STRING Database MCP Server

Performs **network clustering** on a STRING interaction network and returns both a **network image URL** and details about each detected cluster. Use the same parameters as in the network creation step to ensure consistency. If the network already contains disconnected subgraphs, the resulting number of clusters may differ from the requested value. Dashed lines represent connections between clusters, while solid lines indicate interactions within clusters. Notes: - For small queries (≤5 proteins), the `required_score` parameter is automatically lowered to 0. - If only a single cluster is produced, try increasing `required_score`, adjusting the inflation parameter, or switching to `kmeans` for small, highly interconnected networks.

Retrieves direct links to STRING evidence pages for protein–protein interaction pairs. Use this tool only when a STRING evidence page/link is needed. To determine whether an interaction is supported, use `string_interactions_query_set`. It returns URLs linking to STRING’s evidence pages, which display the underlying data sources (experimental results, publications, and curated databases) supporting each predicted interaction. A URL can be generated even for unsupported pairs; the URL is not itself an interaction verdict. Parameters: - **identifier_a**: Query protein identifier (Protein A) - **identifiers_b**: One or more target protein identifiers (Protein B), separated by `%0d` - **species**: NCBI taxonomy ID (e.g. `9606` for human or `10090` for mouse) Typical user questions that should trigger this tool: - "Can you show me the STRING evidence for this interaction?" - "Show me the details supporting this interaction." - "What supports the interaction between TP53 and MDM2?" - "Where can I find the STRING evidence for this pair?"

Provides explanatory text for STRING features and limitations. Use this tool when the user question involves: - What is STRING is or how to use the tool (how_to_use_string, cytoscape) - functionality not available via MCP tools (e.g. GSEA, regulatory networks, large datasets). - meaning of the lines in the network (line_colors)

Retrieves a stable URL to an interactive STRING network for one or more proteins. - For a single protein: includes the protein and its top 10 most likely interactors. - For multiple proteins: includes all known interactions **within the query set**. - If the user asks for "physical interactions", "complexes", or "binding", set `network_type` to "physical". The input may include one numeric value per protein, such as fold change, effect size, or score. These values are visualized as colored halos around the nodes, allowing overlay of protein-level measurements on the network. Example: PTEN 2.1 SMO -1.3 If numeric values are provided: - positive values are shown in blue - negative values are shown in red - larger absolute values produce stronger halo intensity If the user provides numeric values together with the proteins, preserve them in the query. If few or no interactions are shown, consider lowering `required_score`. For large queries (>100 proteins): - use `network_flavor="confidence"` - increase `required_score` (e.g. 700) Always display the link as a markdown hyperlink (hide the raw URL). Input parameters should match those used in related STRING tools unless otherwise specified.

Search for species or clades available in STRING by free-text query and return their NCBI taxonomy IDs. - Use this when the user asks which species or clades are present in STRING, or when you need the correct NCBI taxon ID to pass to other tools. - use this to resolve NCBI taxons IDs to their scientific names. - Accepts up to 100 taxon IDs separated by `%0d`. - The results are limited to the top 50 matches per query. - When the user asks for a species list, do not list clades. - If the requested species cannot be matched (i.e. the correct species is not present in the results), **immediately invoke the 'string_help' tool with topic='missing_species'**.

