propaths-mcp
propaths-mcp
一个 MCP 服务器,将 ProPaths 验证的蛋白质相互作用组作为只读工具暴露给 AI 代理。它是公共 ProPaths API (https://www.propaths.net) 的轻量客户端,因此每个工具都精确返回 API 的 JSON。无需账户,无需 API 密钥。
ProPaths 读取蛋白质的原始文献,并返回一个经过验证的类型化、有向、机制性相互作用图,以及一个通路本体。目前已有一种蛋白质 (ATXN3) 被完整映射。
快速开始 (Claude Desktop / 任何 MCP 客户端)
将此添加到您的 MCP 客户端配置中。uvx 会获取并运行服务器;无需克隆或安装。
{
"mcpServers": {
"propaths": {
"command": "uvx",
"args": ["propaths-mcp"]
}
}
}然后询问,例如,"搜索 ProPaths 中的 SCA3 并总结其最强的机制性相互作用。" 代理将调用 search_proteins,然后调用 get_protein,并使用 get_interaction 深入查看。
更喜欢原始 API?它是公开且无需密钥的:
curl https://www.propaths.net/api/protein/ATXN3
curl 'https://www.propaths.net/api/search?q=SCA3'Related MCP server: dotdog
工具
工具 | 功能 |
| 按符号、别名或名称查找蛋白质(从这里开始) |
| 紧凑的相互作用组概览(主要入口点) |
| 单个相互作用的完整机制 + 证据 |
| 一次调用获取两个蛋白质之间的相互作用 |
| 过滤/排序的标题行 |
| 受控词汇表(边种类、类型、方向)+ 计数 |
| 一个通路节点及其谱系和成员相互作用 |
| 完整的通路脚手架(将通路 ID 解析为名称) |
| 证据最充分的相互作用 |
| 将蛋白质的网络导出为 TSV / SIF / GraphML(Cytoscape、networkx) |
| 图词汇表 + 如何使用工具(离线) |
还作为 MCP 资源(propaths://schema、propaths://interaction-types、propaths://pathways/tree 以及 propaths://protein/{symbol} 模板)和 提示(profile-protein、strongest-evidence、explain-pathway)暴露。
所有工具都是只读且幂等的。
配置
环境变量 | 默认值 | 用途 |
|
| API 基础 URL。指向 |
不使用 uvx 运行
pip install propaths-mcp
propaths-mcp # runs the stdio server
# or: python -m propaths_mcp在发布之前,您可以直接从仓库运行:
uvx --from git+https://github.com/Tahsin-Kazi/propaths-mcp propaths-mcp备注
只读且公开;读取按客户端限速。写入/增强访问和托管 MCP 需要授权。请联系我们。
错误处理优雅:缺失的蛋白质返回
{"error": "...", "status": 404};无法访问的 API 会引发带有提示的错误。
文档:https://www.propaths.net/quick-start · 许可证:MIT
Available Tools
11 toolsdescribe_schemaARead-onlyIdempotent
Explain the graph's vocabulary and how to use these tools: edge kinds, interaction types, direction semantics, orientation, and the recommended call flow. Static guidance that works even if the API is unreachable.
Inputs: no named parameters.
export_networkARead-onlyIdempotent
Export a protein's interactome as text for external tools.
format = tsv (edge list / spreadsheet), sif or graphml (Cytoscape, networkx, igraph, Gephi). Edges carry their biological orientation (an upstream partner points into the protein), so the graph is directed.
Inputs: symbol (required), format. Returns: result
get_highlightsARead-onlyIdempotent
A curated entry point: the best-evidenced interactions, ranked by supporting evidence. Good for a quick, strong overview.
Inputs: no named parameters.
get_interactionARead-onlyIdempotent
One interaction's full enriched record by id.
Includes mechanism prose, direction, per-function effects, kinetics, and
evidence. Pass query (a participating symbol) to orient source/target so
the query protein reads as the source.
Inputs: interaction_id (required), query.
get_interaction_betweenARead-onlyIdempotent
The interaction(s) between two named proteins, oriented from a.
Use this for "what does A do to B" in one call, instead of pulling get_protein and scanning for the partner.
Inputs: a (required), b (required).
get_pathwayARead-onlyIdempotent
A single pathway by id: the node, its ancestors and children, and the interactions placed in it. The pathway-first way into the graph.
