Academic MCP F0a4c03b

MCP文档知识

提供方 Heisenbear-Rebirth

文档知识 stdio · 本地进程 无需鉴权 社区 / 第三方
查看接入方式

Academic MCP Server 是一个专为大规模语言模型设计的高效论文结构化抓取与Markdown分析服务器,支持五大顶尖学术库的反爬限制突破与全链路自动结构化沉淀。

一句话选型结论

按资料字段整理

Academic MCP F0a4c03b 属于文档知识类 MCP 服务器,stdio · 本地进程,无需鉴权,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类文档知识 传输方式stdio · 本地进程 鉴权无需鉴权 部署方式本地部署
GitHub 星标 1 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

文档知识
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

适用场景

学术论文抓取Python本地部署反爬限制突破Markdown分析大规模语言模型自动化处理

安装与配置

stdio · 本地进程 无需鉴权
客户端在本机拉起子进程,数据不出本机
python -m venv .venv

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Python,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
文档检索问答

在你的文档库里按问题找答案。

知识库读写

把新资料写进知识库,随用随取。

内容整理

把零散资料归纳成结构化笔记。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 资料标注无需鉴权,装好就能连。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在文档知识场景里让模型直接调用外部能力的人。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Academic MCP F0a4c03b当前 未标注 stdio · 本地进程 本地部署 有 2026-05-17
dify 未标注 stdio · 本地进程 本地部署 有 2026-04-11
open-webui 未标注 stdio · 本地进程 本地部署 有 2026-04-11
JeecgBoot 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Cherry Studio 未标注 未标注 未标注 无 2026-05-17
mempalace 未标注 stdio · 本地进程 本地部署 有 2026-04-11

服务器档案

文档知识
字段来自项目仓库与公开索引,中文说明由本站标注
提供方Heisenbear-Rebirth上游标注的维护方 Heisenbear-Rebirth
分类文档知识本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式无需鉴权远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · Python本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-05-17上游最后核验时间

详细介绍

35.7 KB
来自项目仓库与上游目录的原文,未做删改

Academic MCP Server

> 中文版:README.zh-CN.md

A Model Context Protocol (MCP) server that exposes a uniform paper-discovery
and full-text-extraction API on top of eleven academic / patent sources:

Code Source Engine
ARXIV arXiv (preprints) Camoufox (Firefox)
CNKI 中国知网 (China National Knowledge Infrastructure) Playwright Chromium
IEEE IEEE Xplore Camoufox (Firefox)
ACM ACM Digital Library Camoufox (Firefox)
SD ScienceDirect (Elsevier) Camoufox (Firefox)
AIAA AIAA Aerospace Research Central request-first HTTP + Camoufox auth
MDPI MDPI journals request-first HTTP
WOS Web of Science Core Collection API-level WoS fetch + Chromium auth
GS Google Scholar Camoufox (Firefox)
PATYEE Patyee 专利之星 Playwright Chromium
DAWEI 大为专利 (pat.daweisoft.com) Playwright Chromium

Every source is wrapped by a per-platform scraper that surfaces a consistent
result schema, and every download/conversion is routed through a local
MongoDB-backed library so repeated queries are served from cache, browser
state is shared across concurrent MCP clients, and downloaded PDFs/Markdown
are deduplicated on disk.

The whole thing is meant to be embedded as a tool provider in an LLM agent
(Claude Desktop, Codex, etc.) via MCP, but the underlying tools are also
useful as a CLI/library on their own.


Architecture```

┌──────────────────────────────────────────────────────────────────────┐
│ MCP client (Claude / Codex / ...) │
└────────────────────────────┬─────────────────────────────────────────┘
│ MCP tool calls
▼
┌──────────────────────────────────────────────────────────────────────┐
│ server.py — FastMCP entry, dispatches to per-platform scrapers │
│ ┌──────────────────────────┐ ┌────────────────────────────────┐ │
│ │ Library (library.py) │◄──►│ Scrapers (11 modules) │ │
│ │ Mongo: papers, │ │ - one Camoufox/Chromium │ │
│ │ search_queries, │ │ persistent context per │ │
│ │ browser_state │ │ platform (singleton) │ │
│ │ Files: .repo/{platform} │ │ - pooled per-PID profile │ │
│ │ /{native_id}/ │ │ when canonical is busy │ │
│ └──────────────────────────┘ └────────────────────────────────┘ │
└────────────────────────────┬─────────────────────────────────────────┘
│ optional
▼
┌──────────────────────────────────────────────────────────────────────┐
│ library_web/ — FastAPI/Jinja2 management console (port 5577) │
│ / /papers /papers/{p}/{id} /searches /browser-state /file │
└──────────────────────────────────────────────────────────────────────┘


