Skip to main content
Glama
Scholar Feed MCP Server

Scholar Feed MCP Server

Scholar Feed MCP 服务器

通过 Claude Code、Cursor 或任何 MCP 客户端,搜索超过 560,000 篇计算机科学/人工智能/机器学习研究论文,并获取基于 LLM 的创新性分析。

Scholar Feed 每日索引 arXiv 论文,并使用多信号评分系统(时效性、引用速度、机构声誉、代码可用性)进行排名。每篇论文都包含 LLM 生成的摘要和创新性评分。

快速开始

npx scholar-feed-mcp init

此交互式向导将:

  1. 选择性地询问 API 密钥(或跳过以进行匿名访问)

  2. 检测您的 MCP 客户端(Claude Code、Cursor 或 Claude Desktop)

  3. 写入配置并验证连接

无需 API 密钥。 匿名访问每天提供 100 次调用,足以满足典型的研究需求。如需更高限额(每天 500 次),请在 scholarfeed.org/settings 获取免费密钥。

尝试询问:"Search for recent papers on test-time compute scaling"(搜索关于测试时计算扩展的最新论文)

Related MCP server: Research MCP

您可以做什么

技术侦察 — “本月发表了哪些关于检索增强生成(RAG)的创新研究?”

文献综述 — “查找与 2401.04088 类似的论文并导出它们的 BibTeX”

趋势监测 — “本周 cs.CV 领域的热门趋势是什么?总结前 3 名。”

深度研究 — “对‘大语言模型中的推理’进行深度研究”

基准测试跟踪 — “向我展示 MMLU 排行榜并比较 GPT-4 和 LLaMA-3”

作者发现 — “谁是致力于高效 LLM 推理的顶尖研究人员?”

手动安装

Claude Code

# Without API key (anonymous, 100 calls/day)
claude mcp add scholar-feed -- npx -y scholar-feed-mcp

# With API key (500 calls/day)
claude mcp add scholar-feed -e SF_API_KEY=sf_your_key_here -- npx -y scholar-feed-mcp

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "scholar-feed": {
      "command": "npx",
      "args": ["-y", "scholar-feed-mcp"]
    }
  }
}

要添加 API 密钥,请在配置中添加 "env": { "SF_API_KEY": "sf_your_key_here" }。

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "scholar-feed": {
      "command": "npx",
      "args": ["-y", "scholar-feed-mcp"]
    }
  }
}

项目范围 (.mcp.json)

{
  "mcpServers": {
    "scholar-feed": {
      "command": "npx",
      "args": ["-y", "scholar-feed-mcp"],
      "env": { "SF_API_KEY": "${SF_API_KEY}" }
    }
  }
}

Windows 注意事项: 使用 "command": "cmd" 和 "args": ["/c", "npx", "-y", "scholar-feed-mcp"]。

可用工具 (23)

核心搜索与发现

工具

描述

关键参数

search_papers

带过滤器的全文关键词搜索

q, category, novelty_min, days, method_category, task, dataset, contribution_type, task_category, has_results, cursor, limit

get_paper

通过 arXiv ID 获取论文详细信息

arxiv_id, fields

find_similar

通过嵌入 + 文献耦合查找相似论文

arxiv_id, limit, days

get_citations

引用图(引出参考文献或引入引用)

arxiv_id, direction, limit, fields

whats_trending

今日基于综合评分的热门论文

category, limit, fields, exclude_ids

batch_lookup

一次查找多篇论文

arxiv_ids (最多 50), fields

论文内容

工具

描述

关键参数

fetch_fulltext

从 LaTeX 源码中提取结果/实验

arxiv_id

fetch_repo

获取 GitHub 仓库 README + 文件树

arxiv_id

export_bibtex

导出论文的 BibTeX

arxiv_ids (最多 50)

get_paper_results

论文中的结构化基准测试结果

arxiv_id

基准测试与方法

工具

描述

关键参数

search_benchmarks

按名称查找数据集/基准测试

q, limit

get_leaderboard

数据集的 SOTA 排行榜

dataset, metric, limit

get_benchmark_stats

分数分布统计(最小值、最大值、中位数等)

