ProPaths 검증 단백질 상호작용체를 AI 에이전트용 읽기 전용 도구로 노출하는 MCP 서버입니다. 공개 ProPaths API(https://www.propaths.net) 위의 얇은 클라이언트이므로 모든 도구는 API의 JSON을 그대로 반환합니다. 계정도, API 키도 필요 없습니다.
ProPaths는 단백질의 1차 문헌을 읽고 유형화되고 방향성이 있으며 기계적 상호작용의 검증된 그래프와 경로 온톨로지를 반환합니다. 현재 한 단백질(ATXN3)이 완전히 매핑되어 있습니다.
MCP 클라이언트 설정에 다음을 추가하세요. uvx가 서버를 가져와 실행합니다. 클론하거나 설치할 것이 없습니다.
{
"mcpServers": {
"propaths": {
"command": "uvx",
"args": ["propaths-mcp"]
}
}
}그런 다음, 예를 들어 *"ProPaths에서 SCA3를 검색하고 가장 강력한 기계적 상호작용을 요약해 줘"*라고 물어보세요. 에이전트는 search_proteins를 호출한 다음 get_protein을 호출하고 get_interaction으로 세부 사항을 파고듭니다.
원시 API를 선호하시나요? 공개되어 있고 키가 필요 없습니다:
curl https://www.propaths.net/api/protein/ATXN3
curl 'https://www.propaths.net/api/search?q=SCA3'Related MCP server: dotdog
도구 | 기능 |
| 기호, 별칭 또는 이름으로 단백질 찾기 (여기서 시작) |
| 간결한 상호작용체 개요 (주요 진입점) |
| 단일 상호작용의 전체 메커니즘 + 증거 |
| 두 단백질 사이의 상호작용(들)을 한 번에 |
| 필터링/정렬된 헤드라인 행 |
| 제어 어휘 (엣지 종류, 유형, 방향) + 개수 |
| 계통 및 구성원 상호작용이 포함된 경로 노드 |
| 전체 경로 스캐폴드 (경로 ID를 이름으로 해석) |
| 가장 잘 입증된 상호작용 |
| 단백질 네트워크를 TSV / SIF / GraphML로 내보내기 (Cytoscape, networkx) |
| 그래프 어휘 + 도구 사용 방법 (오프라인) |
또한 MCP 리소스(propaths://schema, propaths://interaction-types, propaths://pathways/tree, propaths://protein/{symbol} 템플릿) 및 프롬프트(profile-protein, strongest-evidence, explain-pathway)로 노출됩니다.
모든 도구는 읽기 전용이며 멱등적입니다.
환경 변수 | 기본값 | 용도 |
|
| API 기본 URL. 로컬 API에 대해 실행하려면 |
pip install propaths-mcp
propaths-mcp # runs the stdio server
# or: python -m propaths_mcp게시되기 전에는 저장소에서 직접 실행할 수 있습니다:
uvx --from git+https://github.com/Tahsin-Kazi/propaths-mcp propaths-mcp읽기 전용이며 공개적입니다. 읽기는 클라이언트당 속도 제한이 있습니다. 쓰기/강화 액세스 및 호스팅 MCP는 게이트되어 있습니다. 연락 주세요.
오류는 우아하게 처리됩니다: 존재하지 않는 단백질은 {"error": "...", "status": 404}를 반환하고, API에 연결할 수 없으면 힌트와 함께 예외가 발생합니다.
문서: https://www.propaths.net/quick-start · 라이선스: MIT
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.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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.
| Name | Required | Description | Default |
|---|---|---|---|
| format | No | tsv | |
| symbol | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
A curated entry point: the best-evidenced interactions, ranked by supporting evidence. Good for a quick, strong overview.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | ||
| interaction_id | Yes |
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.
| Name | Required | Description | Default |
|---|---|---|---|
| a | Yes | ||
| b | Yes |
A single pathway by id: the node, its ancestors and children, and the interactions placed in it. The pathway-first way into the graph.
| Name | Required | Description | Default |
|---|---|---|---|
| pathway_id | Yes |
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.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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.
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes |
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).
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | ||
| sort | No | evidence | |
| type | No | ||
| limit | No | ||
| order | No | desc | |
| symbol | Yes | ||
| pathway | No | ||
| min_evidence | No |
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.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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.
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | ||
| limit | No |
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.1describe_schemaexport_networkget_highlightsget_interactionget_interaction_betweenget_pathwayget_pathway_treeget_proteinlist_interaction_typeslist_interactionssearch_proteinsScored 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.
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.
