Provides tools for searching and retrieving biomedical literature from PubMed.
Provides tools for AI-powered academic paper search and analysis from Semantic Scholar.
Provides access to World Health Organization Global Health Observatory health statistics and data.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@life-science-mcp What drugs interact with the BRCA1 gene?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A unified MCP server for 110 life science APIs and databases.
{
"mcpServers": {
"life-science": {
"command": "npx",
"args": ["-y", "life-science-mcp"]
}
}
}Related MCP server: BioBTree
Provider | Description |
AI-predicted protein structures from DeepMind | |
Biomedical named entity recognition and normalization | |
Gene expression evolution across species and tissues | |
Metabolic network reconstructions and flux balance models | |
Mathematical models of biological systems (SBML) | |
Preprint server for biology | |
EBI biological sample metadata and attributes | |
Barcode of Life DNA barcode data | |
Global index of species names and taxonomy | |
Multidimensional cancer genomics data | |
Cell line identification and characterization | |
Chemical Entities of Biological Interest via OLS4 | |
Bioactive drug-like small molecules | |
Clinical Interpretations of Variants in Cancer | |
Registry of clinical studies worldwide | |
Genetic variants linked to clinical significance | |
FDA drug labeling and packaging information | |
Single nucleotide polymorphisms and genetic variation | |
Drug-gene interaction data | |
Gene-disease associations | |
Electron Microscopy Data Bank for 3D structures | |
European Nucleotide Archive sequence data | |
Encyclopedia of DNA Elements regulatory data | |
Gene set enrichment analysis platform | |
Genome browser and annotation | |
Open-access biomedical literature | |
Gene expression patterns across species and conditions | |
Comprehensive fish species database | |
Global Biodiversity Information Facility | |
NCI Genomic Data Commons (TCGA and more) | |
Functional gene annotations and ontology | |
Gene Expression Omnibus high-throughput datasets | |
Integrated glycoscience data for glycans and glycoproteins | |
International glycan structure repository | |
Genome Aggregation Database allele frequencies | |
G protein-coupled receptor database | |
Functional enrichment and gene ID conversion | |
Gene expression across human tissues | |
Drug targets and ligands | |
Genome-wide association studies | |
Approved human gene symbols and names | |
Human Metabolome Database | |
Human Phenotype Ontology | |
Protein expression and localization across tissues | |
Immune Epitope Database and Analysis Resource | |
Citizen science biodiversity observations | |
Curated protein-protein interactions | |
Protein families, domains, and functional sites | |
Transcription factor binding profiles | |
Pathway and molecular interaction database | |
Lipid classification and structures | |
Mass spectra for metabolite identification | |
Medical Subject Headings vocabulary | |
Metabolomics experiments and derived information | |
Metabolomics data repository and tools | |
EBI metagenomics analysis and archiving | |
Knowledge graph for disease discovery | |
Aggregated chemical and drug annotations | |
Aggregated disease annotations | |
Aggregated gene annotations | |
Aggregated genetic variant annotations | |
Microbially-derived natural products | |
Biological sample metadata for experimental assays | |
Gene-specific information from Entrez | |
GenBank and RefSeq sequences | |
Protein sequences from RefSeq, UniProt, PDB | |
Taxonomic classification and nomenclature | |
Chemical name/structure resolution and conversion | |
Biological network models exchange | |
Ocean Biodiversity Information System | |
Ontology Lookup Service for biomedical ontologies | |
Signaling pathway and molecular interaction network | |
Open citation index and bibliometrics | |
FDA data on drugs, devices, and adverse events | |
Drug target identification and prioritization | |
Comprehensive synthetic phylogenetic tree | |
Rare disease and orphan drug information | |
Gene evolutionary relationships and orthologs | |
Protein classification and evolutionary analysis | |
Protein Data Bank in Europe | |
Pharmacogenomics knowledge (via CPIC) | |
Proteomics identifications database | |
Open chemistry database | |
Biomedical literature search engine | |
Biomedical text mining and entity annotation | |
Gene Ontology browser | |
3D structural data for biological macromolecules | |
Curated biological pathway database | |
Non-coding RNA families and structured RNA elements | |
Expert-curated biochemical reactions | |
Non-coding RNA sequence database | |
Enzyme kinetics and biochemical reaction data | |
AI-powered academic paper search and analysis | |
Standardized clinical terminology (via FHIR) | |
Chemical-protein interaction network | |
Protein-protein interaction networks | |
Curated knowledge on lipid biology | |
The Cancer Imaging Archive | |
Genome browser, tracks, and annotations | |
Chemical structure cross-referencing | |
Non-redundant protein sequence archive | |
Protein sequence and functional information | |
Clustered protein sequence sets | |
World Health Organization Global Health Observatory | |
Community-curated biological pathways | |
C. elegans and nematode genomics | |
World Register of Marine Species | |
Commercially available compounds for virtual screening |
Category | Query |