dataset, metric

get_benchmark_timeline

随时间变化的原始分数数据点

dataset, metric

search_by_method

按技术名称搜索(LoRA, YOLO, DPO 等)

q, contribution_type, task_category, limit

compare_methods

跨基准测试的模型并排比较

models (2-10), dataset, metric

作者

工具

描述

关键参数

discover_authors

按主题或名称查找研究人员

q, field, limit

get_author

详细作者资料(h-index, 主题, 顶级论文)

author_id

get_author_papers

作者的所有论文(分页)

author_id, limit, page

研究

工具

描述

关键参数

get_research_landscape

主题的聚合景观统计

q, limit

deep_research

多轮研究综合(30-120秒)

topic, depth

refine_research

对已完成的研究报告进行后续提问

report_id, question, date_from, date_to

实用工具

工具

描述

关键参数

check_connection

验证 API 密钥,显示计划和使用情况

—

创新性评分

每篇论文都有一个从 0.0 到 1.0 的 llm_novelty_score:

范围

含义

示例

0.7+

范式转移或广泛的 SOTA

改变该领域的新架构

0.5-0.7

具有显著结果的新方法

具有明显增益的新训练技术

0.3-0.5

增量改进

将已知方法应用于新领域

<0.3

综述、数据集或微小扩展

文献综述、基准测试发布

在 search_papers 中使用 novelty_min: 0.5 来过滤真正创新的工作。

速率限制

端点

限制

check_connection

60/分钟

search_papers

30/分钟

get_paper

60/分钟

find_similar

20/分钟

get_citations

30/分钟

whats_trending

30/分钟

fetch_fulltext

10/分钟

batch_lookup

20/分钟

fetch_repo

10/分钟

export_bibtex

20/分钟

deep_research

5/分钟

refine_research

5/分钟

search_benchmarks

30/分钟

get_leaderboard

30/分钟

get_benchmark_stats

30/分钟

get_benchmark_timeline

30/分钟

search_by_method

30/分钟

compare_methods

20/分钟

discover_authors

20/分钟

get_author

60/分钟

get_author_papers

30/分钟

get_research_landscape

10/分钟

get_paper_results

30/分钟

响应包含 X-RateLimit-Limit、X-RateLimit-Remaining 和 X-RateLimit-Reset 标头。

响应示例

带有 q: "attention mechanism" 的 search_papers 返回:

{
  "papers": [
    {
      "arxiv_id": "2401.04088",
      "title": "Attention Is All You Need (But Not All You Get)",
      "authors": ["A. Researcher", "B. Scientist"],
      "year": 2024,
      "categories": ["cs.LG", "cs.AI"],
      "primary_category": "cs.LG",
      "arxiv_url": "https://arxiv.org/abs/2401.04088",
      "has_code": true,
      "github_url": "https://github.com/example/repo",
      "citation_count": 42,
      "rank_score": 0.73,
      "llm_summary": "Proposes a sparse attention variant that reduces compute by 60% while matching dense attention accuracy on 5 benchmarks.",
      "llm_novelty_score": 0.55
    }
  ],
  "total": 1847,
  "page": 1,
  "limit": 20,
  "next_cursor": "eyJzIjogMC43MywgImlkIjogIjI0MDEuMDQwODgifQ=="
}

将 next_cursor 传回以获取下一页(键集分页 — 对于大型结果集比页码更稳定)。

验证安装

设置完成后,让您的 AI 助手运行 check_connection。您应该看到:

{
  "status": "ok",
  "plan": "free",
  "key_name": "my-key",
  "usage_today": 0
}

环境变量

变量

必需

默认

描述

SF_API_KEY

否

—

您的 Scholar Feed API 密钥(以 sf_ 开头)。如果没有它,则以匿名模式运行(每天 100 次调用)。

SF_API_BASE_URL

否

生产 URL

覆盖 API 基础 URL

开发

npm install
npm run build      # Build to build/
npm run dev        # Watch mode
npm run typecheck  # Type check without emitting
npm test           # Run tests

