sciverse-mcp-server 0.7.2 → 0.8.1

package/README.md

@@ -88,7 +88,7 @@ default (`https://api.sciverse.space`).
 
 | Tool | Purpose |
 |---|---|
-| `search_papers` | Structured metadata search (authors / year / journal / subjects) |
+| `search_papers` | Structured metadata search over papers / authors / sources (set `collection`) |
 | `semantic_search` | Natural-language semantic chunk retrieval (RAG) |
 | `read_content` | Byte-range read of original paper text |
 | `list_catalog` | Field introspection (returns all field names + enum sample values, agents should call this first to learn the schema) |

package/dist/generated/tools.d.ts

@@ -1,4 +1,4 @@
-export declare const TOOLS_VERSION = "0.7.2";
+export declare const TOOLS_VERSION = "0.8.1";
 export interface ToolDef {
     name: string;
     description: string;

package/dist/generated/tools.js

@@ -1,6 +1,6 @@
 // Auto-generated by scripts/gen-tools.mjs. Do not edit.
 // Source of truth: openapi.yaml
-export const TOOLS_VERSION = "0.7.2";
+export const TOOLS_VERSION = "0.8.1";
 export const TOOLS = [
     {
         "name": "search_papers",
@@ -8,6 +8,17 @@ export const TOOLS = [
         "inputSchema": {
             "type": "object",
             "properties": {
+                "collection": {
+                    "type": "string",
+                    "enum": [
+                        "papers",
+                        "authors",
+                        "sources"
+                    ],
+                    "default": "papers",
+                    "description": "检索的实体集合。papers（默认，论文）/ authors（作者）/ sources（来源期刊）。 各 collection 字段集不同，用 list_catalog（collection=<name>）学习对应 schema。 注意：本工具的便捷字段（authors/journals/year_from/subjects 等）只对 papers 有意义； 查 authors/sources 时改用 filters_advanced + 该 collection 的字段名（如 authors 的 summary_stats.h_index / orcid，sources 的 issn / is_oa）。authors 用 orcid、 sources 用 issn 与论文检索结果关联。",
+                    "x-en-description": "Entity collection to search. papers (default) / authors / sources. Each collection has its own field schema — call list_catalog(collection=<name>). The convenience fields (authors/journals/year_from/subjects) apply to papers only; for authors/sources use filters_advanced with that collection's field names."
+                },
                 "query": {
                     "type": "string",
                     "description": "BM25 全文关键词，匹配标题/摘要/期刊名/关键词字段。留空则纯靠结构化过滤。"
@@ -64,6 +75,7 @@ export const TOOLS = [
                             },
                             "operator": {
                                 "type": "string",
+                                "description": "过滤操作符。MATCH（分词模糊）适用于 author、keywords（输入 \"Hinton\" 命中 \"Geoffrey Hinton\"）； MATCH_PHRASE（短语模糊）适用于 publication_venue_name_unified，整词连续匹配（\"Nature\" 命中 \"Nature Communications\"；非前缀匹配，\"Nature Comm\" 不会命中）； doi 用 EQ，服务端归一化（去 doi.org 前缀+转小写）后精确匹配。MATCH/MATCH_PHRASE 仅对配了 text 子字段的字段有效。",
                                 "enum": [
                                     "FILTER_OP_EQ",
                                     "FILTER_OP_NE",
@@ -73,7 +85,9 @@ export const TOOLS = [
                                     "FILTER_OP_LTE",
                                     "FILTER_OP_IN",
                                     "FILTER_OP_NIN",
-                                    "FILTER_OP_CONTAINS"
+                                    "FILTER_OP_CONTAINS",
+                                    "FILTER_OP_MATCH",
+                                    "FILTER_OP_MATCH_PHRASE"
                                 ],
                                 "default": "FILTER_OP_EQ"
                             },
@@ -81,6 +95,30 @@ export const TOOLS = [
                         }
                     }
                 },
+                "sort_advanced": {
+                    "type": "array",
+                    "description": "高级排序逃生舱（按任意可排序字段）。papers 用 sort_by_year 即可； authors/sources 想按 h-index / 被引 / works_count 排序时用本字段。 与 query 互斥（query 走相关性排序）。",
+                    "items": {
+                        "type": "object",
+                        "required": [
+                            "field",
+                            "order"
+                        ],
+                        "properties": {
+                            "field": {
+                                "type": "string"
+                            },
+                            "order": {
+                                "type": "string",
+                                "enum": [
+                                    "SORT_ORDER_DESC",
+                                    "SORT_ORDER_ASC"
+                                ],
+                                "default": "SORT_ORDER_DESC"
+                            }
+                        }
+                    }
+                },
                 "sort_by_year": {
                     "type": "string",
                     "enum": [
@@ -164,15 +202,67 @@ export const TOOLS = [
         "inputSchema": {
             "type": "object",
             "properties": {
+                "collection": {
+                    "type": "string",
+                    "enum": [
+                        "papers",
+                        "authors",
+                        "sources"
+                    ],
+                    "default": "papers",
+                    "description": "字段 catalog 所属实体集合。papers（默认）/ authors / sources，各 collection 字段不同。"
+                },
                 "include_sample_values": {
                     "type": "boolean",
                     "default": false,
                     "description": "是否拉取 enum-like 字段的取值样本。false 仅返回静态 schema（毫秒级）；true 触发 OpenSearch terms agg（首次几百毫秒，之后 24h 走缓存）。"
+                },
+                "include_field_stats": {
+                    "type": "boolean",
+                    "default": false,
+                    "description": "是否返回字段统计（keyword 字段基数 + 数值字段 min/max/avg/p50/p95）。触发 OpenSearch 聚合，缓存 24h。"
                 }
             },
             "required": []
         }
     },
+    {
+        "name": "list_paper_relations",
+        "description": "Paginate the full relation list of a paper. citations/references/related_works\nare unbounded arrays (a highly-cited paper can have thousands); search_papers\nonly inlines a truncated few, so use this endpoint for the full list.\nUse when: \"What does paper X cite?\" (relation=REFERENCES), \"Which papers cite\npaper X?\" (relation=CITATIONS), \"Works related to paper X\" (relation=RELATED_WORKS).\nNote: CITATIONS (incoming: who cites me) and REFERENCES (outgoing: who I cite)\nare opposite directions.\nTypical chain: get unique_id from search_papers / semantic_search, then paginate\nhere by relation.",
+        "inputSchema": {
+            "type": "object",
+            "required": [
+                "unique_id",
+                "relation"
+            ],
+            "properties": {
+                "unique_id": {
+                    "type": "string",
+                    "description": "目标论文 unique_id（如 paper:10.1038/xxx），来自 search_papers / semantic_search；勿传 doc_id。"
+                },
+                "relation": {
+                    "type": "string",
+                    "enum": [
+                        "CITATIONS",
+                        "REFERENCES",
+                        "RELATED_WORKS"
+                    ],
+                    "description": "关系类型。CITATIONS=被引（谁引用了我）；REFERENCES=参考文献（我引用了谁）；RELATED_WORKS=相关工作。"
+                },
+                "page": {
+                    "type": "integer",
+                    "default": 1,
+                    "minimum": 1
+                },
+                "page_size": {
+                    "type": "integer",
+                    "default": 25,
+                    "minimum": 1,
+                    "maximum": 200
+                }
+            }
+        }
+    },
     {
         "name": "read_content",
         "description": "Read a UTF-8 byte range of a paper's original text. Typically used with\na doc_id/offset returned by semantic_search to expand context (read\nmore bytes before or after a chunk).\nReturns: text fragment, bytes_returned, next_offset, more (boolean).",
@@ -230,6 +320,10 @@ export const ENDPOINTS = {
         "method": "GET",
         "path": "/meta-catalog"
     },
+    "list_paper_relations": {
+        "method": "POST",
+        "path": "/meta-paper-relations"
+    },
     "read_content": {
         "method": "GET",
         "path": "/content"