Every MCP tool call passes through the Library first:

- **Search**: the (platform, query, filters) tuple is hashed; on cache hit
  the cached result is returned without launching a browser.
- **Details / Download / Read**: the paper is identified by
  `(platform, native_id)` extracted from the URL. If the metadata / PDF /
  Markdown is already on disk, it is mirrored to the caller's requested
  `output_dir` without re-fetching.
- **Browser state**: each Camoufox scraper pins a single fingerprint per
  platform and reuses verification cookies (cf_clearance / DataDome / …),
  so one manual CAPTCHA carries across reboots and across concurrent MCP
  clients.

---

## Components

| Path                         | Role                                                                                              |
| ---------------------------- | ------------------------------------------------------------------------------------------------- |
| `server.py`                  | FastMCP server. Exposes the five MCP tools and wires them through the Library.                    |
| `runtime_config.py`          | Loads `mcp_runtime_config.json`, resolves project paths, computes profile dirs (with suffix).     |
| `mcp_logging.py`             | UTF-8-safe stderr printer that doesn't break when the MCP transport is JSON-RPC over stdio.       |
| `library.py`                 | MongoDB DAO for `papers`, `search_queries`, `browser_state` + helpers for filesystem mirroring.   |
| `scraper_utils.py`           | Shared helpers: `goto_with_retry`, `venue_matches`, profile pool, fingerprint + cookie sharing.   |
| `pdf_utils.py`               | `convert_pdf_to_markdown()` — uses pymupdf4llm, falls back to per-page images for scanned PDFs.   |
| `{platform}_scraper.py`      | One module per source. All expose `search_papers / get_paper_details / download_paper / read_paper_content / close`. |
| `library_web/`               | FastAPI app + Jinja2 templates for the management console.                                        |
| `library_web_{start,stop}.{bat,ps1}` | Helper scripts to launch / stop the console (port from `mcp_runtime_config.json`).      |
| `.repo/`                     | Canonical file store: `.repo/{PLATFORM}/{safe_native_id}/paper.pdf` and `paper.md`.               |
| `.{platform}_profile/`       | Per-platform browser profile. Canonical profile + per-PID ephemeral copies as needed.             |

---

## Requirements

- **Python 3.10+** (tested on 3.11/3.12). 3.10 is the lower bound for the
  PEP 604 union syntax used in a few places.
- **MongoDB 3.6+** locally reachable (tested against `mongo:4.4` in Docker).
  Collections and their indexes are created automatically on first start;
  JSON-shaped fields (`keywords`, `extra`, `results`, `filters`, `cookies`,
  `fingerprint`) are stored as native BSON documents/arrays.
- **Camoufox kernel** (auto-fetched into `%LOCALAPPDATA%\camoufox` on
  Windows; under `~/.cache/camoufox` on Linux).

---

## Installation```bash
python -m venv .venv
.\.venv\Scripts\activate          # Windows
# source .venv/bin/activate       # POSIX
pip install -r requirements.txt
python -m camoufox fetch          # downloads the patched Firefox kernel

Create .env from .env.example and point it at your MongoDB:```dotenv

Full connection URI (recommended — supports auth / replica sets / options)

MONGODB_URI=mongodb://127.0.0.1:27017
MONGODB_DATABASE=academic_mcp

For an auth-enabled server, include the credentials + authSource, e.g.

MONGODB_URI=mongodb://user:pass@127.0.0.1:27017/?authSource=admin


Alternatively, leave `MONGODB_URI` unset and provide discrete
`MONGODB_HOST` / `MONGODB_PORT` / `MONGODB_USER` / `MONGODB_PASSWORD` parts.

The library creates the database, collections and indexes on first start.
If MongoDB is unreachable the Library disables itself with a clear warning
and the server falls back to passthrough mode (no caching, no shared
browser state — but everything still works).

