-higley-lab/Barnes_et_al_2026): peri-event collation, normalization and correlation that work whatever the data's dimensionality.\n\n## Install\n\n```bash\ngit clone https://github.com/Claybarn/sciflow-mcp && cd sciflow-mcp && uv sync\n```\n\nOpening the repo in Claude Code picks up the server from [.mcp.json](.mcp.json). For other MCP clients, see [MCP tools](#mcp-tools).\n\n## Why it interoperates\n\nThere are exactly two artifact kinds. Both lie on a named **parametric axis** with a unit (`time` in `s` by default):\n\n| kind | contents | invariant |\n|---|---|---|\n| `series` | N-D `data`, 1-D `stamps`, axis labels, coordinates, `stamp_unit` | `len(stamps) == data.shape[0]`, stamps finite and non-decreasing, **the parametric axis is always axis 0** |\n| `intervals` | sorted `ons`, `offs`, `axis`, `unit` | `on <= off`; point events have `on == off` |\n\n- **Workflows are type-checked before they run.** Every operation declares which kinds it takes and which it returns.\n- **No `parametricAxis` argument.** The parametric axis is always axis 0, so `peri_event` works the same on a 1-D wheel trace, a channels × time LFP and a 32 × 32 × time imaging stack.\n- **Axes can't be mixed silently.** Operations that combine artifacts require the same parametric ax…","publisher":null,"homepage":"https://github.com/Claybarn/sciflow-mcp","repository":"https://github.com/Claybarn/sciflow-mcp","version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp","neuroscience","permutation","test","reproducibility","time","series","workflows"],"pricing":null,"endpoints":[{"url":"pypi:sciflow-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"}},"derived":{"capabilities":[{"slug":"automation.workflows","name":"Workflow Automation","confidence":1,"provenance":"declared"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["automation","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":"sciflow-mcp","registry":"pypi","observedAt":"2026-10-30T20:23:27.643Z","publishedAt":"2026-10-28T22:01:48.454569Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"sciflow-mcp","url":"https://pypi.org/project/sciflow-mcp/","firstSeenAt":"2026-10-30T20:22:33.123Z","fetchedAt":"2026-10-30T20:22:33.123Z","normalizedAt":"2026-10-30T20:22:33.123Z"}]},"firstSeenAt":"2026-10-30T20:22:33.123Z","updatedAt":"2026-10-30T20:23:27.643Z"}