sciverse-mcp-server 0.15.1 → 1.0.0

package/dist/generated/tools.d.ts

@@ -1,9 +1,14 @@
-export declare const TOOLS_VERSION = "0.15.1";
+export declare const TOOLS_VERSION = "1.0.0";
 export interface ToolDef {
     name: string;
     description: string;
     inputSchema: Record<string, unknown>;
 }
+export declare const LEGACY_TOOLS: ToolDef[];
+export declare const LEGACY_ENDPOINTS: Record<string, {
+    method: "GET" | "POST";
+    path: string;
+}>;
 export declare const TOOLS: ToolDef[];
 export declare const ENDPOINTS: Record<string, {
     method: "GET" | "POST";

package/dist/generated/tools.js

@@ -1,19 +1,29 @@
 // Auto-generated by scripts/gen-tools.mjs. Do not edit.
 // Source of truth: openapi.yaml
-export const TOOLS_VERSION = "0.15.1";
-export const TOOLS = [
+export const TOOLS_VERSION = "1.0.0";
+export const LEGACY_TOOLS = [
     {
         "name": "search_papers",
-        "description": "Search academic papers by structured filters (title, authors, journal,\nyear, subjects, etc.).\nUse when: \"find Hinton's papers from 2020-2023\", \"Nature papers on\nCRISPR\".\nNot for: natural-language Q&A retrieval (use semantic_search) or\nfull-text snippets (use read_content).\nReturns: list of papers; each entry has unique_id (always present),\ndoc_id (only when full text exists), title, author, abstract,\npublication_venue_name_unified, publication_published_year.",
+        "description": "Deprecated compatibility tool. Prefer search_metadata; legacy paper convenience parameters apply only to papers.",
         "inputSchema": {
             "type": "object",
             "properties": {
+                "fields": {
+                    "type": "array",
+                    "maxItems": 128,
+                    "items": {
+                        "type": "string"
+                    },
+                    "description": "返回字段，须为当前collection已授权且可投影字段；省略返回默认字段集与授权交集。",
+                    "x-en-description": "Project authorized, projectable fields from this collection; omit for authorized defaults."
+                },
                 "collection": {
                     "type": "string",
                     "enum": [
                         "papers",
                         "authors",
-                        "sources"
+                        "sources",
+                        "patents"
                     ],
                     "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。",
@@ -175,10 +185,186 @@ export const TOOLS = [
                 }
             }
         }
+    }
+];
+export const LEGACY_ENDPOINTS = {
+    "search_papers": {
+        "method": "POST",
+        "path": "/meta-search"
+    }
+};
+export const TOOLS = [
+    {
+        "name": "search_metadata",
+        "description": "Search metadata in one collection: papers, patents, authors or sources. Use list_catalog to discover authorized fields before choosing filters, sort and fields. Supports keywords, cursor pagination and facets; no implicit field sorting. Returns results, total_count and next_cursor with collection-specific fields. Use read_content for paper/patent text and semantic_search for paper semantic retrieval. Author/source IDs cannot be used to read content.",
+        "inputSchema": {
+            "type": "object",
+            "additionalProperties": false,
+            "properties": {
+                "fields": {
+                    "type": "array",
+                    "maxItems": 128,
+                    "items": {
+                        "type": "string"
+                    },
+                    "description": "返回字段，须为当前collection已授权且可投影字段；省略返回默认字段集与授权交集。",
+                    "x-en-description": "Project authorized, projectable fields from this collection; omit for authorized defaults."
