science-ai-mcp-server
This MCP server lets an MCP-enabled assistant call Science AI Journal research tools using a saij_... API key, with free and credit-metered capabilities.
Search literature for free with
find_research_gaps: get a field overview, closest papers from a 7.9M-paper library, and most-cited/most-recent work; it does not return unlocked gaps (gaps: [],gapsLocked: true).Check for duplicate publication for free with
check_duplicate_publicationacross CrossRef, PubMed, arXiv, bioRxiv, medRxiv, Europe PMC, Unpaywall, and a local library.Run one specialist AI reviewer agent with
ai_review_paperon a prepared manuscript prompt; returns score, verdict, summary, strengths, concerns, detailed review, confidence, and author questions for 4 credits.Estimate Tier 1/2/3 acceptance probabilities with
pre_check_paperfrom title/abstract/full text/keywords; costs 15 credits when available via MCP.Get ranked target-journal recommendations with
recommend_journalsfrom a 17,500-venue index, including grade, match %, tier, quartile, access, citedness, predatory flags, responding times, and similar papers; costs 15 credits when available.Start and poll Article Writer pipeline jobs for an existing WriterSession via
start_writer_pipelineandget_writer_pipeline_status; these are private beta and currently return 404 for API-key calls.
Pre-Check and Journal Finder may answer “not available through MCP yet” until the server opens those endpoints after 0.1.4; such calls are not charged.
Queried by the duplicate-publication check: searches arXiv by paper title with optional abstract confirmation to detect existing preprint matches and distinguish preprints from journal publications.
Queried by the duplicate-publication check: searches PubMed by paper title, using an abstract when provided to confirm close matches, to determine whether a manuscript has already been published.
science-ai-mcp-server
Model Context Protocol server for Science AI Journal research tools. Run a specialist AI Review agent, the research-gap literature search, the duplicate-publication check, Pre-Check and the Journal Finder from inside Claude Desktop, Claude Code, Cursor, Cline, or any MCP-enabled client — without leaving your assistant. Pre-Check and the Journal Finder need version 0.1.4 or later and open on the server after that release (see Tools).
Full docs: https://scienceaijournal.com/developers/mcp
Quick start (≈ 2 minutes)
Generate an API key at https://scienceaijournal.com/settings?section=api-keys (free account required). Copy the
saij_…token — you only see it once.Add this block to your Claude Desktop config file:
{ "mcpServers": { "science-ai-journal": { "command": "npx", "args": ["-y", "science-ai-mcp-server"], "env": { "SCIENCE_AI_API_KEY": "saij_…paste your key…" } } } }Config file locations:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.jsonLinux:
~/.config/Claude/claude_desktop_config.json
Restart Claude Desktop. The
science-ai-journalserver appears in the 🔌 tool list.
The same config works in Cursor (~/.cursor/mcp.json), Cline (via the VS Code extension panel), and Continue (anywhere that supports an mcpServers object). In Claude Code, one command adds it:
claude mcp add science-ai-journal --env SCIENCE_AI_API_KEY=saij_… -- npx -y science-ai-mcp-serverCalling the API from your own code instead of an assistant? The endpoints, prices and error shapes are at https://scienceaijournal.com/developers/api.
Related MCP server: Scholar Feed MCP Server
Tools
Live today
Tool | What it does | Cost |
| Free literature search: field overview, closest papers from a 7.9M-paper library, most-cited and most-recent work | Free search |
| Cross-reference against CrossRef, PubMed, arXiv, bioRxiv, medRxiv, Europe PMC, Unpaywall and a 7.9M-paper library | Free |
| One specialist reviewer agent on a prepared manuscript prompt | 4 credits per call |
From 0.1.4: Pre-Check and the Journal Finder
Both run on the local library and index, with no LLM call, and both are metered: a call is charged to the API key's account, exactly once.
