A side-by-side look at the Cbioportal and Clinicaltrialsgov MCP Server MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Cbioportal for biology & bioinformatics work as a local process; choose Clinicaltrialsgov MCP Server for biology & bioinformatics as a local process. You can also run both side by side in one mcpServers block.
search_studies, get_study, get_gene.clinicaltrials_search_studies, clinicaltrials_get_study_record, clinicaltrials_get_study_count.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Biology & Bioinformatics | Biology & Bioinformatics |
| Quality signal | 59/100 · Good | 63/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | No auth required |
| Pricing | Free | Free |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 99 |
| Directory activity | 1 views 0 installs 0 upvotes | 3 views 0 installs 0 upvotes |
| Tools | 4 | 7 |
| Full listing | View Cbioportal | View Clinicaltrialsgov MCP Server |
search_studiesSearch public cancer genomics studies in cBioPortal (TCGA, CPTAC, MSK, etc.) by keyword. Matches study name, study id, or cancer-type id (case-insensitive). Returns study ids, names, cancer types, and sample counts. Keyless, open data.get_studyGet full details for one cBioPortal cancer study by its study id (e.g. "brca_tcga_pub", "glioma_mskcc_2019"), including description, cancer type, sample count, PMID, and citation.get_geneResolve a gene to its Entrez gene id and canonical info via cBioPortal. Accepts a HUGO symbol (e.g. "TP53", "BRCA1") or an Entrez gene id. Returns entrez_gene_id, symbol, and type.list_cancer_typesList cancer types defined in cBioPortal (id, display name, parent type). Useful for resolving cancer-type ids used by studies.clinicaltrials_search_studiesSearch studies with full-text and field-specific queries, status/phase/geographic filters, pagination, sorting, and field selectionclinicaltrials_get_study_recordFetch a single study by NCT ID — full protocol record with optional location/outcome/reference capsclinicaltrials_get_study_countFast total study count for a query, without fetching dataclinicaltrials_get_field_valuesDiscover valid values for API fields, with per-value study countsclinicaltrials_get_field_definitionsResolve valid field names — keyword search, path drill-down, or top-level overviewclinicaltrials_get_study_resultsFetch posted results — outcomes, adverse events, participant flow, baseline — for completed studiesclinicaltrials_find_eligibleMatch patient demographics and conditions to candidate recruiting trials, without checking inclusion/exclusion criteriaPaste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"cbioportal": {
"command": "npx",
"args": [
"-y",
"@pipeworx/mcp-cbioportal"
]
}
}
}
{
"mcpServers": {
"clinicaltrialsgov-mcp-server": {
"command": "npx",
"args": [
"-y",
"clinicaltrialsgov-mcp-server"
]
}
}
}