+                },
+                "collection": {
+                    "type": "string",
+                    "enum": [
+                        "papers",
+                        "authors",
+                        "sources",
+                        "patents"
+                    ],
+                    "default": "papers",
+                    "description": "实体集合；用 list_catalog 查看对应字段权限和能力。"
+                },
+                "query": {
+                    "type": "string",
+                    "description": "BM25 关键词，匹配当前实体已授权的可检索字段；专利包含 invention_title、abstract、claims.claim_text。留空则纯靠结构化过滤。\n普通关键词是宽松匹配（任一词命中、按相关性排序）。\n\n也支持布尔检索式：全大写 AND / OR / NOT、括号分组、引号短语；优先级\nNOT > AND > OR，相邻词隐式 AND。例如\n  (histopathology OR pathology) AND (\"deep learning\" OR \"machine learning\") AND (prognosis OR survival)\n布尔式里每个检索词都是硬条件、不做放宽——0 命中就是 0。\n- query 只放检索词：「检索式1（预后预测）」这类标签/说明也会变成必须命中的词。\n- 小写 and/or 是普通词；要检索字面量 OR（如比值比）加引号 \"OR\"。\n- 引号需与运算符同时出现才生效：只写 \"spread through air spaces\" 不带运算符时\n  按普通关键词处理；写成 \"spread through air spaces\" AND lung 才是短语精确匹配。\n- 最多 64 个检索词、括号嵌套 10 层，超限返回 400；复杂检索请拆成多次调用。\n",
+                    "x-en-description": "BM25 keywords over authorized searchable fields in this collection; patents use invention_title, abstract and claims.claim_text. Leave empty for\npure structured filtering. Plain keywords match loosely (any word, ranked by\nrelevance).\n\nBoolean syntax is also supported: UPPERCASE AND / OR / NOT, ( ) grouping and\n\"quoted phrases\"; precedence NOT > AND > OR, adjacent words are implicitly AND.\nExample:\n  (histopathology OR pathology) AND (\"deep learning\" OR \"machine learning\") AND (prognosis OR survival)\nIn boolean mode every term is a hard requirement and nothing is relaxed —\n0 hits means 0.\n- Put only search terms in query: labels or instructions such as\n  \"检索式1（预后预测）\" become required terms too.\n- Lowercase and/or are ordinary words; quote \"OR\" to search the literal\n  (e.g. odds ratio).\n- Quotes only take effect alongside an operator: a query that is just\n  \"spread through air spaces\" is treated as plain keywords, whereas\n  \"spread through air spaces\" AND lung is an exact phrase match.\n- Max 64 terms and 10 nesting levels (400 otherwise); split complex searches\n  into several calls.\n",
+                    "maxLength": 2048
+                },
+                "page": {
+                    "type": "integer",
+                    "default": 1,
+                    "minimum": 1
+                },
+                "page_size": {
+                    "type": "integer",
+                    "default": 25,
+                    "minimum": 1,
+                    "maximum": 50,
+                    "description": "每页条数。省略时为服务端默认 25（SDK / MCP 不注入默认值）；工具层上限 50。"
+                },
+                "freshness_boost": {
+                    "type": "string",
+                    "enum": [
+                        "NONE",
+                        "MILD",
+                        "STRONG"
+                    ],
+                    "default": "NONE",
+                    "description": "模糊搜索新鲜度加权：结果偏向新文献（仅 query 非空时生效；传排序\n（sort_by_year 非 none / sort_advanced）时被忽略，硬排优先）。\nMILD: 近 10 年加权，适合日常查文献；STRONG: 近 3 年加权，适合跟踪\n研究方向 / 追最新进展。与 impact_boost / language_affinity 可叠加\n（均为乘法因子）。boost 生效时为浅翻页：不产 next_cursor、不支持\ncursor 深翻页。\n"
+                },
+                "impact_boost": {
+                    "type": "string",
+                    "enum": [
+                        "NONE",
+                        "MILD",
+                        "STRONG"
+                    ],
+                    "default": "NONE",
+                    "description": "模糊搜索影响力加权：高被引文献在保留相关性的前提下上浮（仅 query\n非空时生效；传排序时被忽略）。MILD: 轻度上浮，相关性仍主导；\nSTRONG: 明显偏向高被引。引用因子有界、零被引中性（不会归零）。\n与 freshness_boost / language_affinity 可叠加；boost 生效时为浅翻页。\n"
+                },
+                "language_affinity": {
+                    "type": "string",
+                    "enum": [
+                        "NONE",
+                        "MILD",
+                        "STRONG"
+                    ],
+                    "default": "NONE",
+                    "description": "模糊搜索语言亲和加权：非 query 语言的结果降序、但不排除（仅 query\n非空时生效；传排序时被忽略）。目标语言由服务端从 query 文本判定\n（假名→ja / 谚文→ko / 汉字→zh / 拉丁→en，其他书写系统不生效）；\n语言未知的文献保持中性不降权。MILD: 非目标语言 ×0.5，跨语言强相关\n结果仍可上浮；STRONG: ×0.2，几乎只看目标语言。与 freshness_boost /\nimpact_boost 可叠加；boost 生效时为浅翻页。要硬排除某语言请改用\nfilters_advanced 的 language 字段（如 {\"field\":\"language\",\"value\":\"en\"}，\n软硬两层语义不同：本参数只调序，filter 直接排除）。\n"
+                },
+                "filters": {
+                    "type": "array",
+                    "description": "按当前实体 catalog 的字段能力填写。",
+                    "items": {
+                        "type": "object",
+                        "required": [