Tool | What it does | Cost |
| Tier 1, 2 and 3 acceptance probabilities from title + abstract, the detected field, and how many similar papers the estimate rests on (local 7.9M-paper library) | 15 credits per call |
| Ranked target journals from a 17,500-venue index: grade, tier, quartile, access, 2-year mean citedness, responding times where reported, predatory-journal flags | 15 credits per call |
Availability. The server opens these two endpoints to API keys in the server release that follows the publication of 0.1.4; the current status is on https://scienceaijournal.com/developers/mcp. Until then a call answers "not available through MCP yet" and nothing is charged; the same tools run in the web app — Pre-Check and the Journal Finder. Versions before 0.1.4 cannot use them at all: the server answers those with HTTP 426 and charges nothing.
What is never charged. A wrong or revoked key (401), an account without enough credits (402, the message names the price and the balance), a key limited to other tools (401, the same answer as a wrong key), a text that does not look like English (422), a rate-limited call (429) and a busy library index (503) are all refused before the charge. A repeat of a Pre-Check the account ran recently returns the saved result's link instead of charging again (
force: trueruns it again). A Journal Finder call that matches no journal is refunded.Non-English text. The library and the journal index are English-language. Pass
acknowledgeLowEnglish: trueto run such a text anyway; that run is charged as usual and the result is rough.How to read the results. Pre-Check's probabilities are estimates from similar published papers; the Journal Finder's list is a ranked shortlist of candidates to check against each journal's aims and scope. Neither is a prediction that a given journal will accept the paper.
One call, one purchase. An API-key call is priced on its own. The web app's bundles (for example the journal list that comes with a Pre-Check run there) apply to signed-in browser sessions, not to API keys.
Private beta
Tool | What it does | Cost |
| Drive the Article Writer pipeline from outside the wizard | Private beta |
The two writer tools get HTTP 404 while the Article Writer is in private beta: writer access is checked against a signed-in browser session, which an API key does not carry — so this holds for every key, including those of accounts with writer access. Nothing is charged.
Research gaps:
find_research_gapsis the free search, so it returnsgaps: []andgapsLocked: true. The gaps come from unlocking the topic at https://scienceaijournal.com/research-gaps — one charge of 50 credits that also includes the filled comparison table, a research proposal and one Pro Report run.Credits: a free account starts with 25 welcome credits; after that, credits come in one-time packs of 50 that never expire, with no subscription. A call the account can't afford returns HTTP 402 and charges nothing.
What changed in each version: CHANGELOG.md.
Configuration
Env var | Default | Purpose |
| required | Your |
|
| Override for self-hosted or staging environments |
Troubleshooting
Tools don't appear after editing config: fully quit the host app (not just close the window) and reopen.
"Not available through MCP yet" from
pre_check_paperorrecommend_journals: the server has not opened that endpoint to API keys yet (see above). Every key gets this answer there, it says nothing about your key, and nothing is charged. Use the web app meanwhile.426 from
pre_check_paperorrecommend_journals: the MCP client is still running a package older than 0.1.4. Restart it sonpx -y science-ai-mcp-server@lateststarts the current one. Nothing is charged.401 "missing, revoked, or expired, or limited to other tools": the key was wrong, revoked or expired, or it was minted for other tools only. Mint a fresh one at Settings → API Keys. Nothing is charged.
402 insufficient credits: nothing was charged. Top up at https://scienceaijournal.com/pricing; the free tools keep working.
404 from the writer tools: the Article Writer is in private beta, and during the beta every API key gets a 404 there.
429 rate limit on
find_research_gaps: you hit the 10-per-hour IP quota. Wait an hour.429 on any other tool: each API key has a per-minute and a per-day limit across all tools. The error says when to retry; a refused call is not charged.
502 or 504 from a metered tool: the answer was lost on the way, but the run may have finished and been charged. A finished run is saved in the account's history in the web app; look there before calling again.
npxcan't resolve the package: ensure Node ≥ 20 and that your npm registry isn't set to a private mirror without this package yet (npm config set registry https://registry.npmjs.org/).
