BioMCP-TS MCP server

Read from the package source without running it. The installed server may list more.

• analysis_bam_summary

  Inspect an alignment (SAM/BAM/CRAM) before deeper work \u2014 "what is in this BAM?": header contigs and lengths, sample and read groups, flagstat mapping metrics, and per-contig mapped/unmapped counts via idxstats when an index is available. Follow up with analysis_bam_view_region for loci of interest; analysis_biowasm_convert for format plumbing. Large host files are estimate-gated: when the ful

• analysis_bam_view_region
• analysis_bcf_summary

  Inspect a VCF/BCF before querying variants \u2014 "what is in this variant file?": total variant record count (from the index per-contig counts when available, else a streaming count), contigs, sample count and names (watch for cohort-scale files), and the full INFO/FORMAT field inventory from the header (bcftools view -h; with an index, per-contig record counts are included). Follow up with analy

• analysis_bcf_view_region

  Variants in a genomic region as a narrow field projection instead of raw VCF rows (bcftools query): pick columns (CHROM/POS/REF/ALT/\u2026/GT), a `samples` subset (strongly recommended for cohort VCFs \u2014 the #1 context-reduction lever), an expression `filter` (e.g. 'INFO/DP>10 && QUAL>30'), and variant_types. format="artifact" returns a sliced VCF.gz for analysis_biowasm_convert instead. Defau

• analysis_bed_op

  Interval algebra on BED tracks (bedtools): intersect, merge, subtract, coverage, jaccard, or sort. Binary ops take `source` (A) and `b_source` (B) \u2014 pass b_source as an OBJECT like {"content": "chr1\t10\t20\ chr1\t100\t200\ "} or {"host_path": "..."}, never as a JSON-encoded string; set sorted_inputs=true for the memory-frugal -sorted algorithm on coordinate-sorted inputs (B-side inputs are o

• analysis_biowasm_cli

  Advanced escape hatch: run an allowlisted samtools/bedtools/bcftools subcommand directly (args are passed as an array to the tool \u2014 never through a shell). Prefer the workflow tools \u2014 analysis_bam_summary, analysis_bam_view_region, analysis_bcf_summary, analysis_bcf_view_region, analysis_bed_op, analysis_biowasm_convert \u2014 which validate inputs and bound outputs; use this only for su

• analysis_biowasm_convert

  Format plumbing between the biowasm tools: SAM/BAM/CRAM via samtools view, VCF/BCF via bcftools view, and VCF/BCF -> TSV via bcftools query with a field projection and optional filter. The input format is inferred from the source (inline content is sniffed); the result is an artifact handle (id, sha256, size, preview) reusable as artifact_id by every other analysis_biowasm tool \u2014 the glue for

• analysis_biowasm_session_info

  Biowasm runtime report: pinned samtools/bedtools/bcftools versions, asset cache location and verification time, engine status, retained artifact count, and process memory \u2014 for diagnosing analysis_biowasm_* issues. Read-only; never downloads assets or starts the worker.

• analysis_r_deseq2

  Differential expression analysis of RNA-seq count data with Bioconductor DESeq2 (negative-binomial, variance-stabilizing shrinkage, independent filtering), running in a sandboxed WebAssembly R runtime.

• analysis_r_edger

  Differential expression analysis of RNA-seq count data with Bioconductor edgeR (TMM normalization, empirical Bayes dispersion, quasi-likelihood F-test or exact test), running in a sandboxed WebAssembly R runtime.

• analysis_r_limma

  Differential expression analysis of RNA-seq count data with limma-voom (TMM normalization via edgeR, precision-weighted linear models, empirical Bayes moderation), running in a sandboxed WebAssembly R runtime.

• analysis_r_session_info

  Report the R analysis runtime status: R/WebAssembly version, installed Bioconductor package versions, library paths, memory usage, and the package mirror endpoint. Use this to diagnose analysis tool issues.

• article_get

  Get article by PMID/PMCID/DOI. Citation: fast mode (~4s, 4 providers, auto-fallback to PubMed) or full mode (~15-30s, all 5 providers incl. PubMed). Forward citation lists come from Europe PMC, Semantic Scholar, and OpenCitations; Crossref provides counts and references only.