贡献

请参阅 CONTRIBUTING.md 获取指南。

故障排除

“Authentication failed: your SF_API_KEY is invalid” 密钥可能已被撤销。请在 scholarfeed.org/settings 生成一个新密钥。或者删除密钥以使用匿名模式。

“Rate limit exceeded” 或 “Anonymous daily limit exceeded” 匿名模式每天允许 100 次调用。在 scholarfeed.org/settings 获取免费 API 密钥,每天可进行 500 次调用。

工具调用超时或静默失败 确保已安装 Node.js 18+ (node --version)。旧版本缺少原生的 fetch API。

过时的 npx 缓存 如果您在更新后仍停留在旧版本:npx --yes scholar-feed-mcp@latest

Windows: “command not found” 在您的 MCP 配置中使用 "command": "cmd" 和 "args": ["/c", "npx", "-y", "scholar-feed-mcp"]。

许可证

MIT

Available Tools

25 tools
add_to_collectionAdd to CollectionAInspect

Add a paper to a collection, addressed by collection_id OR collection_name (get-or-create by name — no need to look up an id first). Nest with "/": collection_name "AgentOPA/Formal" files the paper under an "AgentOPA" folder. MUTATES: also auto-saves the paper to the library. Idempotent (adding a paper already in the collection is a no-op). Requires SF_API_KEY.

Inputs: arxiv_id (required), collection_name, collection_id. Returns: ok, message, action, arxiv_id, +2 more

ask_libraryAsk LibraryA
Read-only
Inspect

Answer a question using ONLY the papers you've saved — a synthesis over your library (or one collection) with inline [arXiv-ID] citations. The inverse of find_gaps (which finds important work you're MISSING): ask_library reasons over what you HAVE. Optionally scope to one collection (collection_name OR collection_id); omit both to use your whole library. Read-only. Requires SF_API_KEY (it reads your saved set). Free accounts get 1 question/month; Pro raises this to 200/day.

Inputs: question (required), collection_name, collection_id, limit. Returns: answer, citations, papers, ok, +1 more

check_watchesCheck WatchesA
Read-only
Inspect

Pull new matching papers since the last digest delivery, in the same shape as search_papers results. Optionally scope to one watch by watch_name OR watch_id; omit both for all watches. Read-only and idempotent — does NOT advance any watermark (only digest delivery does), so it is safe to call repeatedly (no mark-on-read). This is the in-session 'anything new on my watches?' pull. Requires SF_API_KEY.

Inputs: watch_name, watch_id, limit. Returns: papers, total, page, limit, +8 more

co_author_graphCo-Author GraphA
Read-only
Inspect

Find the co-authorship neighborhood of one or more authors. Given a list of author_ids, returns edges {from, to, papers_count, last_collab_year} where 'from' is one of the input authors and 'to' is any co-author appearing on a shared paper within the window. Use for AC reviewer triage (find conflicts), disambiguating researchers (who do they actually work with?), or expanding an author seed into a research community. window_years defaults to 10. Result is capped at 500 edges, sorted by papers_count DESC.

Inputs: author_ids (required), window_years. Returns: queried_author_ids, window_years, edge_count, edges

create_collectionCreate CollectionAInspect

Create a new named collection. MUTATES. If a collection with that name already exists, returns the existing one (get-or-create — never errors on duplicate). Use "/" to nest under a folder, e.g. "AgentOPA/Formal" — the folder is derived from the name, so there is no parent to create first. Requires SF_API_KEY.

