science-ai-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SCIENCE_AI_API_KEY | Yes | Your saij_… token for authentication | |
| SCIENCE_AI_BASE_URL | No | Base URL for Science AI API, default: https://scienceaijournal.com | https://scienceaijournal.com |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| start_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_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 |
| check_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. |
| ai_review_paperA | 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. |
| recommend_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. |
| pre_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. |
| find_research_gapsA | 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. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
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.