---

## Configuration

`mcp_runtime_config.json` (committed) holds non-secret tunables:

| Key                                   | Type    | Default          | Purpose                                                                                 |
| ------------------------------------- | ------- | ---------------- | --------------------------------------------------------------------------------------- |
| `playwright_browsers_path`            | string  | `".ms-playwright"` | Where Playwright stores its Chromium download.                                          |
| `override_playwright_browsers_path`   | bool    | `true`           | Force-export the path so the right Chromium is picked up by Playwright on every launch. |
| `set_cwd_to_project_root`             | bool    | `true`           | `chdir` to the project root on import — keeps relative paths sane in MCP servers.       |
| `allow_headful_fallback`              | bool    | `false`          | Master switch: on anti-bot block, may we relaunch with a visible browser for human verification? |
| `allow_headful_fallback_platforms`    | list    | `["ACM","SD","AIAA","WOS"]` | Subset of platforms allowed to do the headful CAPTCHA fallback.                         |
| `manual_verification_timeout_seconds` | int     | `180`            | How long we wait (in headful mode) for a human to click through the CAPTCHA.            |
| `library_enabled`                     | bool    | `true`           | Master switch for the MongoDB+filesystem Library. Set to `false` to disable caching.    |
| `library_root`                        | string  | `".repo"`        | Where canonical PDFs/MD/images live (relative to project root or absolute).             |
| `library_web_host` / `library_web_port` | string/int | `127.0.0.1:5577` | Bind address for the management console.                                              |
| `profile_suffix`                      | string  | `""`             | Optional shared suffix; per-client override via `MCP_PROFILE_SUFFIX` env var (see below). |

Secrets live in `.env` (gitignored). Only the MongoDB connection so far.

---

## MCP tools

All five tools are registered on the FastMCP server (`server.py`) and
appear to the LLM with the docstrings preserved verbatim.

### `search_papers(query, platform="CNKI", ...)`

Parameter · Type · Description
`query` · str · The search terms. Free text; per-platform syntax (e.g. IEEE supports `("Publication Title":"...")`) is allowed.
`platform` · str · One of `CNKI`, `IEEE`, `ARXIV`, `ACM`, `SD`, `AIAA`, `MDPI`, `WOS`, `GS`, `PATYEE`, `DAWEI`.
`search_field` · str · Restricts the query field. Platform-specific (see docstring); defaults to each platform's "all".
`db_scope` · str · Database. CNKI: `总库 / 中文 / 外文`. WOS: the "Search in" database (default `WOSCC`). Verified: `WOSCC`, `ALLDB`, `CCC`, `CSCD`, `KJD`, `MEDLINE`, `PPRN`, `PQDT`, `RC`, `SCIELO`. Not supported: `DIIDW` (Derwent), `GRANTS`. `editions` apply to WOSCC only.
`source_type` · str · Document type filter (research-article, conference, journal, …). Platform-specific.
`journal` · str \ · None · Restrict to a publication. Server combines URL-level filters with a client-side fuzzy `venue_matches` check that tolerates Google-Scholar-style "…" truncations.
`start_year` · int \ · None · Inclusive lower bound on publication year.
`end_year` · int \ · None · Inclusive upper bound on publication year.
`sort_by` · str · `relevance` (default), `citations`, or `date_desc`.
`start_index` · int · Pagination offset; pass e.g. 20 to skip the first page of 10–20 results.
`limit` · int · Max number of results to return (default 10).
`editions` · str · WOS only. Restrict the WOSCC "Editions"; empty = All. Comma-separated codes/labels: `SCI-EXPANDED`(`SCI`), `SSCI`, `AHCI`, `CPCI-S`, `CPCI-SSH`, `ESCI`, `CCR-EXPANDED`, `IC`.

**Returns** a JSON string with:```json
{
  "total_results": "1707",
  "papers": [
    {
      "id": "<8-hex hash of detail_link>",
      "title": "...",
      "author": "...",
      "source": "...",                // raw publisher line (Volume / Issue / etc.)
      "venue_name": "...",            // canonical journal / conference name when extractable
      "doi": "10.1145/...",           // ACM only; others fill in from get_paper_details
      "date": "March 2026",
      "db_type": "Research article",
      "detail_link": "https://..."
    }
  ],
  "_cache_hit": true                  // server-only flag; true when served from MongoDB cache
}

Cache key is (platform, normalized query, filters, pagination). Cache
entries never expire by default (the user picked permanent caching during
the initial design). To force a refresh, delete the row from the
search_queries table or via the web console.

get_paper_details(url, platform="CNKI")

Fetches abstract / keywords / DOI for a specific paper. Re-uses cached
data when the same paper has already been seen (abstract column in
papers). Returns:```json
{
"url": "...",
"abstract": "...",
"keywords": ["..."],
"doi": "...",
"_cache_hit": true
}


`get_paper_details` is wrapped in `goto_with_retry` — transient Firefox
network aborts (`NS_ERROR_ABORT`, `NS_ERROR_NET_INTERRUPT`, ...) get up to
two automatic retries with exponential backoff before the failure
propagates.