Gene lookup | What is the approved gene symbol for p53 and what chromosome is it on? |
Chemistry | Give me the molecular formula, weight, and canonical SMILES for metformin. |
Functional annotation | What biological process GO terms are annotated to the human insulin receptor gene INSR? |
Clinical trials | Find open clinical trials recruiting patients with glioblastoma. |
Taxonomy | What species are in the family Felidae and how are they classified? |
Structural biology | Retrieve the AlphaFold-predicted structure confidence (pLDDT) for human serum albumin. |
Pharmacovigilance | What are the known side effects of ibuprofen in FDA adverse event reports? |
Pathways | Look up the glycolysis pathway and list the enzymes involved. |
Category | Query |
Pharmacogenomics | My patient had an unexpected bleeding event on standard-dose warfarin — are there CYP2C9 or VKORC1 variants that could explain abnormal metabolism, and do clinical dosing guidelines exist for those genotypes? |
Drug metabolism | CYP3A4 metabolizes over half of all prescribed drugs — which of its protein interaction partners in liver tissue are also drug-metabolizing enzymes, and do any share substrates that could cause undocumented interactions? |
Post-GWAS | A GWAS hit near FOXP3 is associated with autoimmune disease but the mechanism is unknown — what regulatory elements overlap this locus in ENCODE, what pathways is FOXP3 in, and are there phenotypically similar rare diseases caused by FOXP3 mutations? |
Drug repurposing | Imatinib was designed for BCR-ABL, but what other kinase targets does it hit, are any of those targets implicated in non-cancer diseases, and are there trials testing imatinib for those conditions? |
Evolutionary biology | The FOXP2 "language gene" is highly conserved — how does its protein domain architecture compare across human, mouse, zebrafish, and songbird, and are any domains under positive selection in the human lineage? |
Marine ecology | Lionfish (Pterois volitans) are invasive in the Caribbean — where are they being observed now vs. their native Indo-Pacific range, what native species occupy the same phylogenetic niche, and has anyone studied how their gut microbiome shifts in the invaded habitat? |
Metabolic disease | Branched-chain amino acids are elevated in pre-diabetic patients — which enzymatic pathways degrade them, are the genes for those enzymes differentially expressed in diabetic vs. healthy pancreatic islets, and do any of those enzymes have known drug modulators? |
Undiagnosed disease | A child presents with seizures, intellectual disability, and microcephaly — what genes are associated with all three HPO phenotypes simultaneously, which of those genes have pathogenic variants in ClinVar, and are any located in the patient's candidate region on chromosome 7q? |
Category | Query |
Adverse drug reaction | A patient on both acetaminophen and isoniazid develops liver failure — could isoniazid's CYP2E1 induction increase NAPQI formation beyond the glutathione detox capacity? Find the enzymes, check if the patient's population has high-frequency CYP2E1 variants that compound the risk, map the oxidative stress cascade, and see if this specific drug combination has a disproportionate signal in FDA adverse event data. |
Resistance mechanism | A melanoma patient initially responded to vemurafenib (BRAF V600E inhibitor) but progressed after 8 months — what bypass resistance mechanisms are reported in the literature, do any involve kinases with existing approved inhibitors, what does the structural basis of drug-resistant BRAF look like, and are there combination trials enrolling patients with acquired resistance? |
Gut-brain axis | The gene SLC6A4 (serotonin transporter) appears in both depression GWAS and gut microbiome association studies — is there a mechanistic link? Find its expression across gut and brain tissues, identify which gut bacterial metabolites interact with serotonin pathways, check if SLC6A4 polymorphisms alter transporter kinetics, and search for clinical evidence connecting microbiome composition to SSRI treatment response. |
Neoantigen prioritization | A tumor exome reveals a novel frameshift in TP53 — predict the neoantigen peptides, determine which patient HLA alleles could present them, check whether those HLA alleles are common or rare in the patient's population, verify the mutant region has high structural confidence and isn't in a disordered domain, confirm the gene is expressed in the tumor tissue type, and rule out homology to self-proteins that would cause tolerance. |
Cryptic species discovery | DNA barcodes from a deep-sea vent survey match no known species — find the closest sequences in GenBank, place the organism on the tree of life, check if the vent location has been previously surveyed in OBIS or GBIF, identify whether related organisms have characterized genomes or metagenomes, and search preprints for any recent reports from the same vent system. |
Polypharmacy risk | An elderly patient takes metformin, atorvastatin, amlodipine, and omeprazole — map every CYP enzyme involved in metabolizing these four drugs, find shared enzymes where competitive inhibition could alter plasma levels, check if any of the patient's known pharmacogenomic variants affect those specific enzymes, look up FDA adverse event co-occurrence signals for each pairwise drug combination, and identify which interactions lack clinical guideline coverage. |
MIT — see LICENSE.
