A side-by-side look at the Clinicaltrialsgov MCP Server and Mydisease MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Clinicaltrialsgov MCP Server for biology, medicine and bioinformatics work as a local process; choose Mydisease for biology, medicine and bioinformatics as a local process. You can also run both side by side in one mcpServers block.
clinicaltrials_search_studies, clinicaltrials_get_study_record, clinicaltrials_get_study_count.query, disease, metadata.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Biology, Medicine and Bioinformatics | Biology, Medicine and Bioinformatics |
| Quality signal | 61/100 · Good | 45/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 99 | 0 |
| Directory activity | 1 views 0 installs 0 upvotes | 2 views 0 installs 0 upvotes |
| Tools | 7 | 3 |
| Full listing | View Clinicaltrialsgov MCP Server | View Mydisease |
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 criteriaquerySearch MyDisease.info for diseases by free-text name or fielded query. Returns matching hits, each keyed by a MONDO disease id (e.g. "MONDO:0015967") with the best-matching ontology and annotation keys. Use this to resolve a disease name to canonical ontology ids before calling the "disease" tool.…diseaseFetch the full aggregated annotation object for a single disease id. Accepts MONDO ("MONDO:0015967"), DOID ("DOID:9351"), OMIM ("OMIM:125853") and other supported ontology ids. Returns cross-referenced data including MONDO ontology (labels, synonyms, xrefs, parents/children), gene-disease associati…metadataReturns MyDisease.info build metadata: total disease document count, available annotation sources (MONDO, DOID, OMIM, DisGeNET, HPO, CTD), and their current release versions.Paste 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": {
"clinicaltrialsgov-mcp-server": {
"command": "bunx",
"args": [
"clinicaltrialsgov-mcp-server@latest"
]
}
}
}
{
"mcpServers": {
"mydisease": {
"command": "npx",
"args": [
"-y",
"@pipeworx/mcp-mydisease"
]
}
}
}