Inputs: name (required). Returns: ok, message, action, arxiv_id, +2 more

create_watchCreate WatchAInspect

Create a standing watch — evaluated daily against newly-indexed papers, surfacing new matches via the email digest and via check_watches. MUTATES. Get-or-create by name (re-creating with an existing name returns it unchanged — never errors on duplicate). TWO forms: (1) the v2 STRUCTURED filter via criteria (collections/authors/categories/text/has_code/min_novelty/similar, AND-composed) — the composable, agent-tunable form, recommended; tune it with preview_watch first, and edit later with update_watch. Structured watches rank by 'rising' (forecasted breakout impact) by default, and tighten with min_impact_pct for an anti-noise watch that surfaces only the breakout papers in your niche. (2) a single legacy seed selector (q OR collection_name OR collection_id OR anchor_paper_id); if criteria is given it takes precedence. Requires SF_API_KEY.

Inputs: name (required), novelty_min, q, collection_name, +7 more. Returns: ok, message, action, arxiv_id, +2 more

delete_watchDelete WatchA
Destructive
Inspect

Delete a watch, addressed by watch_id OR name. MUTATES. Idempotent: deleting a non-existent watch is a no-op (no error). To change a watch in place (rename / novelty_min / retarget criteria) use update_watch instead of delete-and-recreate. Requires SF_API_KEY.

Inputs: name, watch_id. Returns: ok, message, action, arxiv_id, +2 more

embed_textEmbed TextA
Read-only
Inspect

Embed a text string into a 768-dim Gemini Flash vector. Use for HyDE-style retrieval: (1) write a hypothetical short paper that would perfectly answer the user's query, (2) embed it with task_type='RETRIEVAL_DOCUMENT' (default — matches the corpus embedding side), (3) pass the resulting embedding back through search-style tools to find real papers nearest to the hypothetical. task_type='RETRIEVAL_QUERY' matches the query side and is useful for direct user-query embedding without HyDE. Pro-only — requires an SF_API_KEY on a Pro account; anonymous and free callers get a 403 pro_required. Cost: ~$0.0001/call; rate-limited at 30/minute per API key.

Inputs: text (required), task_type. Returns: embedding, model, task_type, dimensions, +1 more

fetch_fulltextFetch Full TextA
Read-only
Inspect

Extract paper content from an arXiv paper's LaTeX source. Two modes: 'results' (default) returns 800 chars of results/experiments + 3 table captions. 'all' returns full paper sections (abstract, introduction, related work, method, results, conclusion) at up to 3000 chars each + 5 table captions. ~62% of arXiv papers have LaTeX source. May take a few seconds.

Inputs: arxiv_id (required), sections. Returns: source, arxiv_id, results_text, sections, +1 more

find_authorFind AuthorA
Read-only
Inspect

Two-mode author tool — replaces discover_authors and get_author. Provide exactly one of q or id. Q-MODE (q=...): search for researchers by topic or name — uses embedding similarity for topics ('efficient LLM inference'), fuzzy matching for names ('Yann LeCun'). Returns a list of matching authors with author_id, name, h_index, total_papers, primary_field, research_topics. ID-MODE (id=...): look up a single author profile by author_id (obtained from a previous q-mode call or from co_author_graph results). Returns h-index, total citations, global rank, primary field, novelty score distribution, research topics, code/venue scores, years active, and their top 10 papers by rank score.

Inputs: q, id, field, limit. Returns: query, search_type, total, authors, +9 more

find_gapsFind Research GapsA
Read-only
Inspect

Find important work you HAVEN'T saved, for a collection or topic — a 'what am I missing?' analysis. Returns two buckets: foundational_gaps (canonical citation-graph anchors in the niche, not in your library) and frontier_gaps (recent high-novelty work in the niche, not yet saved). Provide exactly one seed: collection_name OR collection_id OR topic. The backend derives the niche, runs lineage + recent-novelty search, and subtracts your saved set. Read-only. Requires SF_API_KEY (it needs your library to subtract) and is a Pro feature — free accounts receive an upgrade prompt.

Inputs: collection_name, collection_id, topic, scope, +1 more. Returns: foundational_gaps, frontier_gaps, ok, message

get_citationsGet CitationsA
Read-only
Inspect

Get the citation graph for a paper, sorted by citing-paper rank_score (highest-impact first). 'citing' = outgoing references this paper cites; 'cited_by' = incoming citations from other papers. Default response is a lean 12-field shape per paper — pass verbose=true for the full 28-field shape.