As a side effect, every successful details fetch also stores an
EndNote-importable RIS record on `papers.ris_text` (see
RIS auto-store below).

### `download_paper(url, output_dir, platform="CNKI")`

Downloads the PDF. If the file is already on disk under
`.repo/{PLATFORM}/{native_id}/...pdf` it is just mirrored to `output_dir`.
On a fresh download, it is written into the canonical location AND
mirrored to `output_dir`. Returns the local filesystem path.

The current download stack is request-first. For protected platforms, the
browser is used to establish a valid verification state and, when the site
requires it, to reach the page state that mints a signed asset URL. The
actual data path then uses direct HTTP, in-page `fetch`, response-body
capture, or Playwright's download event instead of button-click automation.

Platform-specific behavior:

- `ACM`: attempts the DOI PDF endpoint with verified cookies. If both the
  detail page and `/doi/pdf/...` expose only abstract HTML, the item is
  classified as `unavailable` instead of a scraper failure.
- `SD`: search/details prefer direct HTTP. PDF retrieval navigates only far
  enough to trigger the signed ScienceDirect asset stream, then saves bytes
  through programmatic download/body capture. A solved PDF-host challenge
  can be reused by later requests until the publisher invalidates the token.
- `AIAA`: search, details, PDF, and RIS are request-first against Atypon
  endpoints (`/action/doSearch`, `/doi/...`, `/doi/pdf/...`,
  `/action/downloadCitation`). The browser is only used to refresh the
  Cloudflare verification state; direct requests reuse that state with the
  Firefox 135 network fingerprint required by the issued `cf_clearance`.
- `MDPI`: search/details/PDF/RIS are request-first. The scraper handles
  MDPI's Akamai interstitial in-process by parsing the `bm-verify` payload
  and posting to `/_sec/verify?provider=interstitial`, then reuses the
  resulting session cookie for HTML, `/pdf`, and `/export` requests.
- `WOS`: discovery-only. Search calls the captured
  `/api/wosnx/core/runQuerySearch` NDJSON endpoint and parses records,
  abstracts, citation counts, DOI, source, and document type metadata.
  `search_field="ADVANCED"` enables native Web of Science query syntax, for
  example `TS=("aeroelastic flutter") AND PY=(2020-2026)`. Normal fielded
  search mirrors the WoS dropdown: `ALL`, `TS`, `TI`, `AU`, `SO`, `PY`, `OG`,
  `FO`, `PUBL`, `DOP`, `AB`, `UT`, `AD`, `AI`, `AK`, `CF`, `DT`, `DO`, `ED`,
  `FG`, `GP`, `KP`, `LA`, `PMID`, and `WC`, with English/Chinese aliases for
  the common labels. Boolean basic-search rows are supported either as JSON
  rows, for example
  `[{"field":"TS","text":"flutter"},{"op":"OR","field":"TI","text":"aeroelastic"},{"op":"NOT","field":"AU","text":"Smith"}]`,
  or as multiline shorthand: `TS=flutter`, `OR TI=aeroelastic`,
  `NOT AU=Smith`. In the tested Tongji VPN route, plain Python/curl HTTP
  stacks fail during TLS while Chromium succeeds, so the scraper uses a
  verified Chromium profile to issue API-level `fetch()` requests without
  clicking through the UI. PDF download and full-text reading are intentionally
  unsupported; use DOI/publisher links from the result with the native
  publisher scraper.

### `read_paper_content(url, output_dir, platform="CNKI")`

Three-level cache:

1. If Markdown is already in the library → mirror MD + images/ to
   `output_dir` and return immediately.
2. If only the PDF is cached → re-run `pdf_utils.convert_pdf_to_markdown`
   against the cached PDF.
3. Cache miss → full scrape, store PDF + MD + images, mirror to
   `output_dir`.