+                            "field",
+                            "operator",
+                            "value"
+                        ],
+                        "properties": {
+                            "field": {
+                                "type": "string"
+                            },
+                            "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",
+                                    "FILTER_OP_GT",
+                                    "FILTER_OP_GTE",
+                                    "FILTER_OP_LT",
+                                    "FILTER_OP_LTE",
+                                    "FILTER_OP_IN",
+                                    "FILTER_OP_NIN",
+                                    "FILTER_OP_CONTAINS",
+                                    "FILTER_OP_MATCH",
+                                    "FILTER_OP_MATCH_PHRASE"
+                                ],
+                                "default": "FILTER_OP_EQ"
+                            },
+                            "value": {}
+                        },
+                        "additionalProperties": false
+                    },
+                    "maxItems": 128
+                },
+                "sort": {
+                    "type": "array",
+                    "description": "按当前实体 catalog 的字段能力填写。",
+                    "items": {
+                        "type": "object",
+                        "required": [
+                            "field",
+                            "order"
+                        ],
+                        "properties": {
+                            "field": {
+                                "type": "string"
+                            },
+                            "order": {
+                                "type": "string",
+                                "enum": [
+                                    "SORT_ORDER_DESC",
+                                    "SORT_ORDER_ASC"
+                                ],
+                                "default": "SORT_ORDER_DESC"
+                            }
+                        },
+                        "additionalProperties": false
+                    },
+                    "maxItems": 32
+                },
+                "cursor": {
+                    "type": "string",
+                    "description": "使用上页 next_cursor 原样续查，保持查询条件不变；不与 page>1 共用。"
+                },
+                "facets": {
+                    "type": "array",
+                    "maxItems": 5,
+                    "items": {
+                        "type": "object",
+                        "additionalProperties": false,
+                        "required": [
+                            "field"
+                        ],
+                        "properties": {
+                            "field": {
+                                "type": "string"
+                            },
+                            "size": {
+                                "type": "integer",
+                                "minimum": 1,
+                                "maximum": 50,
+                                "default": 10
+                            }
+                        }
+                    }
+                }
+            }
+        }
     },
     {
         "name": "semantic_search",
-        "description": "Natural-language semantic search returning relevant paper chunks for\nRAG-style answering.\nUse when: \"How does Transformer attention work?\", \"What are recent\nmethods for protein structure prediction?\".\nNot for: precise field filtering (use search_papers) or fetching full\noriginal text (use read_content).\nReturns: list of chunks; each entry has chunk_id, doc_id, abstract,\nchunk, score, title, offset.\nTypical chain: semantic_search → pick chunk → read_content(doc_id,\noffset).",
+        "description": "Natural-language semantic search returning relevant paper chunks for\nRAG-style answering.\nUse when: \"How does Transformer attention work?\", \"What are recent\nmethods for protein structure prediction?\".\nNot for: precise field filtering (use search_metadata) or fetching full\noriginal text (use read_content).\nReturns: list of chunks; each entry has chunk_id, doc_id, abstract,\nchunk, score, title, offset.\nTypical chain: semantic_search → pick chunk → read_content(doc_id,\noffset).",
         "inputSchema": {
             "type": "object",
             "required": [
@@ -265,7 +451,7 @@ export const TOOLS = [
     },
     {
         "name": "list_catalog",