Inputs: arxiv_id (required), direction, limit, fields, +2 more. Returns: papers, total, page, limit, +8 more

get_field_orientationGet Field OrientationA
Read-only
Inspect

Returns CANDIDATE FOUNDATIONAL PAPERS for a research topic — cheap retrieval only, no synthesis. Ranks papers by a blend of citation count (0.6 weight, captures importance) and semantic similarity to your topic (0.4 weight). Use this to bootstrap a literature survey or get a fast sense of the landscape. For a synthesized orientation report (key concepts, open problems, reading order), use the /field-guide skill which calls this tool internally. Does not require a Pro API key — no LLM calls are made.

Inputs: topic (required), limit. Returns: papers, total, page, limit, +8 more

get_foundational_lineageGet Foundational LineageA
Read-only
Inspect

Returns the FOUNDATIONAL WORK FOR A PAPER'S NICHE via the citation graph — the relative question ('what is foundational for THIS paper's specific sub-field', often itself only modestly cited) rather than the obvious global landmarks. Anchors on the paper, takes its embedding neighbourhood as the niche, and ranks what the niche cites into three tiers: niche_roots (the niche-specific foundations, ranked by how specifically the neighbourhood builds on them — surfaces canonical anchors that semantic search misses), field_level (broader secondary foundations), and discipline (universal landmarks like Attention Is All You Need, collapsed out of the way). Each paper carries cited_by_in_niche evidence so the claim is grounded, not asserted. Use this to trace prior art / lineage for a paper, or to find the canonical methods a niche is built on. Complements get_field_orientation (which is topic-anchored and retrieval-only). No Pro key and no LLM calls required.

Inputs: anchor_paper_id (required), scope, generality_ceiling, limit. Returns: anchor, scope, niche_size, tiers, +4 more

get_paperGet PaperA
Read-only
Inspect

Get full details for one or more papers by arXiv ID. Pass a single-element array for one paper; pass multiple IDs to batch-fetch up to 50 papers in one call (replaces the removed batch_lookup tool). Pass format='bibtex' to get a .bib citation entry (replaces the removed export_bibtex tool — bibtex is single-paper only; for multi-paper bibtex, call repeatedly). Default returns a lean 14-field shape (arxiv_id, title, authors, year, categories, has_code, github_url, citation_count, venue_name, llm_summary, llm_significance, llm_novelty_score, impact_pct, impact_tier — where impact_pct is the ML-forecast per-category impact percentile 0-100 and impact_tier its A+/A/B/C/D grade; both NULL on older papers outside the recent scoring window). Pass verbose=true for the full shape with structured extraction (method_name, contribution_type, task_category, datasets, baselines) and institution_tags. Use fields='arxiv_id,title,abstract' to select an exact subset, or fetch_fulltext with sections='all' for the full paper.

Inputs: arxiv_ids (required), format, fields, verbose. Returns: papers, total, page, limit, +13 more

like_paperLike PaperAInspect

Like a paper — a 'more like this' calibration signal that tunes the user's For You feed toward similar work. INSERT-only and idempotent (liking twice is a no-op, never un-likes). Distinct from save_paper: like expresses taste for ranking; save bookmarks for later reading. Requires SF_API_KEY.

Inputs: arxiv_id (required). Returns: ok, message, action, arxiv_id, +2 more

list_collectionsList CollectionsA
Read-only
Inspect

List the authenticated user's collections (named groups of saved papers) with paper counts. Read-only. Use before add_to_collection to see existing collections. Requires SF_API_KEY.

Inputs: no named parameters. Returns: collections, ok, message

list_libraryList LibraryA
Read-only
Inspect

List the authenticated user's saved papers (their library), newest first. Read-only. Use this to review a reading list or to see what's already saved before saving more. Requires SF_API_KEY.

