brapi-mcp-server
Server Details
Collaborative BrAPI v2.1 MCP workspace: studies, germplasm, genotypes across Breedbase, T3, more.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- cyanheads/brapi-mcp-server
- GitHub Stars
- 4
- Server Listing
- @cyanheads/brapi-mcp-server
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 23 tools
Most tools map to a distinct resource+action, and overlapping surfaces (find_observations vs build_phenotype_matrix vs germplasm_performance, find_genotype_calls vs export_genotype_matrix) are delineated by their descriptions. The main residual ambiguity is between curated find_*/get_* tools and the raw_get/raw_search passthroughs, plus connect vs server_info which both return the orientation envelope.
All 23 tools share a brapi_ snake_case prefix with predictable verb_noun families (find_*, get_*, dataframe_*, raw_*). A few names break the pattern in minor ways (brapi_connect, brapi_server_info, brapi_federated_find, brapi_germplasm_performance), but the set remains readable and largely predictable.
23 tools is on the heavier side, but the BrAPI domain is broad (germplasm, studies, observations, variables, variants, images, locations, genotypes) and each finder/getter targets a real resource, with a small shared infrastructure layer (connect, dataframe_describe/query, describe_filters, raw passthroughs, server_info). Nothing looks redundant enough to cut without losing coverage.
The read surface covers discovery, detail fetches, genotype/phenotype matrices, pedigree traversal, federation, and spillover SQL analysis, with raw_get/raw_search as an escape hatch for anything uncurated. Gaps are minor: single-record getters exist only for germplasm, study, and image, and there's no mutation/write path, though raw passthrough mitigates both.
Available Tools
23 toolsbrapi_build_phenotype_matrixBrapi Build Phenotype MatrixARead-onlyInspect
Pull observations across one or more studies and pivot them into a germplasm × trait matrix materialized as a canvas dataframe. Returns a dataframe handle (read it with brapi_dataframe_describe and 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. A study whose pull fails is named in warnings and the rest still build the matrix; the call fails only when every study failed.
Inputs: studies (required), alias, shape, aggregate, +4 more. Returns: cap, alias, error, shape, +14 more
brapi_connectBrapi ConnectAIdempotentInspect
Open a connection to a BrAPI v2 server, authenticate, and return the full orientation envelope (server identity, capability profile, content summary, suggested next tools). Other BrAPI tools connect an alias the server has a URL configured for (a built-in or operator-configured alias, or default on a deployment with a default server) on first use; call this to connect any other server by baseUrl, to pass auth, or to re-point an alias. Supports multiple concurrent connections via named aliases. Credentials can be configured server-side and omitted from this call. When a request carries no MCP session on a deployment without per-user auth, aliases live in one namespace shared by every such caller: re-registering an alias re-points their later calls to it. Built-in known servers (callable with no baseUrl or auth — public BrAPI v2 endpoints): bti-breedbase-demo, bti-cassava, bti-sweetpotato. 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.
Inputs: auth, alias, baseUrl. Returns: auth, alias, error, notes, +8 more
brapi_dataframe_describeBrapi Dataframe DescribeARead-onlyIdempotentInspect
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. On a shared HTTP endpoint without per-caller auth, listing without a name is available only where each MCP session has its own workspace, and never to a request without a session; pass a known name instead.
Inputs: dataframe. Returns: error, tables
brapi_dataframe_queryBrapi Dataframe QueryAInspect
Run read-only 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. Use LIMIT/OFFSET to walk results, projection to trim columns, and aggregation to summarize. Use registerAs to chain — the result lands as a new dataframe.
Inputs: sql (required), preview, rowLimit, registerAs. Returns: cap, rows, error, shown, +5 more
brapi_describe_filtersBrapi Describe FiltersARead-onlyIdempotentInspect
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.