-        "description": "Returns the schema catalog for search_papers: every field name, type,\nwhether it's filterable / sortable, default-return status, human\ndescription, and applicable FilterOperators.\nUse when: \"Which field do I filter by DOI?\", \"What values can\naccess_oa_status take?\", \"What's the right enum for metadata_type?\".\nNot for: actually searching papers (use search_papers / semantic_search).\nTypical pattern: call once when first encountering Sciverse or facing\nan ambiguous field need, then construct precise search_papers filters\nfrom the returned schema.\nPass include_sample_values=true to also fetch top-20 values for\nenum-like fields (OpenSearch terms aggregation, 24h cached).",
+        "description": "Returns the schema catalog for search_metadata: every field name, type,\nwhether it's filterable / sortable, default-return status, human\ndescription, and applicable FilterOperators.\nUse when: \"Which field do I filter by DOI?\", \"What values can\naccess_oa_status take?\", \"What's the right enum for metadata_type?\".\nNot for: actually searching papers (use search_metadata / semantic_search).\nTypical pattern: call once when first encountering Sciverse or facing\nan ambiguous field need, then construct precise search_metadata filters\nfrom the returned schema.\nPass include_sample_values=true to also fetch top-20 values for\nenum-like fields (OpenSearch terms aggregation, 24h cached).",
         "inputSchema": {
             "type": "object",
             "properties": {
@@ -274,7 +460,8 @@ export const TOOLS = [
                     "enum": [
                         "papers",
                         "authors",
-                        "sources"
+                        "sources",
+                        "patents"
                     ],
                     "default": "papers",
                     "description": "字段 catalog 所属实体集合。papers（默认）/ authors / sources，各 collection 字段不同。"
@@ -295,7 +482,7 @@ export const TOOLS = [
     },
     {
         "name": "list_paper_relations",
-        "description": "Paginate the full relation list of a paper. citations/references/related_works\nare unbounded arrays (up to 340k entries for a single paper) and are NOT\nprojectable in search_papers, so this endpoint is the only way to read them.\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.\nTwo limits (CITATIONS only; REFERENCES/RELATED_WORKS max out at 11833/20 in practice):\nmore than 10000 relations returns 429; page*page_size above 10000 returns 400.\nIn both cases switch to search_papers with filters_advanced on\nreferences_unique_id — it supports deep paging and arbitrary sorting.\ntotal_count counts in-corpus matches only, so it can differ from the paper's own\ncitation_count by about 1%.",
+        "description": "Paginate the full relation list of a paper. citations/references/related_works\nare unbounded arrays (up to 340k entries for a single paper) and are NOT\nprojectable in search_metadata, so this endpoint is the only way to read them.\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_metadata / semantic_search, then paginate\nhere by relation.\nTwo limits (CITATIONS only; REFERENCES/RELATED_WORKS max out at 11833/20 in practice):\nmore than 10000 relations returns 429; page*page_size above 10000 returns 400.\nIn both cases switch to search_metadata with filters on\nreferences_unique_id — it supports deep paging and arbitrary sorting.\ntotal_count counts in-corpus matches only, so it can differ from the paper's own\ncitation_count by about 1%.",
         "inputSchema": {
             "type": "object",
             "required": [
@@ -305,7 +492,7 @@ export const TOOLS = [
             "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。"
+                    "description": "目标论文 unique_id（如 paper:10.1038/xxx），来自 search_metadata / semantic_search；勿传 doc_id。"
                 },
                 "relation": {
                     "type": "string",
@@ -332,13 +519,22 @@ export const TOOLS = [
     },
     {
         "name": "read_content",
-        "description": "Read a range of a paper's original text addressed in Unicode code\npoints (offset/limit count characters like Python len(), not bytes).\nTypically used with a doc_id/offset returned by semantic_search to\nexpand context (read more text before or after a chunk).\nReturns: text fragment, bytes_returned (UTF-8 byte length of text, for\nreference only), next_offset (code-point offset of the next fragment —\npage with it, never with bytes_returned), more (boolean).\nServer behaviour: limit above 524288 is silently clamped; omitting\noffset returns the whole document ignoring limit — the SDKs / MCP\nserver send offset=0 and limit=4096 by default, so pass offset\nexplicitly when calling the HTTP API directly.",