• article_search

  Search literature across multiple backends with federated search and deduplication

• batch_get

  Get multiple entities in parallel

• biomcp_configure
• db_describe_table

  Get the column schema for a specific table. **Returns for each column:** - Field name - Data type - Nullable status - Key type (PRI for primary key) - Default value **Workflow:** 1. Use `db_list_tables` first to see available databases, aliases, and tables 2. Use this tool to understand the column structure 3. Use `db_query` to query the data **Multiple databases:** table names resolve against the

• db_list_tables

  List all tables/views across the configured database(s) with metadata. **Returns:** - `databases`: every reachable database (SQLite multi-file setups: `main` plus attached aliases) with its file path and table count - `collections`: table/view names with their owning `database`, type, and row count - Row count is approximate for MySQL; exact for SQLite tables, except for large databases (>256 MB)

• db_query
• discover

  Free-text concept resolution - find entities matching a free-text query

• disease_drugs

  Get drugs for a disease via OpenTargets

• disease_get

  Get detailed disease information by ID

• disease_search

  Search for diseases by name, phenotype, or keyword

• disease_trials

  Get clinical trials for a disease

• drug_get

  Get detailed drug information by name

• drug_search

  Search for drugs by name, mechanism, or keyword

• drug_trials

  Find clinical trials for a drug

• ensembl_consequence
• ensembl_homology

  Find orthologues or paralogues of a gene across species (Ensembl Compara) \u2014 the cross-species gene mapping source in biomcp. Returns target stable IDs, species, taxonomy level, and percent identity, sorted by identity. Accepts an HGNC symbol or Ensembl gene ID; scope to one species with target_species ('mouse') or target_taxon (10090). Use it for conservation questions ('is this gene conserve

• ensembl_lookup

  Resolve a gene in Ensembl terms for ANY Ensembl species (356 available): stable ID (ENSG\u2026), symbol\u2194ID mapping, versioned identifier, canonical transcript, and coordinates on the current assembly (GRCh38 human, GRCm39 mouse, \u2026). With expand=true, returns all transcripts with translation/protein IDs. Accepts an HGNC symbol (BRAF) or Ensembl gene ID (ENSG00000157764, versioned or bare

• ensembl_region

  Query what lives in a genomic interval on the current assembly (GRCh38 for human): genes/transcripts (stable IDs, symbols, biotypes) and known variants (rsIDs, alleles, consequence terms, clinical significance). Ideal for locus triage \u2014 "what genes and known variants sit in this GWAS hit interval?". Keep spans modest (<1 Mb recommended); output is capped at limit with a truncated marker. For

• genbank_genes

  Map a GenBank/RefSeq nucleotide accession to its NCBI Gene IDs (elink nuccore\u2192gene). The returned gene_ids are entrezgene IDs usable directly with MyGene-backed gene tools (gene_get, gene_search). Useful bridge from a sequence record to gene-level annotation.

• genbank_get

  Fetch a GenBank/RefSeq nucleotide record as text (GenBank flat file or FASTA). Whole-record fetches are capped at 2,000,000 bp \u2014 larger records require a seq_start/seq_stop region (1-based, inclusive, up to 10 Mb span; set strand=2 for a reverse-strand slice where seq_start > seq_stop \u2014 the region field echoes the request as given, while NCBI's text shows complement(min..max)). Output gu

• genbank_search

  Search NCBI nucleotide records (GenBank/RefSeq/INSDC). Queries may be plain terms, an accession, or NCBI field syntax ("TP53[Gene Name] AND Homo sapiens[Organism]", "BRCA1[Gene Name]"). Results include accession.version, definition, length_bp, organism, and topology \u2014 chain accessions into genbank_get or genbank_genes.

• gene_articles

  Find articles about a gene

• gene_diseases

  Get diseases associated with a gene. Requires DISGENET_API_KEY environment variable for DisGeNET data; falls back to OpenTargets gene-disease associations when unavailable.

• gene_drugs

  Find drugs targeting a gene

• gene_enrich

  Perform pathway enrichment analysis for a gene list

• gene_get

  Get detailed gene information by symbol

• gene_search

  Search for genes by symbol, name, or keyword

• gene_trials

  Find clinical trials for a gene

• geo_get

  Get the full SOFT record details for a GEO entry: series (GSE...), sample (GSM...), or platform (GPL...). A series detail includes summary, organisms, platform_ids, a sample preview, supplementary file URLs, and cross-references for chaining: sra \u2192 sra_get(SRP.../SRR...), pubmed_ids \u2192 article_get, samples \u2192 geo_get(GSM...), platform_ids \u2192 geo_get(GPL...). download=true addition

• geo_search

  Search NCBI GEO (Gene Expression Omnibus) for functional genomics studies \u2014 expression microarrays, RNA-seq, and other high-throughput sequencing series. Queries accept plain terms ("breast cancer RNA-seq", "melanoma single cell") or NCBI field syntax ("GSE183947[Accession]"). Each result carries cross-links for chaining: sra_project \u2192 sra_get, bioproject, pubmed_ids \u2192 article_get,

• gtex_eqtl

  Get significant cis-eQTL associations for a gene in a specific GTEx tissue (GTEx Analysis v10): variant_id, p_value, and NES (effect direction/size), sorted by ascending p-value. tissue is a required GTEx tissueSiteDetailId (e.g. Whole_Blood, Brain_Cortex).