Inputs: endpoint (required). Returns: error, filters, endpoint, filterCount, +2 more
brapi_export_genotype_matrixBrapi Export Genotype MatrixARead-onlyInspect
Pull genotype calls for a variant set and pivot them into a call set × variant matrix. Each row is one call set (one sample's calls), led by callSetDbId, callSetName, and germplasmDbId — the germplasm resolved through the call set's sample, null when unresolved. Join to brapi_build_phenotype_matrix on germplasmDbId; a germplasm with several call sets joins once per call set. variantDbIds restricts the pull to chosen variants, such as a region's from brapi_find_variants. matrix-json registers a wide canvas dataframe; vcf-lite adds VCF-subset text in vcf; plink adds .ped/.map text in ped/map. Text formats pull /variants metadata and convert zero-based BrAPI start to one-based positions; missing/invalid positions use ./0. Read the dataframe with brapi_dataframe_describe and brapi_dataframe_query (SQL). variantColumnLegend maps SQL-safe columns to original variant IDs.
Inputs: format (required), variantSetDbId (required), alias, maxCalls, +3 more. Returns: map, ped, vcf, alias, +10 more
brapi_federated_findBrapi Federated FindARead-onlyInspect
Find studies, germplasm, or observations across BrAPI connection aliases. Reuses each finder’s filters, dialect handling, and read limits. Rows retain their source alias and DbId. Only an unambiguous exact germplasm PUI can group records across aliases. Returns per-alias coverage and stages the merged collection when the inline limit is reached.
Inputs: query (required), aliases (required), loadLimit. Returns: cap, error, shown, entity, +8 more
brapi_find_genotype_callsBrapi Find Genotype CallsARead-onlyInspect
Pull genotype calls for a call set × variant set. Filter to bound cost — at minimum, set one of variantSetDbId, variantSetDbIds, germplasmDbIds, callSetDbIds, or variantDbIds. The upstream pull is capped by deployment policy; when the pull is truncated, narrow the filters. results[] holds the leading calls up to loadLimit and a 24,000-byte budget; when it holds fewer than were collected, every collected call is materialized as a dataframe — read it with brapi_dataframe_describe and brapi_dataframe_query (SQL) instead of paging row-by-row.
Inputs: alias, loadLimit, callFormat, callSetDbIds, +4 more. Returns: cap, alias, error, shown, +11 more
brapi_find_germplasmBrapi Find GermplasmARead-onlyInspect
Find germplasm by name, synonym, accession number, PUI, crop, study, trial, program, or free-text query. Matches across registered synonyms. results[] holds the leading matches up to loadLimit and a 24,000-byte budget; when it holds fewer rows than matched, the matched set is materialized as a dataframe — read it with brapi_dataframe_describe and brapi_dataframe_query (SQL) instead of paging row-by-row.
Inputs: text, alias, crops, genus, +12 more. Returns: cap, alias, error, shown, +11 more
brapi_find_imagesBrapi Find ImagesARead-onlyInspect
Filter images by observation unit, observation, study, descriptive ontology term, file name, or MIME type. Named mimeTypes are verified case-insensitively on each scanned row. Returns metadata only — use brapi_get_image to fetch bytes inline. results[] holds the leading matches up to loadLimit and a 24,000-byte budget; when it holds fewer rows than matched, the matched set is materialized as a dataframe — read it with brapi_dataframe_describe and brapi_dataframe_query (SQL).
Inputs: alias, images, studies, loadLimit, +6 more. Returns: cap, alias, error, shown, +12 more
brapi_find_locationsBrapi Find LocationsARead-onlyInspect
Find research stations / field sites by country, abbreviation, type, location ID, or free-text. Pass countryCodes directly or use English countryNames to resolve ISO codes. On SGN-family servers (CassavaBase, Sweetpotatobase, other Breedbase deployments), resolved names also search alpha-2, ISO numeric, and E.164 calling codes, and a row matched only by a numeric code is dropped when its countryName names another country. Optional bbox restricts rows to a latitude/longitude window. The BrAPI Community Test Server dialect reads GeoJSON Points in [lat, lon, alt] order; other dialects use [lon, lat, alt]. results[] holds the leading matches up to loadLimit and a 24,000-byte budget; when it holds fewer rows than matched, the matched set is materialized as a dataframe — read it with brapi_dataframe_describe and brapi_dataframe_query (SQL).