License
MIT
Available Tools
7 toolsai_review_paperAI Multi-Agent Peer Review (single agent)A
Run one specialist reviewer agent (methodology, formulas, originality, literature, reproducibility, clarity or figures) on a prepared agent prompt and return the structured editorial decision: score (1-10), verdict (Accept / Minor Revision / Major Revision / Reject), summary, strengths, concerns, detailed multi-section review, confidence band, and questions for the authors. Costs 4 Science AI Journal credits per call (one call = one agent), charged to the API key's account; an account without enough credits gets HTTP 402 and is not charged. For a whole manuscript, AI Review in the web app at scienceaijournal.com/ai-review runs all 9 specialist agents plus a synthesis in one pass.
Inputs: prompt (required), agentType.
check_duplicate_publicationCheck Duplicate PublicationA
Pre-submission duplicate-publication check: has this paper already been published? Checks 7 external sources — CrossRef, PubMed, arXiv, bioRxiv, medRxiv and Europe PMC by title (an abstract, when given, is used to confirm close matches), and Unpaywall by DOI (so only when you pass one) — plus a 7.9M-paper local library, all queried in parallel with a 12-second cap per source. Returns a status — likely_published, preprint_found (the match is a preprint, not a journal article), uncertain (a possible match), not_found, or unable_to_check (no source could be reached) — with a message and, on a match, a link and a confidence score where the source gives one. A not_found that could not reach some sources says which. Free — spends no credits. Rate-limited per account (an API key counts against its account); a 429 says when to retry. Use before submission to catch an accidental duplicate or to see whether a preprint has since been formally published.
Inputs: title (required), doi, abstract.
find_research_gapsResearch Gaps: Free Literature SearchA
Free literature search on a research topic — spends no credits and makes no LLM call; rate-limited to 10 searches/hour per IP. Returns a field overview and the papers the search found: the closest matches from a 7.9M-paper local library, plus the most-cited and most-recent work on the topic. It does NOT return research gaps: the response carries gaps: [] and gapsLocked: true. Gaps come from unlocking the topic in the web app at scienceaijournal.com/research-gaps — one charge of 50 credits that also includes the filled comparison table, a research proposal and one Pro Report run. Use for early-stage literature discovery and proposal scoping.
Inputs: query (required), field, departmentId.
get_writer_pipeline_statusGet Article Writer Pipeline StatusA
Not available with an API key during the Article Writer's private beta (the server answers every API-key call with 404). Once the writer is public: return the latest writer-pipeline job for a (sessionId, section). Use after start_writer_pipeline and poll every 5-10 seconds. Terminal statuses: 'done', 'failed', 'aborted'.
Inputs: sessionId (required), section.
pre_check_paperPre-Check PaperA
Pre-submission scoring of an academic paper from its title and abstract. Returns Tier 1, Tier 2 and Tier 3 acceptance probabilities, the detected research field, and how much evidence the estimate rests on (how many similar papers were retrieved, and whether the result is provisional), scored against a local 7.9M-paper library via FTS5 BM25 with no LLM call. Use this when the user wants a fast readiness check before submitting, or which tier of journal to target. Costs 15 Science AI Journal credits per call, charged to the API key's account; an account without enough credits gets HTTP 402 and is not charged, and a repeat of a recent run returns the saved result's link without charging. The probabilities are estimates from similar published papers, not a decision: present them as a rough guide. Calls are rate-limited per API key; a refused call (401, 402, 422, 429, 503) is not charged and the error says what to do. If the server answers that this tool is not available through MCP yet, nothing was charged: run Pre-Check in the web app at scienceaijournal.com/scorer instead.
