io.github.cyanheads/brapi-mcp-server

Pull observations across one or more studies and pivot them into a germplasm × trait matrix materialized as a canvas dataframe. Returns a dataframe handle (query with brapi_dataframe_query) plus a summary of dimensions and aggregate method. Long-form output is suitable for downstream GROUP BY analysis by study, germplasm, or variable.

Open a connection to a BrAPI v2 server, authenticate, and return the full orientation envelope (server identity, capability profile, content summary). Required handshake before other BrAPI tools. Supports multiple concurrent connections via named aliases. Credentials can be configured server-side and omitted from this call. Built-in known servers (callable with no `baseUrl` or `auth` — public BrAPI v2 endpoints): `bti-breedbase-demo`, `bti-cassava`, `bti-sweetpotato`, `t3-barley`, `t3-oat`, `t3-wheat`. Operator-configured aliases on this deployment (credentials and/or baseUrl read from server env vars): `default`, `cassava`. Aliases are shortcuts only; any other BrAPI v2 server is reachable by passing `baseUrl` directly.

Start here after a spillover. Lists dataframes (or describes one) with columns, row counts, and originating-source provenance. The dataframe name appears inline on every find_* response that spilled (`result.dataframe.tableName`) — pass it as `dataframe` to inspect schema and provenance before writing the first brapi_dataframe_query. Listing without a name is unavailable when this server runs as a shared HTTP endpoint without per-caller auth; pass a known name instead.

Run SQL across in-memory dataframes. Dataframes auto-populate when find_* tools spill (named `df_<uuid>`) — the dataframe name appears inline on every find_* response that spilled (`result.dataframe.tableName`), so the typical flow is find_* → read the name → query here. Use brapi_dataframe_describe to inspect schema and provenance for a known name. SELECT only — writes/DDL/COPY/PRAGMA/ATTACH/file-reads are rejected. Use SQL as the paging idiom: `LIMIT/OFFSET` to walk results, projection to trim columns, aggregation to summarize. Use `registerAs` to chain — the result lands as a new dataframe.

List the valid filter names for a BrAPI endpoint (studies, germplasm, observations, variables, images, variants, locations) — companion lookup for the `extraFilters` passthrough on any `find_*` tool. Entries reflect the BrAPI v2.1 spec; individual servers may implement subsets.

Pull genotype calls for a germplasm × variant set and pivot them into a matrix. `format` controls the output: `matrix-json` registers a wide germplasm × variant canvas dataframe for SQL analysis; `vcf-lite` returns VCF-subset text (in the `vcf` field) and also registers the dataframe; `plink` returns .ped/.map text (in the `ped`/`map` fields) and also registers the dataframe. vcf-lite/plink pull /variants metadata for CHROM/POS/REF/ALT (`.`/`0` when the server lacks them). Column names are SQL-safe identifiers; `variantColumnLegend` maps them back to original variant IDs.

Pull genotype calls for a germplasm × variant set. Filter to bound cost — at minimum, set `variantSetDbId` or `germplasmDbIds`. The upstream pull is capped by deployment policy; when the pull is truncated, narrow the filters or query the spilled dataframe. `loadLimit` bounds the rows returned inline; the full collected set is materialized as a dataframe — query it with brapi_dataframe_query (SQL) instead of paging row-by-row.

Find germplasm by name, synonym, accession number, PUI, crop, or free-text query. Matches across registered synonyms. When the upstream total exceeds loadLimit, the full result set is materialized as a dataframe — query it with brapi_dataframe_query (SQL) instead of paging row-by-row.

Filter images by observation unit, observation, study, descriptive ontology term, file name, or MIME type. Returns metadata only — use brapi_get_image to fetch bytes inline. When the upstream total exceeds loadLimit, the full result set is materialized as a dataframe — query it with brapi_dataframe_query (SQL).