Inputs: limit, page. Returns: papers, total, page, limit, +8 more

list_watchesList WatchesA
Read-only
Inspect

List the authenticated user's watches with name, a one-line definition summary, last_evaluated_at, and pending_hits (count of new matches since the last digest delivery). Read-only. Use before create_watch to see what's already tracked. Requires SF_API_KEY.

Inputs: no named parameters. Returns: watches, ok, message

preview_watchPreview WatchA
Read-only
Inspect

Dry-run a structured filter over recent papers WITHOUT creating a watch — the tuning loop. Returns {window_days, needs_similarity, match_count, sample} so you can iterate (add a category, raise min_novelty, switch the collection relation) before saving with create_watch. Structured watches rank by 'rising' (forecasted breakout impact) by default, and tighten with min_impact_pct for an anti-noise watch that surfaces only the breakout papers in your niche. NOTE: for a similarity filter, match_count is capped at 200 (the cosine fetch window) and so saturates at 200 on broad/hot topics — tune by the sample scores and narrow with categories/min_novelty (or a higher similar floor) rather than relying on match_count alone. Read-only. Requires SF_API_KEY.

Inputs: criteria (required), recency_days. Returns: window_days, needs_similarity, match_count, sample, +2 more

remove_from_collectionRemove from CollectionA
Destructive
Inspect

Remove a paper from a collection, addressed by collection_id OR collection_name. MUTATES (the paper stays in your library; it's only removed from this collection). Idempotent. Requires SF_API_KEY.

Inputs: arxiv_id (required), collection_name, collection_id. Returns: ok, message, action, arxiv_id, +2 more

save_paperSave PaperAInspect

Save a paper to the authenticated user's Scholar Feed library (bookmark). MUTATES the library and feeds the user's personalization — saved papers are the strongest signal in the For You feed and the email digest. Idempotent: calling it again on an already-saved paper leaves it saved. Requires SF_API_KEY. To file it into a named collection in one step, use add_to_collection (that also saves).

Inputs: arxiv_id (required). Returns: ok, message, action, arxiv_id, +2 more

search_papersSearch PapersA
Read-only
Inspect

Search Scholar Feed's 600k+ CS/AI/ML paper corpus. Defaults to semantic (embedding) search — finds conceptually related papers even when the user's wording doesn't match the paper's title/abstract. Pass mode='keyword' for exact-string full-text search. CAVEAT: semantic search often misses old high-citation CANONICAL papers (e.g. foundational anchors like H2O for KV eviction, GRIT for unified embedding+generation) because the ranker prefers recent stylistically-matched papers. If you're hunting the canonical anchor for an area, parse the top-5 result abstracts for baseline mentions ('we compare against X, Y, Z'), then look the most-mentioned name up directly. Returns papers with LLM-generated summaries, novelty scores, and structured extraction data. Default response is a lean 14-field shape (arxiv_id, title, authors, year, categories, has_code, github_url, citation_count, venue_name, llm_summary, llm_significance, llm_novelty_score, impact_pct, impact_tier) — pass verbose=true or fields=... for the full shape with method/task/dataset extraction. RANKING BY IMPACT — two different notions, don't confuse them: (1) PROVEN impact = citations. For 'the important/seminal papers on topic X', pass sort='impactful' (most-cited among the relevant) or sort='balanced' (relevant AND well-cited). This is the right tool for established/foundational work. (2) FORECAST impact = impact_pct (0-100), an ML per-category percentile of PREDICTED citations, only computed for the last ~90 days; impact_tier is its A+/A/B/C/D grade. For 'what's rising/new in X' pass sort='trending' or filter impact_min=N — but NOTE impact_pct is NULL on everything older than ~90 days, so impact_min DROPS all established/canonical papers (it is NOT a way to find the influential papers in a niche — use sort='impactful' for that). Both impact notions are distinct from llm_novelty_score (new-idea-ness, an orthogonal filter). (3) ADOPTION impact = GitHub traction. Pass sort='community' to rank by real-world engineering adoption (stars + star-velocity) — the papers practitioners are actually running/building on, independent of citations or recency. Filter on it with min_stars=N (minimum GitHub stars) and has_code=true (only papers with a code release); has_code/min_stars surface RUNNABLE/ADOPTED work, the engineering counterpart to citations. github_url_exists=true is the stricter has_code (requires a linked repo). Supports filtering by category, novelty, recency, method, task, dataset, and contribution type — plus min_citations (minimum PROVEN citations, keeps established papers unlike the ~90-day impact_min) and an explicit date window via published_after / published_before ('YYYY-MM-DD', vs days' rolling lookback). v3 ABSORPTIONS: pass sort='trending' to rank by rising/forecast impact (impact_pct); pass anchor_paper_id to replicate find_similar (q is ignored in anchor mode, results carry similarity_score); pass scope_to_citations_of to restrict search to a paper's citation graph (replaces find_citations_about).