This tool retrieves functional enrichment for a set of proteins using STRING. - If queried with a single protein, the tool expands the query to include the protein’s 10 most likely interactors; enrichment is performed on this set, not the original single protein. - For two or more proteins, enrichment is performed on the exact input set. - When calling related tools, use the same input parameters unless otherwise specified. - Focus summaries on the top categories and most relevant terms for the results. Always report FDR for each claim. - Report FDR as a human-readable value (e.g. 2.3e-5 or 0.023). - IMPORTANT: Remember to suggest showing an enrichment graph for a specific category of user interest (e.g., GO, KEGG) - Very large responses are capped while preserving category diversity. - Use `expand_category` to return only one category with expanded term coverage and per-term gene details. - If a row has `preferredNames_omitted: true`, do not infer which proteins are in that term from the returned rows. Use `string_functional_annotation` with the same proteins/species and `detail_for_term` set to the exact term ID. Output fields (per enriched term): - category: Term category (e.g., GO Process, KEGG pathway) - term: Enriched term (GO ID, domain, or pathway) - number_of_genes: Number of input genes with this term - number_of_genes_in_background: Number of background genes with this term - ncbiTaxonId: NCBI taxon ID - preferredNames: Canonical protein names, only when the full per-term list is short enough to show - proteinCount: Number of proteins matching this term - preferredNames_omitted: True when the gene list was omitted instead of showing a misleading partial list - p_value: Raw p-value - fdr: False Discovery Rate (B-H corrected p-value) - description: Description of the enriched term Response metadata: - input_gene_name_mapping: Only included when displayed gene lists contain submitted identifiers that differ from STRING preferred names. - category_summary: Total and returned term counts per category; use `expand_category` for categories where `truncated` is true or where the user wants deeper category-specific detail. - truncated_categories / omitted_categories: Categories with terms not shown in the current response.

This tool tests if your network is enriched in protein-protein interactions compared to the background proteome-wide distribution (i.e., if your proteins are more functionally connected than expected by chance). - The enrichment is assessed using the actual observed edges versus expected edges in a random network of the same size. - The p-value reflects the likelihood that your observed number of interactions would occur by chance. - Report the p-value as a human-readable value (e.g. 2.3e-5 or 0.023). When calling related tools use the same input parameters unless otherwise specified. Output fields: - number_of_nodes: Number of proteins in your network - number_of_edges: Number of observed edges/interactions - average_node_degree: Mean degree (average number of interactions per node) - local_clustering_coefficient: Average clustering coefficient in the network - expected_number_of_edges: Expected number of edges in a random network of the same size - p_value: p-value for network enrichment (smaller = more enriched) Example identifiers: "SMO%0dTP53"

Creates a downloadable file for STRING-derived results. Use this tool when the user explicitly asks to download, save, export, or receive a file containing STRING data, tables, protein lists, enrichment results, networks, etc. When a response would otherwise include a publication-style or supplementary result table, or another table clearly intended for reuse outside chat, mention that a downloadable TSV/CSV file can be generated on request. Ask whether they want the file, unless they already requested it. Do not create the file until the user asks for it. Do not store unrelated data or full conversation transcripts.

Retrieves a URL to a **STRING interaction network image** for one or more proteins. - For a single protein: includes the protein and its top 10 most likely interactors. - For multiple proteins: includes all known interactions **within the query set**. - If the user asks for "physical interactions", "complexes", or "binding", set `network_type` to "physical". The input may include one numeric value per protein, such as fold change, effect size, or score. These values are visualized as colored halos around the nodes, allowing overlay of protein-level measurements on the network. Example: PTEN 2.1 SMO -1.3 If numeric values are provided: - positive values are shown in blue - negative values are shown in red - larger absolute values produce stronger halo intensity If the user provides numeric values together with the proteins, preserve them in the query. If few or no interactions are shown, consider lowering `required_score`. For large queries (>100 proteins): - use `network_flavor="confidence"` - increase `required_score` (e.g. 700) Always ask if the user also wants a link to the interactive STRING network page. Input parameters should match those used in related STRING tools (e.g. `string_interactions_query_set`), unless otherwise specified.

Retrieves pairwise protein similarity scores (Smith–Waterman bit scores) for the query proteins. - If no target species (`species_b`) is provided, results are intra-species (within the query species). - To retrieve homologs in other species or clades (e.g. vertebrates, yeast, plants), specify one or more NCBI taxon IDs in `species_b`. - Multiple target species are supported; ask the user to clarify if needed. - Always report species names together with their taxon IDs. - Bit scores < 50 are not reported. - Results are truncated to the top 50 proteins per input protein.