+        "description": "Read a range of a paper or patent’s original text addressed in Unicode code\npoints (offset/limit count characters like Python len(), not bytes).\nTypically used with a doc_id/offset returned by semantic_search to\nexpand context (read more text before or after a chunk).\nReturns: text fragment, bytes_returned (UTF-8 byte length of text, for\nreference only), next_offset (code-point offset of the next fragment —\npage with it, never with bytes_returned), more (boolean).\nServer behaviour: limit above 524288 is silently clamped; omitting\noffset returns the whole document ignoring limit — the SDKs / MCP\nserver send offset=0 and limit=4096 by default, so pass offset\nexplicitly when calling the HTTP API directly.",
         "inputSchema": {
             "type": "object",
             "properties": {
+                "collection": {
+                    "type": "string",
+                    "enum": [
+                        "papers",
+                        "patents"
+                    ],
+                    "default": "papers",
+                    "description": "正文实体；专利必须传 patents，doc_id 来自元数据查询，不能用公开号。"
+                },
                 "doc_id": {
                     "type": "string",
-                    "description": "文献 ID（来自 search_papers / semantic_search）。"
+                    "description": "文献 ID（来自 search_metadata / semantic_search）。"
                 },
                 "offset": {
                     "type": "integer",
@@ -379,7 +575,7 @@ export const TOOLS = [
     }
 ];
 export const ENDPOINTS = {
-    "search_papers": {
+    "search_metadata": {
         "method": "POST",
         "path": "/meta-search"
     },

package/dist/server.js

@@ -2,7 +2,7 @@
 // TODO: 后续可加 SSE / Streamable HTTP 形态（目前只支持 stdio，覆盖主流 coding agent）。
 import { Server } from "@modelcontextprotocol/sdk/server/index.js";
 import { CallToolRequestSchema, ListToolsRequestSchema, } from "@modelcontextprotocol/sdk/types.js";
-import { TOOLS, TOOLS_VERSION } from "./generated/tools.js";
+import { TOOLS, LEGACY_TOOLS, TOOLS_VERSION } from "./generated/tools.js";
 import { executeTool } from "./tools.js";
 export function createServer(config) {
     const server = new Server({
@@ -13,9 +13,10 @@ export function createServer(config) {
             tools: {},
         },
     });
-    server.setRequestHandler(ListToolsRequestSchema, async () => ({
-        tools: TOOLS,
-    }));
+    server.setRequestHandler(ListToolsRequestSchema, async () => {
+        const tools = process.env.SCIVERSE_ENABLE_LEGACY_TOOLS === "true" ? [...TOOLS, ...LEGACY_TOOLS] : TOOLS;
+        return { tools };
+    });
     server.setRequestHandler(CallToolRequestSchema, async (request) => {
         const { name, arguments: args } = request.params;
         const result = await executeTool(config, name, (args ?? {}));

package/dist/tools.js

@@ -3,10 +3,76 @@
 // `toBackendPayload` 是从 packages/typescript/src/client.ts 的 `toBackendPayload`
 // 复制过来的（约 50 行）。MCP 包刻意不依赖 TS SDK，避免 monorepo 内部环依赖。
 // 后续如有第 4 处复制，再用 codegen 收敛。
-import { ENDPOINTS } from "./generated/tools.js";
+import { ENDPOINTS, LEGACY_ENDPOINTS } from "./generated/tools.js";
 import { randomUUID } from "node:crypto";
-const PASSTHROUGH = ["query", "page", "page_size", "fields", "collection"];
+const PASSTHROUGH = ["query", "page", "page_size", "fields", "collection", "freshness_boost", "impact_boost", "language_affinity"];
+const COLLECTIONS = ["papers", "authors", "sources", "patents"];
+const CANONICAL_SEARCH_KEYS = [
+    "query", "collection", "filters", "sort", "fields", "page", "page_size",
+    "cursor", "facets", "freshness_boost", "impact_boost", "language_affinity",
+];
+const PAPER_CONVENIENCE_KEYS = [
+    "title_contains", "abstract_contains", "authors", "year_from", "year_to",
+    "journals", "subjects",
+];
+function validateCollection(collection, allowed = COLLECTIONS) {
+    if (collection !== undefined && (typeof collection !== "string" || !allowed.includes(collection))) {
+        throw new Error(`collection must be one of ${allowed.join(" / ")}`);
+    }
+}
+function rejectUnknown(args, allowed) {
+    for (const key of Object.keys(args)) {
+        if (!allowed.includes(key))
+            throw new Error(`unknown parameter: ${key}`);
+    }
+}
+function toMetadataPayload(args) {
+    rejectUnknown(args, CANONICAL_SEARCH_KEYS);
+    // query/collection 的 null 与省略等价，其余参数不做静默过滤。
+    args = { ...args, collection: args.collection ?? "papers" };
+    if (args.query === null)
+        delete args.query;
+    validateCollection(args.collection);
+    for (const [key, allowed] of [
+        ["filters", ["field", "operator", "value"]],
+        ["sort", ["field", "order"]],
+        ["facets", ["field", "size"]],
+    ]) {
+        if (args[key] === undefined)
+            continue;
+        if (!Array.isArray(args[key]))
+            throw new Error(`${key} must be an array`);
+        for (const item of args[key]) {
+            if (!item || typeof item !== "object" || Array.isArray(item))