Find research stations / field sites by country, abbreviation, type, location ID, or free-text. Countries filter by ISO 3166-1 alpha-3 code via countryCodes, or by free-form English country name via countryNames (resolved client-side to alpha-3 — "Uganda" → "UGA"). Optional bbox parameter restricts rows to a latitude/longitude window. When the spec-correct GeoJSON [lon, lat, alt] reading produces zero matches and at least one row carries a Point geometry, the bbox filter retries once with axes swapped (handles non-conformant servers that store [lat, lon, alt]) and surfaces a warning + `coordinateAxisOrder: "swapped"`. When the upstream total exceeds loadLimit, the full result set is materialized as a dataframe — query it with brapi_dataframe_query (SQL).

Pull observation records filtered by study, germplasm, variable, season, or observation unit. When the upstream total exceeds loadLimit, the full result set is materialized as a dataframe — query it with brapi_dataframe_query (SQL).

Locate studies matching crop, trial type, season, location, or program. Enriches results with program/trial/location context in one call. When the upstream total exceeds loadLimit, the full result set is materialized as a dataframe — query it with brapi_dataframe_query (SQL).

Find observation variables (traits) by name, trait class, ontology term, or free-text query. Free-text queries are ranked against the returned set and may resolve to ontology URIs when the server advertises them. When the upstream total exceeds loadLimit, the full result set is materialized as a dataframe — query it with brapi_dataframe_query (SQL).

Find variant records by variant set, reference sequence, or genomic region (start/end, 1-based inclusive / exclusive). When the upstream total exceeds loadLimit, the full result set is materialized as a dataframe — query it with brapi_dataframe_query (SQL).

Aggregate a single germplasm's observations across every study it appears in, returning per-variable summary statistics (n, mean, median, sd, min, max), the contributing studies, and seasons. Study-anchored: discovers the germplasm's studies first (with a dialect-honor cross-check, capped at 200 studies), then pulls observations per study — avoids the unanchored germplasm-only pull that stalls on SGN/Breedbase. Pass an explicit studyDbIds set to skip discovery and its 200-study cap — e.g. process a chunk of the full study list retrieved via brapi_find_studies with extraFilters.germplasmDbIds. For the underlying observation matrix, use brapi_build_phenotype_matrix.

Fetch a single germplasm by DbId with attributes and direct parents. Response companions report study count, direct parent count, and direct descendant count — signals for pedigree depth and observation coverage.

Fetch image bytes for up to 5 imageDbIds and return them inline as `type: image` content blocks. Falls back to the metadata `imageURL` when the server lacks dedicated image-content delivery. No filesystem side-effects.

Fetch a single study by DbId with program, trial, and location fully resolved. Response includes cheap observation/observation-unit/variable counts as drill-down signals.

Passthrough to any BrAPI GET /{path} endpoint. Returns the raw upstream envelope without enrichment or foreign-key resolution. Emits a `suggestion` field when a curated tool exists for the same data. Spills to a canvas dataframe when the upstream advertises more rows than `loadLimit` AND the result is a list shape (`result` array or `result.data` envelope); inline `result` is unchanged. Skips spillover when the caller drives paging via `params.page` / `params.pageSize`.

Passthrough to any BrAPI POST /search/{noun} endpoint, returning the resolved envelope (async polling resolved upstream). Spills to a canvas dataframe when the upstream advertises more rows than `loadLimit` AND the result is a list shape; inline `result` is unchanged. Skips spillover when the caller drives paging via `body.page` / `body.pageSize`. No distributions or foreign-key resolution applied.

Return the full orientation envelope for a registered BrAPI connection — server identity, capabilities, content counts, and notes. Re-running refreshes the cached capability scan; pass an alias to read a non-default connection.

Walk germplasm ancestry or descendancy as a deduplicated DAG, with multi-generation traversal, cycle detection, and depth limits. Returns nodes + edges plus traversal stats (depthReached, rootCount, leafCount, cycleCount, deadEndCount).