string_network_clustering
ActiveTool of 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.
Parameters schema
{
"type": "object",
"required": [
"proteins"
],
"properties": {
"species": {
"anyOf": [
{
"type": "string",
"description": "Required. NCBI/STRING taxonomy ID (e.g. 9606 for human, or STRG0AXXXXX for uploaded genomes)."
},
{
"type": "null"
}
],
"default": null
},
"proteins": {
"type": "string",
"description": "Required. One or more protein identifiers (optionally with values). Example:\nPTEN 0.234\nSMO -3.445\nSeparate entries with newline (%0d). Numeric values (e.g. expression data) can be provided after identifiers."
},
"network_type": {
"anyOf": [
{
"anyOf": [
{
"enum": [
"functional",
"physical"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "Optional. Omit for STRING default functional associations. Set physical only for binding, complex, or co-complex questions."
},
{
"type": "null"
}
],
"default": null
},
"extend_network": {
"anyOf": [
{
"anyOf": [
{
"type": "integer",
"minimum": 0
},
{
"type": "null"
}
],
"description": "Optional. Add specified number of additional nodes to the network based on their interaction scores. Default: 0, or 10 for single-protein queries."
},
{
"type": "null"
}
],
"default": null
},
"network_flavor": {
"anyOf": [
{
"anyOf": [
{
"enum": [
"evidence",
"confidence"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "Optional. Edge display style. Omit for STRING default evidence styling. Set only when the user asks for evidence or confidence edge display."
},
{
"type": "null"
}
],
"default": null
},
"required_score": {
"anyOf": [
{
"anyOf": [
{
"type": "integer",
"maximum": 1000,
"minimum": 0
},
{
"type": "null"
}
],
"description": "Optional. Minimum interaction confidence score. Omit for STRING default filtering. Set only when a threshold is requested or a broader/narrower threshold is needed."
},
{
"type": "null"
}
],
"default": null
},
"center_node_labels": {
"anyOf": [
{
"anyOf": [
{
"enum": [
0,
1
],
"type": "integer"
},
{
"type": "null"
}
],
"description": "Optional. Center protein labels on nodes when set to 1. Set only if the user asks to center labels."
},
{
"type": "null"
}
],
"default": null
},
"clustering_algorithm": {
"anyOf": [
{
"anyOf": [
{
"enum": [
"MCL",
"kmeans"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "Optional. MCL identifies densely connected subnetworks based on connectivity flow. kmeans partitions proteins into a fixed number of clusters. If omitted, the server uses MCL."
},
{
"type": "null"
}
],
"default": null
},
"clustering_parameter": {
"anyOf": [
{
"anyOf": [
{
"type": "number",
"minimum": 1
},
{
"type": "null"
}
],
"description": "Optional. Controls clustering granularity. For MCL: inflation parameter 1.0-10.0, default 3.0; higher values produce more, smaller clusters. For kmeans: number of clusters, integer >=2, default 3."
},
{
"type": "null"
}
],
"default": null
},
"hide_disconnected_nodes": {
"anyOf": [
{
"anyOf": [
{
"enum": [
0,
1
],
"type": "integer"
},
{
"type": "null"
}
],
"description": "Optional. Hide unconnected nodes when set to 1. Set only if the user asks to hide disconnected or unconnected proteins."
},
{
"type": "null"
}
],
"default": null
}
}
}No endpoints wrapped at confidence ≥ 0.70.
Parent server
STRING Database MCP Server
https://github.com/meringlab/string-mcp
2/7 registries