Returns the MD file path and a 1000-character preview.

### `convert_local_pdf(pdf_path, output_dir)`

Standalone helper to convert a user-supplied PDF to Markdown using the
same image-extraction pipeline. Does not touch the Library.

---

## The Library (MongoDB + filesystem)

### Collections```
papers          unique index (platform, native_id); integer `id` (web UI)
                title, author, source, venue_name, pub_date, db_type, doi,
                detail_link, abstract, keywords (array),
                pdf_path, md_path, images_dir, extra (subdocument),
                ris_text (platform-native or synthesized RIS export),
                created_at, updated_at

search_queries  unique index (platform, md5(query + filters)); integer `id`
                query_text, filters (subdocument), total_results,
                results (array of subdocuments), fetched_at

browser_state   _id == platform
                fingerprint (subdocument: BrowserForge Fingerprint),
                cookies     (array: Playwright context.cookies()),
                user_agent, verified_at, updated_at, note

counters        _id == collection name; seq -> emulates AUTO_INCREMENT so the
                integer `id` the web UI relies on stays stable.

JSON-shaped fields are stored as native BSON documents/arrays (no more
text round-tripping). The integer id on papers/search_queries is
assigned from the counters collection only on genuine inserts, so the
web UI's numeric paper-export / search-delete keys stay stable.

Filesystem layout```

.repo/
ARXIV/2605.16230/
arxiv_2605_16230.pdf
arxiv_2605_16230.md
images/
arxiv_2605_16230.pdf-0002-08.png
...
IEEE/9266228/
ieee_9266228.pdf
ieee_9266228.md
images/...
CNKI/CJFD|...


`native_id` is normalized to a filesystem-safe slug. The canonical
location is the single source of truth; every download mirrors to the
caller's `output_dir` afterward.

### RIS auto-store

Every `get_paper_details` call that produces a usable abstract also
populates `papers.ris_text` with an EndNote-importable RIS record.
The server prefers the platform's own RIS export endpoint (richer
pagination, ISSN, conference proceedings name) and falls back to
synthesizing one from the stored metadata (`ris_utils.synthesize_ris`)
when the platform doesn't expose an endpoint or the network call fails.
Either way the column is populated idempotently — re-running details
on a cached row doesn't refetch.

| Platform | Source         | Endpoint / strategy                                                                                                        |
| -------- | -------------- | -------------------------------------------------------------------------------------------------------------------------- |
| IEEE     | platform       | `/rest/search/citation/format`, with `/xpl/downloadCitations` form POST fallback.                                          |
| ACM      | platform       | `/action/downloadCitation?format=ris&include=abs`.                                                                         |
| SD       | platform       | `/sdfe/arp/cite?format=application/x-research-info-systems` — issued via `page.evaluate("fetch(url)")` so DataDome sees an in-app XHR (a direct `context.request.get` returns a 403 challenge page). |
| AIAA     | platform       | `/action/downloadCitation` form POST with `format=ris&include=abs`.                                                        |
| MDPI     | platform       | `/export` form POST with `articles_ids[]` and `export_format_top=ris`.                                                     |
| ARXIV / CNKI / WOS / GS / PATYEE / DAWEI | synthesized | `ris_utils.synthesize_ris` infers `TY` from db_type + venue, splits `AU`, parses `PY/DA` from `pub_date`, and tags `AN  - {platform}:{native_id}` for round-tripping. |

A bundled export is available from the web console: filter `/papers` by
state, tick the checkboxes, and POST to `/papers/export-ris`.
Rows that are missing `ris_text` (e.g. a synthesizer was added after the
row was first seen) are synthesized on demand during the export and the
result is written back, so the next export hits cache.

---

## Browser state pool (concurrency + verification reuse)

Firefox/Camoufox refuses to open the same profile directory from two
processes simultaneously. Without coordination, running two MCP clients
(e.g. one inside Claude Desktop and one inside Codex) would either hang
on the "Firefox is already running" modal or force every client to clear
its own CAPTCHA.

The browser-state pool solves both:

1. **Pooled profile dirs.** The first MCP server to claim a platform uses
   the canonical `._profile/`. Concurrent servers transparently
   fall back to an ephemeral per-PID copy `._profile__p/`
   (auto-removed on `close()`). A PID-aware sentinel file
   (`.mcp_owner`) prevents stale locks from crashed processes from
   blocking new launches.