Execute a tool on a life science source
| Name | Required | Description | Default |
|---|---|---|---|
| tool | Yes | ||
| params | No | ||
| source | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavior disclosure. It only says 'execute a tool' and omits side effects, auth requirements, error behavior, whether execution is remote, and what a successful call returns. This is effectively a placeholder for behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single front-loaded sentence with no filler. It is concise, but the brevity comes at the cost of substance; there is room to add a second sentence clarifying source/tool meanings without hurting clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 3-parameter tool with no annotations and no output schema, a one-sentence description is far from complete. It leaves unclear how to populate params, where to get valid source/tool values, what the response looks like, and how this tool fits the workflow.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must compensate for the bare string/object types. It adds only the weak hint that 'source' is a life science source and 'tool' is the thing being executed; the required params object and accepted values/formats are completely unspecified.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a concrete action (execute) and a resource (a tool on a life science source), and the contrast with siblings searchTools/getToolInfo suggests this is the invocation sibling. However, it doesn't explain what constitutes a tool, so the purpose is clear but not fully elaborated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to choose callTool over searchTools or getToolInfo, nor any prerequisite such as discovering valid source/tool names. The context signals list siblings, but the description itself provides no routing or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get full parameter schema for a specific tool on a source
| Name | Required | Description | Default |
|---|---|---|---|
| tool | Yes | ||
| source | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the get-like behavior and does not mention whether the operation is strictly read-only, how missing or invalid source/tool values behave, or what the returned schema looks like.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with no filler. Every word contributes to understanding the tool's scope, and the structure wastes no space.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and 0% parameter documentation, the description is too thin. An agent is left to guess what a 'source' is, how to find valid source/tool identifiers, and how this tool fits into the search-then-call workflow suggested by the sibling names.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, but the phrase 'for a specific tool on a source' gives meaning to the two string parameters tool and source. It adds some value beyond the raw schema, yet it does not explain acceptable formats, where valid source identifiers come from, or how tool names should be specified.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('get') and resource ('full parameter schema for a specific tool on a source'), which clearly conveys what the tool does. It is distinguishable from siblings searchTools and callTool, though it does not explicitly name them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or when-not-to-use guidance is provided. The intended usage can be inferred from the sibling names: use this to inspect a tool's schema before calling it, but that is implied rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search across all life science sources by intent, keyword, or tag
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | ||
| query | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It only states that the tool searches, but does not reveal what the search returns, whether it is read-only, any rate limits, authentication needs, or scope limitations. This is a significant transparency gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that conveys the essential purpose with no filler. Every word contributes to understanding the tool's function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, no annotations, and 0% schema description coverage, the description is under-specified. It fails to explain return values, parameter details, edge cases, or usage context, leaving an agent with insufficient information to invoke the tool correctly in a complex scenario.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It mentions 'intent, keyword, or tag,' which loosely maps to query and tags, but does not explicitly explain how the two parameters interact, whether they can be combined, or what format values should take. The mapping is too vague to reliably guide parameter usage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Search'), the resource ('all life science sources'), and the search modes ('by intent, keyword, or tag'). It distinguishes the tool from sibling tools like getToolInfo and callTool by framing it as a cross-source search operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for searching across life science sources, but it does not explicitly state when to use it versus alternatives or provide any exclusions. Sibling tools are generic, so the intended context is somewhat inferable but not directly stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0callToolgetToolInfosearchToolsEach tool serves a distinct purpose: searching for tools, retrieving schema details, and executing tools. There is no overlap between these operations.
All tool names follow a consistent verb-noun camelCase pattern: searchTools, getToolInfo, callTool. The naming is uniform and predictable.
With only 3 tools, the server is minimal yet appropriately scoped for its role as a meta-server. It provides the essential discover, inspect, and execute operations without unnecessary bloat.
The server covers the full lifecycle for interacting with external life science tools: discover via search, understand via getToolInfo, and run via callTool. No obvious gaps in this proxy-like design.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Connect AI clients to biomedical data and tools.
Link compounds to protein targets, rank bioactivity, and look up drug mechanisms and indications.
Semantic search across 5 US government healthcare databases.
Knowledge graph ingestion, entity search, ontology analysis, and CoPass scoring.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/achillesrasquinha/life-science-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