Inputs: title (required), abstract (required), force, fullText, +4 more.
recommend_journalsRecommend Target JournalsA
Recommend ranked target journals for a paper from a 17,500-venue index. Each result includes a letter grade (A-F), a match percentage, tier (1-3), Scimago quartile, publisher, access (open, hybrid or subscription), OpenAlex 2-year mean citedness (an open proxy, not the Journal Impact Factor), a predatory-journal flag, responding times where the venue reports them, and up to 2 similar papers from the venue that our library holds. Runs on FTS5 + topic profiles, no LLM call. Costs 15 Science AI Journal credits per call, charged to the API key's account; an account without enough credits gets HTTP 402 and is not charged, and a call that matches no journal is refunded. The list is a ranked shortlist of candidates to check against each journal's aims and scope, not a prediction of acceptance: present it that way. Calls are rate-limited per API key; a refused call (401, 402, 403, 422, 429) is not charged and the error says what to do. If the server answers that this tool is not available through MCP yet, nothing was charged: use the Journal Finder in the web app at scienceaijournal.com/journal-recommender instead. Use when the user asks 'where should I submit this paper' or wants to compare target venues before deciding.
Inputs: title (required), abstract (required), sort, field, +6 more.
start_writer_pipelineStart Article Writer PipelineA
Not available with an API key during the Article Writer's private beta: the server answers every API-key call to this tool with 404. Once the writer is public: enqueue a writer-pipeline job for an existing WriterSession. Returns immediately with a jobId; the orchestrator-worker claims it within ~5 seconds. Default section is step_7_5 — the auto-chain that replaces the three buttons in Step 7.5. Use get_writer_pipeline_status to poll until status is 'done', 'failed', or 'aborted'. Writer steps are billed in Science AI Journal credits.
Inputs: sessionId (required), force, section, language.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Most tools target recognizably different stages (pre-check scoring, duplicate check, journal recommendation, single-agent review), but find_research_gaps is actively misleading: it does not return gaps and ships gaps: [] plus gapsLocked: true, so an agent must read the description carefully to avoid picking it for the wrong job. The pair of writer tools also only make sense together and are both unusable, adding noise to selection.
The set is consistently snake_case with verb_noun form: pre_check_paper, find_research_gaps, start_writer_pipeline, get_writer_pipeline_status, check_duplicate_publication, recommend_journals. The only deviation is ai_review_paper, which leads with a noun-ish token ('ai') rather than a clean verb, but it remains readable and predictable.
Seven tools is a well-scoped size for a pre-submission paper workflow, and each has a distinct role. Two of the seven (start_writer_pipeline, get_writer_pipeline_status) are hard-404 during the private beta, so the effective surface is smaller than advertised, but the count itself is reasonable.
The core pre-submission loop — tier estimate, journal shortlist, duplicate check, and single-agent review — is covered, but there are notable dead ends: research gaps (and the comparison table/proposal) can only be obtained by unlocking in the web app, and the entire Article Writer pipeline is unavailable via MCP. There is also no tool for revision/response-letter work or for running the full multi-agent review that the description points users to the web app for.
Maintenance
Related MCP Connectors
Paper search (free), literature review packs, hallucinated-citation checks, arXiv digests, citations
Check if references exist or were retracted, look up journal AI policies, and preview manuscripts.
Search arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools.
Check AI references against Crossref and DataCite. DOI/arXiv metadata checks, plus tool discovery.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables 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 npmMIT
- AlicenseAqualityBmaintenanceEnables searching and analyzing over 560,000 CS/AI/ML research papers with LLM-powered novelty scoring and summaries. Supports literature reviews, trend monitoring, benchmark tracking, and deep research sessions through 23 specialized tools.2585 npm14MIT

OpenArxofficial
AlicenseNot gradedqualityCmaintenanceOpen scientific knowledge MCP for AI agents. Three profiles: search (15 tools incl. find_evidence, compare_papers, explore_topic), publish (5 tools for direct submission with AI-assisted review), govern (20 tools for proposals, voting, methodology shaping).8Apache 2.0- FlicenseNot gradedqualityDmaintenanceAutomates literature review, research gap detection, and novelty evaluation for academic research, providing tools to search, summarize, find gaps, generate ideas, and evaluate novelty.-