package/dist/tools.js

@@ -5,7 +5,7 @@
 // 后续如有第 4 处复制，再用 codegen 收敛。
 import { ENDPOINTS } from "./generated/tools.js";
 import { randomUUID } from "node:crypto";
-const PASSTHROUGH = ["query", "page", "page_size", "fields"];
+const PASSTHROUGH = ["query", "page", "page_size", "fields", "collection"];
 function toBackendPayload(args) {
     const out = {};
     const filters = [];
@@ -46,6 +46,12 @@ function toBackendPayload(args) {
             order: sortByYear === "desc" ? "SORT_ORDER_DESC" : "SORT_ORDER_ASC",
         });
     }
+    if (Array.isArray(args.sort_advanced)) {
+        for (const item of args.sort_advanced) {
+            if (item && item.field)
+                sort.push({ field: item.field, order: item.order ?? "SORT_ORDER_DESC" });
+        }
+    }
     if (filters.length > 0)
         out.filters = filters;
     if (sort.length > 0)
@@ -149,10 +155,15 @@ export async function executeTool(config, name, args) {
         case "semantic_search":
             return call(config, "POST", endpoint.path, { body: args });
         case "list_catalog": {
-            const { include_sample_values } = args;
-            return call(config, "GET", endpoint.path, {
-                query: { include_sample_values: String(Boolean(include_sample_values)) },
-            });
+            const { include_sample_values, include_field_stats, collection } = args;
+            const query = {
+                include_sample_values: String(Boolean(include_sample_values)),
+            };
+            if (include_field_stats)
+                query.include_field_stats = "true";
+            if (collection)
+                query.collection = collection;
+            return call(config, "GET", endpoint.path, { query });
         }
         case "read_content": {
             const { doc_id, offset, limit } = args;
@@ -174,6 +185,16 @@ export async function executeTool(config, name, args) {
             }
             return callBinary(config, endpoint.path, { file_name });
         }
+        case "list_paper_relations": {
+            const { unique_id, relation } = args;
+            if (!unique_id || !relation) {
+                return {
+                    isError: true,
+                    content: [{ type: "text", text: JSON.stringify({ error: "unique_id and relation are required" }) }],
+                };
+            }
+            return call(config, "POST", endpoint.path, { body: args });
+        }
         default:
             return {
                 isError: true,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sciverse-mcp-server",
-  "version": "0.7.2",
+  "version": "0.8.1",
   "description": "Sciverse MCP server — exposes academic paper retrieval (search_papers / semantic_search / read_content) to MCP-compatible coding agents (Claude Code, Cursor, Codex CLI, Windsurf, ...).",
   "license": "Apache-2.0",
   "homepage": "https://github.com/opendatalab/Sciverse-Agent-Tools/tree/main/packages/mcp",