2. **Pinned fingerprint.** Cloudflare's `cf_clearance` and DataDome
   tokens are bound to the browser fingerprint. We generate ONE
   `browserforge` Fingerprint per platform with `os="windows"`, store it
   pickled+base64 in `browser_state.fingerprint`, and pass it to every
   `AsyncCamoufox(fingerprint=...)` launch. All concurrent clients on a
   platform present the same identity.

3. **Shared cookies.** After a successful pass of CAPTCHA / Cloudflare /
   DataDome, the scraper captures `context.cookies()` into
   `browser_state.cookies`. The next launch (any client, any MCP server
   process) injects those cookies via `context.add_cookies` *before* the
   first navigation. One manual verification covers all clients until
   the platform invalidates the token.

A row in `browser_state` is marked `verified_at = NOW()` whenever the
captured cookies contain a known clearance cookie (`cf_clearance`,
`datadome`, `__ddg`, `incap_ses`, `reese84`).

### Limitations

`cf_clearance` is bound to `(IP, fingerprint, TLS JA3)`. We pin
fingerprint; your IP is your local IP; but Camoufox's outgoing TLS
fingerprint is not byte-identical across launches. In practice this
means most launches reuse the verification, but a tightened Cloudflare
policy can still occasionally force a re-verify. This is still strictly
better than the unfixed state (every client, every restart needs
manual interaction).

### Web console pages

| URL                                       | Purpose                                                                          |
| ----------------------------------------- | -------------------------------------------------------------------------------- |
| `/`                                       | Counts per platform + totals.                                                   |
| `/papers`                                 | Paginated listing with platform / keyword / state filter. Checkbox-select rows and POST `/papers/export-ris` for a bundled `.ris` download. |
| `/papers/{platform}/{native_id}`          | Full metadata, abstract, links to served PDF / Markdown.                        |
| `/searches`                               | Cached search queries; delete per row to force refetch.                         |
| `/browser-state`                          | Per-platform fingerprint / cookies / verification status; clear or full reset.  |
| `/file?path=...`                          | Static file server scoped to `.repo/`. Path traversal is rejected.              |
| `/health`                                 | JSON: `{enabled, reason, library_root}`.                                        |

---

## Running

### MCP server (production)

Wire the server into your MCP client's configuration. For Claude
Desktop's `mcp.json` (or Codex's equivalent):```jsonc
{
  "academic-mcp": {
    "command": "E:\\Projects\\CNKI-MCP\\.venv\\Scripts\\python.exe",
    "args": ["E:\\Projects\\CNKI-MCP\\server.py"],
    "env": {
      "MCP_PROFILE_SUFFIX": "claude"
    }
  }
}

MCP_PROFILE_SUFFIX is optional. Leave it unset for the default
behavior (one canonical profile, automatic per-PID fallback for the
second client). Set it differently in each client only if you want each
MCP server to have its own dedicated profile set
(.ieee_profile_claude, .ieee_profile_codex, etc.). The DB-backed
browser state is shared regardless.

MCP server (standalone, for debugging)```bash

..venv\Scripts\python.exe server.py


The server speaks MCP over stdio, so a raw invocation will just hang
waiting for JSON-RPC. Useful only when attached from an MCP client.

### Management console```bat
library_web_start.bat   :: starts uvicorn on the configured port, opens the browser
library_web_stop.bat    :: kills the listener on that port

PowerShell equivalents (library_web_start.ps1 /
library_web_stop.ps1) are also provided. The console runs read-write
(it can delete cache rows / clear browser state) but is bound to
127.0.0.1 by default — change library_web_host in
mcp_runtime_config.json if you really want remote access.


Multi-client guidance

Scenario What happens What you should do
One MCP client at a time Canonical profile, full caching, one CAPTCHA per platform per token TTL. Nothing.
Two clients, same platform, same time First client gets canonical profile; second gets per-PID ephemeral copy. Both share cookies. Nothing.
Two clients, you want fully isolated profiles Set MCP_PROFILE_SUFFIX=claude / MCP_PROFILE_SUFFIX=codex in each client's env. Edit MCP client config.
CAPTCHA appeared and you solved it once Cookies captured to browser_state. Subsequent launches inject them and skip the challenge. Nothing.
Platform banned the fingerprint All clients fail equally because they all present the same identity. /browser-state → "完全重置".
Just want to drop stale cookies verified_at will go stale; new searches may take the manual path again. /browser-state → "清 Cookie".