Inputs: pathway_id (required).
get_pathway_treeARead-onlyIdempotent
The full pathway scaffold as a flat node list.
Assemble the tree client-side via each node's parentId. Use this to resolve the canonicalPathwayId values returned on interactions into human-readable pathway names.
Inputs: no named parameters.
get_proteinARead-onlyIdempotent
Overview map for one protein, the main entry point.
Returns a COMPACT overview sized for an agent: protein metadata, counts, the top-level pathway roots, and one headline row per interaction (id, oriented source/target, kind, direction, type, a one-line supportSummary, resolved pathway names, and function/evidence counts). It deliberately omits the heavy per-edge mechanism and evidence prose (the full protein page is ~700K tokens for a hub protein).
Drill into any row by id for full depth: get_interaction(id) for an edge's mechanism + kinetics + evidence.
Inputs: symbol (required).
list_interactionsARead-onlyIdempotent
Filtered, sorted, headline-only list of a protein's interactions.
kind = activates|inhibits|binds|regulates; type = direct|indirect; pathway = a pathway-name substring; min_evidence = minimum supporting papers; sort = evidence|functions|partner. Lighter than get_protein; use it for targeted questions ("best-evidenced inhibitory edges in ERAD"), then drill in with get_interaction(id).
Inputs: symbol (required), kind, sort, type, +4 more.
list_interaction_typesARead-onlyIdempotent
The controlled vocabulary with plain-language meanings and live counts: edge kinds, interaction types, directions, and the mechanisms present in the graph. Call this before filtering so you use valid values.
Inputs: no named parameters.
search_proteinsARead-onlyIdempotent
Search proteins by symbol prefix (case-insensitive).
Returns matching symbols with HGNC id and description. Use this first to resolve a protein of interest, then call get_protein.
Inputs: q (required), limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Each tool has a clearly distinct purpose: search_proteins for finding proteins, get_protein for overview, get_interaction for deep detail, list_interactions for filtered lists, get_pathway/get_pathway_tree for pathway navigation, export_network for output, and describe_schema for guidance. Even closely related tools like get_interaction_between and get_interaction are differentiated by their argument (pair vs. ID) and described usage.
All tool names follow a consistent get_/list_/search_/export_/describe_ + noun pattern, all in snake_case. The verb clearly indicates the action (get for single resource, list for collection, search for prefix query, export for output, describe for metadata) and the noun identifies the resource (protein, interaction, pathway, network, schema).
11 tools is well within the recommended 3-15 range and each tool addresses a specific need for exploring a biological interaction graph. The count feels neither thin nor bloated—there are distinct entry points, filtering utilities, vocabulary support, and export functionality without redundant overlaps.
The tool surface covers the full read-only lifecycle of the domain: find a protein (search_proteins), get overview (get_protein), drill into details (get_interaction), filter (list_interactions), navigate pathways (get_pathway, get_pathway_tree), discover vocabularies (list_interaction_types), get curated highlights (get_highlights), and export (export_network). The inclusion of describe_schema ensures agents can self-orient, and there are no obvious dead ends—every tool's output either stands alone or provides IDs that are directly consumed by other tools.
Maintenance
Related MCP Connectors
Read-only MCP tools for AI agent discovery, structured resources, and NIULAI information.
Reactome MCP — open biological pathway knowledge-base.
Read-only search of 2,189 AI agent tools (MCP servers, x402 APIs) with daily automated trust scores.
Public read-only MCP access to digital learning concepts, semantic relationships, and citations.
Related MCP Servers
- AlicenseAqualityAmaintenanceAn MCP server that gives AI assistants access to biological and biomedical RDF databases via SPARQL at the RDF Portal, as well as selected REST APIs (NCBI E-utilities, UniProt, ChEMBL, PDB, Reactome, Rhea, MeSH, and more).23321MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to query and traverse spec genomes via MCP tools, providing structured access to entities, relationships, and graph data.8MIT

reactome-mcpofficial
AlicenseBqualityCmaintenanceEnables AI assistants to search, browse, analyze, and export biological pathway data from Reactome through natural language.566Apache 2.0- AlicenseNot gradedqualityCmaintenanceEnables AI agents to query the Reactome biological pathway knowledge-base for pathways, participants, and orthologous events using natural language.98 npmMIT