Inputs: bbox, alias, loadLimit, locations, +6 more. Returns: cap, alias, error, shown, +12 more
brapi_find_observationsBrapi Find ObservationsARead-onlyInspect
Pull observation records filtered by study, germplasm, variable, season, or observation unit. SGN/Breedbase uses advertised embedded units for study or germplasm scopes. Other GET observation queries without a study, trial, observation unit, or observation anchor run a one-row count probe and skip the bulk pull when the probe fails or reports more than 5,000 rows. results[] holds the leading matches up to loadLimit and a 24,000-byte budget; when those bounds cut it short, read the staged dataframe with brapi_dataframe_describe and brapi_dataframe_query (SQL).
Inputs: alias, trials, seasons, studies, +10 more. Returns: cap, alias, error, shown, +11 more
brapi_find_studiesBrapi Find StudiesARead-onlyInspect
Locate studies matching crop, trial type, season, location, program, or recorded observation variable. Enriches results with program/trial/location context in one call. results[] holds the leading matches up to loadLimit and a 24,000-byte budget; when it holds fewer rows than matched, the matched set is materialized as a dataframe — read it with brapi_dataframe_describe and brapi_dataframe_query (SQL).
Inputs: crop, alias, active, trials, +8 more. Returns: cap, alias, error, shown, +12 more
brapi_find_variablesBrapi Find VariablesARead-onlyInspect
Find observation variables (traits) by name, trait class, ontology term, or free-text query. Free-text queries are ranked against every fetched row by PUI, name, synonym, and trait text; every match leads results[] with its textMatchRank, and a candidate carries the ontology PUI of its row as termId when the row has one. results[] holds the leading rows up to loadLimit and a 24,000-byte budget; when it holds fewer rows than matched, the matched set is materialized as a dataframe — read it with brapi_dataframe_describe and brapi_dataframe_query (SQL).
Inputs: crop, text, alias, scales, +9 more. Returns: cap, alias, error, shown, +14 more
brapi_find_variantsBrapi Find VariantsARead-onlyInspect
Find variant records by variant set, reference sequence, or genomic region. Named reference and region filters are verified on each scanned row using exact reference names and overlap with the 0-based half-open window [start, end). results[] holds the leading matches up to loadLimit and a 24,000-byte budget; when it holds fewer rows than matched, the matched set is materialized as a dataframe — read it with brapi_dataframe_describe and brapi_dataframe_query (SQL).
Inputs: end, alias, start, variants, +5 more. Returns: cap, alias, error, shown, +12 more
brapi_germplasm_performanceBrapi Germplasm PerformanceARead-onlyInspect
Aggregate a single germplasm's observations across studies, returning per-variable statistics (n, mean, median, sd, min, max), contributing studies, seasons, and collection coverage. SGN/Breedbase uses advertised germplasm-scoped observation units with embedded measurements, including zeros. Other servers discover up to 200 studies before pulling per study. Pass studyDbIds to skip discovery and restrict collection to known studies. Per-study observation limits, page limits, failures, and incomplete scans appear in coverage and warnings. For the underlying matrix, use brapi_build_phenotype_matrix.
Inputs: germplasmDbId (required), alias, loadLimit, variables, +1 more. Returns: alias, error, coverage, warnings, +6 more
brapi_get_germplasmBrapi Get GermplasmARead-onlyIdempotentInspect
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.
Inputs: germplasmDbId (required), alias. Returns: alias, error, parents, warnings, +5 more
brapi_get_imageBrapi Get ImageARead-onlyIdempotentInspect
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 or that request fails. No filesystem side-effects.