• gtex_expression

  Get median gene expression across GTEx tissues (GTEx Analysis v10, 54 tissue sites, TPM, sorted highest first). Accepts an HGNC symbol (TP53) or Ensembl gene ID (ENSG00000141510, versioned or bare). Optionally filter to a single tissue via its tissueSiteDetailId (e.g. Brain_Cortex, Whole_Blood).

• patent_get

  Get patent details by publication number (e.g. "US11027025B2", "EP3904939B1", "US20260240819A1"). Sections: abstract, claims (US fulltext via USPTO Public Search; EP/WO via EPO OPS), citations (backward + forward), family, classifications.

• patent_search
• pdb

  Access the Protein Data Bank (RCSB PDB) for macromolecular structure data. SEARCH: Provide "query" to find structures (e.g., "kinase inhibitor", "hemoglobin"). GET: Provide "pdb_id" to retrieve entry metadata with optional detail sections. DOWNLOAD: Provide "pdb_id" + download=true to save the structure file and get the file path.

• sra_get

  Get full details for an NCBI SRA accession: SRR run (instrument, spots, bases, size), SRX experiment (library design), SRP study (experiment list), or SRS sample. Chain from geo_get (sra field) or sra_search (experiment_accession / first_run_accession). European (ERP/ERR) and DDBJ (DRP/DRR) accessions are NOT indexed in NCBI SRA \u2014 use ENA (https://www.ebi.ac.uk/ena) for those.

• sra_search

  Search NCBI's Sequence Read Archive (SRA) for sequencing experiments and runs. The query may be free text, an accession (SRP study, SRX experiment, SRR run, SRS sample), or NCBI field syntax ("RNA-SEQ AND Homo sapiens[Organism]"). Results list experiment/study/sample accessions, organism, library strategy, run count, and first_run_accession for chaining into sra_get.

• trial_get

  Get detailed trial information by NCT ID

• trial_search

  Search clinical trials by condition, intervention, or keyword

• variant_get

  Get detailed variant information with optional sections. Core data (id, gene, rsid, significance) is always returned at the top level. Use sections to request additional data.

• variant_oncokb

  Get OncoKB annotations for a variant in a cancer gene. Requires ONCOKB_TOKEN environment variable.

• variant_search

  Search for variants. Use structured parameters for best results: - rsid: e.g. query="rs113488022" - HGVS: e.g. query="NM_004333.4:c.1799T>A" - Gene filter: e.g. gene="BRAF" with hgvsp="V600E" or consequence="missense" - ClinVar significance: e.g. significance="pathogenic" Do NOT use compound free-text like "BRAF V600E" \u2014 use separate gene and hgvsp parameters instead.

• variant_trials

  Find clinical trials for a variant

• Code scan7 source files scanned20/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitystatic API keys via environment variables6/15
• Maintenancelast push 0 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Safety score

75/100

higher than 35% of 802 Databases servers

Tools

56

the typical Databases server has 8

Tools that change things

0%

typical: 10%. Fewer write tools means less an agent can break

GitHub stars

12

more than 81% of 602 Databases servers

Downloads a week

236

more than 73% of 328 Databases servers with a package

Grade history

• 2026-09-19restoreC → Bscore 75: eval / new Function used

BioMCP-TS: common questions

Is BioMCP-TS MCP server safe?

Mostly: it is graded B (75/100). Read the BioMCP-TS safety report

How do I install BioMCP-TS?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does BioMCP-TS need an API key?

Yes. The registry entry asks for NCBI_API_KEY, S2_API_KEY, OPENFDA_API_KEY, ONCOKB_TOKEN and 1 more.

Is BioMCP-TS maintained?

The last commit was 20 days ago (2026-10-15). The latest release is v1.4.3.

What can I use instead of BioMCP-TS?

Servers from other publishers that do the same job: Ensembl MCP server, DBHub MCP server and Motherduck MCP server.

How does BioMCP-TS compare with other Databases MCP servers?

safety score 75/100 (higher than 35% of 802 Databases servers); tools 56 (the typical Databases server has 8); tools that change things 0% (typical: 10%. Fewer write tools means less an agent can break). Full comparison.