This tool retrieves curated functional annotations for a set of proteins. Each input protein is mapped to known biological terms from ontologies, pathway databases, tissues, compartments and domains — such as Gene Ontology (GO), KEGG, and UniProt Keywords. - Use this when the user asks what a protein does, where it's localized, expressed, or which pathways it participates in. - Keep the output short and focused by highlighting a few diverse and specific annotations for each protein. - This tool does not perform statistical enrichment — use the enrichment tool for that. Output fields (per protein): - stringId: STRING protein identifier - preferredName: Gene name or alias - annotation: Functional description or keyword - category: Source category (e.g. GO, KEGG, Keyword) - term: Functional term or ID

Maps one or more protein identifiers to their corresponding STRING metadata, including: gene symbol, description, sequence, domains, species, and internal STRING ID. This method is useful for translating raw identifiers into readable, annotated protein entries. Example input: "TP53%0dSMO"

Retrieves the STRING enrichment figure image *URL* for a set of proteins.

Retrieves all interaction partners for one or more proteins from STRING. This tool returns all known interactions between your query protein(s) and **any other proteins in the STRING database**. - Use this when asking **“What does TP53 interact with?”** - It differs from the `network` tool, which only shows interactions **within the input set** or a limited extension of it. - If the user refers to "physical interactions", "complexes", or "binding", set the network type to "physical". You can filter for strong interactions using `required_score`. - Evidence scores: `nscore` (neighborhood), `fscore` (fusion), `pscore` (phylogenetic profile), `ascore` (coexpression), `escore` (experimental), `dscore` (database), `tscore` (text mining)

Searches the STRING database using **amino acid sequences** to identify matching proteins. - Accepts a single sequence or multiple sequences in FASTA format. - Returns the most similar STRING protein(s) for the specified species, based on sequence similarity. - Use this when the protein identifier is unknown or unresolvable by `string_resolve_proteins`.

Retrieve proteins annotated with a functional term or descriptive text in a single species. You can query for tissues, compartments, diseases, processes, pathways, and domains. IMPORTANT: For cross-species comparisons, run this tool separately for each species. Select relevant model organisms to search or ask user to provide the selection. The results reflect annotation depth within each category; use caution when interpreting. If no results are found, try simplifying the query. For tissue queries, follow BRENDA tissue nomenclature and omit the word "tissue" (e.g. use "skin" instead of "skin tissue"). Output fields: - category: Source database of the matched functional term (e.g. GO, KEGG, Reactome, Pfam, InterPro). - term: Exact identifier for the functional term. - description: The free text description of the term. - proteinCount: Number of proteins annotated with that term - preferredNames: Full protein-name list when `detail_for_term` is set - stringIds: STRING protein identifiers when returned - preferredNames_omitted: True when a row omits the protein-name list - stringIds_omitted: True when STRING identifiers are omitted

Retrieves the interactions between the query proteins. Use this method only when you specifically need to list the interactions between all proteins in your query set. If user asks for 'physical' or 'complex' use 'physical' network type. - For a **single protein**, the network includes that protein and its top 10 most likely interaction partners, plus all interactions among those partners. - For **multiple proteins**, the network includes all direct interactions between them. - If the user refers to "physical interactions", "complexes", or "binding", set the network type to "physical". - STRING does not store or report information about self-interactions/homomers; if asked, explain the limitation. If few or no interactions are returned, consider reducing the `required_score`. For large query sets (>50 proteins), consider increasing the `required_score` (e.g. ≥700) to focus on high-confidence interactions and avoid overly dense networks. - Expand the names of score sources: `nscore` (neighborhood), `fscore` (fusion), `pscore` (phylogenetic profile), `ascore` (coexpression), `escore` (experimental), `dscore` (database), `tscore` (text-mining)