# UniProt MCP for AI Agents AI Agent Connect > UniProt MCP lets you pull protein data from the world's biggest biological database. It handles searches for gene symbols, protein names, and functional annotations. Use it to grab full amino acid sequences, subcellular locations, and curated biological data for research, drug discovery, and bioinformatics. It connects your agent directly to millions of records for faster analysis. ## Overview - **Category:** the-unthinkable - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_jPSrejZI835eE2T6bJttqT3k3CdFHVP7joPQheuT/ai-agent-connect - **Tags:** protein-sequences, bioinformatics, genomics, functional-annotation, biological-data, research-database ## Description Connect your agent to the gold standard of protein data. Instead of manually digging through nested tables or switching between tabs to find a specific gene's functional role, your agent does the heavy lifting. You can ask it to find every protein encoded by a specific gene across different species or pull the full sequence for a known accession number. It works by pulling from both manually curated and auto-annotated records, meaning you get high-quality data whether it's a well-studied human protein or a newer discovery. When you're building a pipeline for drug discovery or trying to map out protein domains for a new experiment, this Connector acts as a direct line to the biological facts you need. It is one of the many tools you can find in the Vinkius catalog to bridge the gap between raw biological data and useful research. You get the data in a clean format, ready for your next step, without the friction of navigating complex web interfaces. This means you spend less time on data entry and more time on actual analysis. You can quickly cross-reference orthologs, check subcellular locations, and verify amino acid sequences without ever leaving your chat interface. It turns a tedious multi-tab research process into a simple conversation. ## Tools ### search_uniprot_gene Find all protein isoforms and functional annotations for a given gene name. Use this to see how a gene is expressed across different types. ### get_uniprot_protein Get full protein details and sequences using a specific UniProt accession ID. This is useful for pulling exact data for a known protein. ### search_uniprot Search the database for proteins by name, function, or keywords like insulin or p53. This helps you find data when you only have a general term. ## Prompt Examples **Prompt:** ``` Tell me about the p53 tumor suppressor protein and its function. ``` **Response:** ``` **P53_HUMAN** (UniProt P04637) * **Gene:** TP53 * **Organism:** Homo sapiens * **Length:** 393 amino acids * **Review Status:** Swiss-Prot reviewed **Function:** Acts as a tumor suppressor in many tumor types by inducing growth arrest or apoptosis. Activated in response to DNA damage, oncogene activation, and hypoxia. **Location:** Located in the nucleus and cytoplasm. ``` **Prompt:** ``` Find all proteins encoded by the BRCA1 gene. ``` **Response:** ``` I found several entries for the **BRCA1** gene. Here are the top results: | Protein ID | Organism | Amino Acids | Function | | :--- | :--- | :--- | :--- | | **P38398** | Homo sapiens | 1863 | E3 ubiquitin ligase, DNA repair | | **Q61187** | Mus musculus | 1800 | E3 ubiquitin ligase | | **Q61187** | Rattus norvegicus | 1800 | E3 ubiquitin ligase | *Note: Mutations in the human version are associated with increased risk of breast and ovarian cancer.* ``` **Prompt:** ``` Look up UniProt accession Q9BYF1 and show me its full details. ``` **Response:** ``` **Q9BYF1: ACE2_HUMAN** * **Gene:** ACE2 * **Organism:** Homo sapiens * **Length:** 805 amino acids * **Review Status:** Swiss-Prot reviewed **Function:** Metalloprotease that converts angiotensin II to angiotensin-(1-7). It notably serves as the functional receptor for SARS-CoV and SARS-CoV-2 spike proteins. **Location:** Cell membrane. ``` ## Capabilities ### Pull full protein details Get complete data including sequences and locations using a specific accession ID. ### Find gene isoforms Retrieve all protein isoforms and functional annotations for a specific gene. ### Search by keyword Find proteins by name, function, or specific biological terms like p53. ### Compare orthologs Identify and compare proteins across different species and organisms. ### Retrieve amino acid sequences Get full sequence data for use in comparative analyses or experimental design. ## Use Cases ### Finding a specific protein sequence A researcher asks for the human p53 sequence. The agent uses get_uniprot_protein to pull the exact amino acid data and functional summary. ### Mapping gene isoforms across species A bioinformatician asks for all proteins encoded by the BRCA1 gene. The agent uses search_uniprot_gene to list isoforms in humans and mice. ### Identifying therapeutic targets A drug discovery team asks about the ACE2 receptor. The agent uses search_uniprot to find its role as a functional receptor for viruses. ### Comparing orthologs for research A scientist needs to find proteins related to insulin in different organisms. The agent uses search_uniprot to gather a comparative list. ## Benefits - Stop manual searching: Use search_uniprot to find proteins by keyword or function instantly without navigating multiple websites. - Get precise data: Use get_uniprot_protein to pull exact amino acid sequences and subcellular locations for your experiments. - Compare species: Use search_uniprot_gene to find orthologs and paralogs across multiple organisms in one step. - Faster drug discovery: Identify therapeutic targets by pulling disease associations directly into your chat interface. - High-quality results: Access both manually curated Swiss-Prot and auto-annotated TrEMBL records for comprehensive coverage. ## How It Works The bottom line is you get instant access to 250 million protein records without needing to manage API keys. 1. Subscribe to the UniProt MCP on Vinkius. 2. Connect the Connector to your preferred AI client like Claude or Cursor. 3. Ask your agent to find specific proteins or pull sequences directly. ## Frequently Asked Questions **What is the UniProt MCP?** The UniProt MCP is a tool that lets your AI agent access the world's largest database of protein sequences and functional information. It allows your agent to perform searches and pull biological data directly into your workspace. **Can I use UniProt MCP to find protein sequences?** Yes, you can pull full amino acid sequences for specific proteins using their accession numbers. This is great for research, comparative analysis, and experimental design. **How does UniProt MCP help with drug discovery?** It helps you identify therapeutic targets by pulling functional annotations and disease associations for specific proteins. You can quickly see what a protein does and where it is located in the cell. **Does UniProt MCP support different species?** Yes, it supports data for many organisms. You can use it to find orthologs and paralogs to see how proteins differ across different species like humans, mice, and rats. **Is an API key required for UniProt MCP?** No, you do not need to manage any API keys. You can start searching and pulling protein data immediately after subscribing to the Connector on Vinkius. **Can UniProt MCP find specific gene isoforms?** Yes, the Connector can find all protein isoforms encoded by a specific gene. This is helpful for understanding how different versions of a protein function in different contexts. **What is the difference between Swiss-Prot and TrEMBL entries?** Swiss-Prot contains 570K+ entries that have been manually reviewed and curated by expert biologists — the gold standard for protein annotation. TrEMBL contains 250M+ entries that are computationally annotated from gene sequences. Swiss-Prot entries are marked as 'reviewed' and are highly reliable; TrEMBL entries are automatically generated and may contain errors. **Do I need to register or pay for an API key?** No. UniProt REST API is completely free and open without any authentication. There are no rate limits for reasonable usage patterns. UniProt is funded by the National Institutes of Health (NIH), European Molecular Biology Laboratory (EMBL), and the Swiss Institute of Bioinformatics (SIB). **Can I retrieve full amino acid sequences for proteins?** Yes. Every protein entry includes the full amino acid sequence with length information. The sequence is returned in standard one-letter amino acid code. For very large proteins (10,000+ residues), the sequence may be truncated in the response but the full accession data is always provided for direct download.