Inputs: imageDbIds (required), alias. Returns: alias, error, errors, images, +2 more
brapi_get_studyBrapi Get StudyARead-onlyIdempotentInspect
Fetch a single study by DbId with its program, trial, and location records resolved where those lookups succeed. Response includes cheap observation/observation-unit/variable counts as drill-down signals.
Inputs: studyDbId (required), alias. Returns: alias, error, study, trial, +6 more
brapi_raw_getBrapi Raw GetARead-onlyInspect
Passthrough to BrAPI GET /{path} without foreign-key resolution. List results (result array or result.data) return a leading preview within loadLimit and a 24,000-byte budget on each serialized row representation; an oversized first row returns no inline rows. Omitted fetched rows remain in a dataframe readable with brapi_dataframe_describe and brapi_dataframe_query. Explicit params.page/pageSize fetches only that upstream page, staging it if trimmed. Non-list results and envelope siblings are preserved. Emits a suggestion when a curated tool covers the endpoint.
Inputs: path (required), alias, params, loadLimit. Returns: cap, url, path, alias, +9 more
brapi_raw_searchBrapi Raw SearchARead-onlyInspect
Passthrough to BrAPI POST /search/{noun}, polling async search IDs. Sends loadLimit as the initial pageSize unless body.page/pageSize drives explicit paging. List previews fit loadLimit and a 24,000-byte budget on each serialized row representation; an oversized first row returns no inline rows. Every fetched row omitted inline stays in a dataframe readable with brapi_dataframe_describe and brapi_dataframe_query. Explicit paging fetches only the requested page, staging it if trimmed. Non-list results and envelope siblings are preserved; no distributions or foreign-key resolution.
Inputs: body (required), noun (required), alias, loadLimit. Returns: cap, kind, noun, alias, +10 more
brapi_server_infoBrapi Server InfoARead-onlyIdempotentInspect
Return the full orientation envelope for a BrAPI connection — server identity, capabilities, content counts, suggested finders, and notes. Pass forceRefresh to refetch the cached capability scan; pass an alias to read a non-default connection.
Inputs: alias, forceRefresh. Returns: auth, alias, error, notes, +8 more
brapi_walk_pedigreeBrapi Walk PedigreeARead-onlyInspect
Walk germplasm ancestry or descendancy as a deduplicated DAG with cycle detection and depth limits. leafCount counts graph terminals, confirmedLeafCount counts successfully verified leaves, and frontier records unresolved directions. Nodes and edges each fit loadLimit and a 24,000-byte preview budget; trimmed discovered graphs and already-fetched omitted relatives are staged for brapi_dataframe_describe and brapi_dataframe_query (SQL). Diagrams describe only the discovered graph, never unvisited relatives.
Inputs: germplasmDbIds (required), alias, diagram, maxDepth, +2 more. Returns: alias, edges, error, nodes, +20 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Public MCP endpoint for collaborative research and knowledge discovery.
MCP gateway federating 30 biomedical MCP servers behind one endpoint: gnomAD, ClinVar, HPO, VEP.
MetaboLights MCP — EBI's metabolomics study repository.
MCP server for Gramps genealogy via the Gramps Web API: CRUD, search, merge, timelines, DNA.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides access to EBI's MetaboLights metabolomics study repository via an MCP gateway, enabling querying and retrieval of metabolomics data.84 npmMIT
- AlicenseBqualityBmaintenanceEnables querying organism taxonomy, OBO reference terms, food and nutrition composition, organism and weather observations, and Wikidata alignments through nine MCP tools, with keyed source credentials resolved server-side.9MIT
- AlicenseBqualityCmaintenanceEnables biomedical research workflows via MCP, including experiment and document search, PDF text extraction, evidence retrieval, and validation with provenance tracking.10MIT
- AlicenseBqualityDmaintenanceMCP server providing access to the BERtron API for aggregating genomic and environmental data from multiple BER data sources, enabling geospatial search and health checks.83BSD 3-Clause
Glama MCP Gateway
Add one secure layer between your agents and this server.