Inputs: q, sort, anchor_paper_id, scope_to_citations_of, +23 more. Returns: papers, total, page, limit, +8 more

unsave_paperUnsave PaperA
Destructive
Inspect

Remove a paper from the authenticated user's Scholar Feed library. MUTATES the library. Idempotent: removing a paper that isn't saved leaves it unsaved. Note: the saved library is a superset of all collections, so un-saving a paper ALSO removes it from every collection it was in. To keep it filed in a collection, use remove_from_collection instead (that leaves the paper saved). Requires SF_API_KEY.

Inputs: arxiv_id (required). Returns: ok, message, action, arxiv_id, +2 more

update_watchUpdate WatchAInspect

Update an existing watch in place — rename, change novelty_min, or RETARGET its structured filter criteria. MUTATES. Address by watch_id OR name. Changing criteria replaces the definition and clears the watch's pending hits (so stale matches don't deliver); the next daily eval repopulates. Structured watches rank by 'rising' (forecasted breakout impact) by default, and tighten with min_impact_pct for an anti-noise watch that surfaces only the breakout papers in your niche. Tune the new criteria with preview_watch first. Requires SF_API_KEY.

Inputs: name, watch_id, new_name, novelty_min, +2 more. Returns: ok, message, action, arxiv_id, +2 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.5/5.0

    Scored across 25 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes, but some overlap exists between search and discovery tools like ask_library, find_gaps, get_field_orientation, and get_foundational_lineage. However, detailed descriptions help differentiate them.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with underscores. Even compound names like get_foundational_lineage adhere to this pattern, making it predictable and easy for agents to understand.

    Tool Count4/5

    25 tools is slightly above the typical 3-15 range, but the server covers a broad domain (library management, search, analysis, watches, collections, author discovery, etc.), justifying the count. It is not excessive.

    Completeness5/5

    The tool set provides comprehensive coverage: CRUD operations for libraries, collections, watches, and full analysis capabilities (citation graphs, gap analysis, author discovery, embedding). No obvious gaps exist for the intended purpose.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI-powered academic paper discovery, search, and analysis from arXiv with advanced features like semantic search, citation network analysis, and multi-format exports (BibTeX, RIS, JSON, CSV). Provides intelligent research assistance through specialized AI prompts for summarization, trend tracking, and literature review automation.
      17
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables LLMs to search, analyze, and summarize academic research papers in real-time from arXiv, Semantic Scholar, and PubMed. Provides automatic deduplication, citation analysis, and BibTeX generation across multiple research databases.
      22 npm
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      Enables real-time tracking of AI/LLM research progress by searching and aggregating content from arXiv, GitHub, Hugging Face, and Papers with Code. Supports intelligent search, automated daily/weekly research summaries, and covers 15+ AI research areas with smart caching.
      8
      MIT
    • F
      license
      Not graded
      quality
      B
      maintenance
      Enables researchers to search ArXiv papers, extract key insights (problems, methods, results) from abstracts, and perform ML-powered analysis including topic modeling, trend visualization, and author collaboration networks.
      -