+                throw new Error(`${key} entries must be objects`);
+            rejectUnknown(item, allowed);
+            if (key === "facets") {
+                const { size } = item;
+                if (size !== undefined && (typeof size !== "number" || !Number.isInteger(size) || size < 1 || size > 50)) {
+                    throw new Error("facets size must be an integer from 1 to 50");
+                }
+            }
+        }
+    }
+    return { ...args, collection: args.collection ?? "papers" };
+}
 function toBackendPayload(args) {
+    const collection = args.collection ?? "papers";
+    validateCollection(collection);
+    let sortByYear = args.sort_by_year ?? "auto";
+    if (typeof sortByYear !== "string" || !["auto", "none", "asc", "desc"].includes(sortByYear)) {
+        throw new Error("sort_by_year must be one of auto / none / asc / desc");
+    }
+    if (collection !== "papers") {
+        if (sortByYear === "asc" || sortByYear === "desc") {
+            throw new Error("sort_by_year asc/desc is only supported for collection papers");
+        }
+        for (const key of PAPER_CONVENIENCE_KEYS) {
+            if (Object.prototype.hasOwnProperty.call(args, key)) {
+                throw new Error(`${key} is only supported for collection papers`);
+            }
+        }
+    }
     const out = {};
     const filters = [];
     const sort = [];
@@ -41,9 +107,8 @@ function toBackendPayload(args) {
     }
     // sort_by_year 默认 auto：有 query（或 sort_advanced）时不加年份排序——保 BM25
     // 相关性且软加权可用；纯结构化筛选时按年份降序（后端默认序实质乱序）。
-    let sortByYear = args.sort_by_year ?? "auto";
     if (sortByYear === "auto") {
-        sortByYear = args.query || (Array.isArray(args.sort_advanced) && args.sort_advanced.length > 0)
+        sortByYear = collection !== "papers" || args.query || (Array.isArray(args.sort_advanced) && args.sort_advanced.length > 0)
             ? "none" : "desc";
     }
     if (sortByYear !== "none") {
@@ -167,7 +232,9 @@ async function callBinary(config, path, query) {
     };
 }
 export async function executeTool(config, name, args) {
-    const endpoint = ENDPOINTS[name];
+    const endpoints = process.env.SCIVERSE_ENABLE_LEGACY_TOOLS === "true"
+        ? { ...ENDPOINTS, ...LEGACY_ENDPOINTS } : ENDPOINTS;
+    const endpoint = Object.prototype.hasOwnProperty.call(endpoints, name) ? endpoints[name] : undefined;
     if (!endpoint) {
         return {
             isError: true,
@@ -175,8 +242,17 @@ export async function executeTool(config, name, args) {
         };
     }
     switch (name) {
-        case "search_papers":
-            return call(config, "POST", endpoint.path, { body: toBackendPayload(args) });
+        case "search_metadata":
+        case "search_papers": {
+            let body;
+            try {
+                body = name === "search_metadata" ? toMetadataPayload(args) : toBackendPayload(args);
+            }
+            catch (e) {
+                return { isError: true, content: [{ type: "text", text: JSON.stringify({ error: e.message }) }] };
+            }
+            return call(config, "POST", endpoint.path, { body });
+        }
         case "semantic_search": {
             let body;
             try {
@@ -202,7 +278,13 @@ export async function executeTool(config, name, args) {
             return call(config, "GET", endpoint.path, { query });
         }
         case "read_content": {
-            const { doc_id, offset, limit } = args;
+            const { doc_id, collection, offset, limit } = args;
+            try {
+                validateCollection(collection, ["papers", "patents"]);
+            }
+            catch (e) {
+                return { isError: true, content: [{ type: "text", text: JSON.stringify({ error: e.message }) }] };
+            }
             if (!doc_id) {
                 return {
                     isError: true,
@@ -211,7 +293,7 @@ export async function executeTool(config, name, args) {
             }
             // 后端未传 offset 时返回整篇全文并忽略 limit；这里始终显式传两者，避免把整篇论文灌进模型上下文。
             return call(config, "GET", endpoint.path, {
-                query: { doc_id, offset: offset ?? 0, limit: limit ?? 4096 },
+                query: { doc_id, offset: offset ?? 0, limit: limit ?? 4096, collection },
             });
         }
         case "get_resource": {

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "sciverse-mcp-server",
-  "version": "0.15.1",
-  "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, ...).",
+  "version": "1.0.0",
+  "description": "Sciverse MCP server — metadata search across papers, patents, authors and sources, paper semantic retrieval and document content reading.",
   "license": "Apache-2.0",
   "homepage": "https://github.com/opendatalab/Sciverse-Agent-Tools/tree/main/packages/mcp",
   "repository": {