Validation and performance

Latest full-platform integration smoke run: scratch/full_platform_test.py,
run id 20260614_full_final (2026-06-14). AIAA was added and tested
separately with run id 20260628_aiaa_final_relevance (2026-06-28);
MDPI was added and tested with run id 20260628_mdpi_retry (2026-06-28). Each
downloadable platform was tested with up to three fresh sample downloads.
WOS was added as a discovery-only platform and smoke-tested with run id
20260704_wos_fields_boolean (2026-07-04), covering native advanced-search
payloads plus basic-field dropdown mappings and Boolean rows.
These runs completed with 0 hard failures. unavailable means the
publisher or the tool semantics did not expose a downloadable PDF for that
sample; it is not counted as a transport or parser failure.

Platform Search Details Download classification Read
ARXIV 6.584 s 4.976 s 3/3 OK: 15.065, 12.841, 10.203 s success, 20.405 s
CNKI 1.587 s 0.198 s 3/3 OK: 1.488, 1.479, 1.325 s success, 2.178 s
IEEE 4.165 s 1.149 s 3/3 OK: 29.498, 8.352, 2.809 s success, 36.236 s
ACM 25.385 s 3.034 s 3/3 unavailable: sampled articles exposed no PDF link unavailable
SD 15.312 s 4.913 s 3/3 OK: 4.835, 5.381, 3.819 s success, 22.149 s
AIAA 1.879 s 0.828 s 3/3 OK: 8.993, 5.554, 3.004 s success, 14.402 s
MDPI 2.388 s 0.976 s 3/3 OK: 4.977, 11.925, 19.477 s success, 7.186 s
WOS 9.026 s 0.000 s not applicable by design not applicable
GS 2.443 s 0.000 s not applicable by design not applicable
PATYEE 1.695 s 0.374 s 1/3 OK, 2/3 unavailable success, 8.778 s
DAWEI 2.551 s 0.755 s 3/3 OK: 3.115, 3.284, 2.598 s success, 4.768 s

Operational notes:

  • ACM, SD, and AIAA require valid verification state for some requests. Once the
    visible challenge has been solved, subsequent retrievals reuse the stored
    browser identity and cookies where the publisher accepts them.
  • SD PDF success depends on the separate pdf.sciencedirectassets.com
    challenge as well as the ScienceDirect detail-page DataDome state.
  • AIAA accepts direct programmatic requests only when the request fingerprint
    matches the Firefox profile that produced cf_clearance; the implemented
    path uses curl_cffi with firefox135.
  • AIAA's latest-date book-chapter samples may return publisher purchase
    pages from /doi/pdf/...; these are classified as unavailable, not
    transport failures (20260628_aiaa_date_sort_classified had 0 hard
    failures).
  • MDPI is open-access and uses a lightweight Akamai interstitial; the
    challenge is solved programmatically and does not require a browser
    warmup profile.
  • WOS may require hCaptcha/passive verification. Run
    warmup_platform_auth(platforms="WOS") once when it returns
    Server.passiveVerificationRequired; after that, searches use the WoS
    NDJSON endpoint through the verified Chromium profile. WoS is not a PDF
    source in this MCP.
  • Google Scholar is search-oriented in this server; PDF download/read is

…(正文过长,页面只展示前面部分,完整内容见仓库)

常见问题

7 问
答案由本站依据条目字段整理,不引用上游原文
Academic MCP F0a4c03b 怎么安装?

在客户端按下面的安装命令接入:python -m venv .venv。装完在客户端配置里引用同一个包或端点。

Academic MCP F0a4c03b 怎么在客户端里配置?

它的传输方式未标注,在客户端 MCP 配置里按官方文档填写启动命令和参数,保存后重启客户端生效。

Academic MCP F0a4c03b 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Academic MCP F0a4c03b 需要 API Key 吗?

资料标注为无需认证,装好就能连;如果实际调用时报鉴权错误,按官方文档补上凭据。

Academic MCP F0a4c03b 能提供哪些能力?

资料显示能力标签包括 Python、自动化处理、文档处理。具体工具清单以官方文档为准。

Academic MCP F0a4c03b 需要什么运行环境?

运行时为 Python;属于本地进程,需要在本机装好运行环境。

Academic MCP F0a4c03b 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-17。