This server provides academic research and publishing tools from Science AI Journal, accessible inside MCP-enabled AI assistants (e.g., Claude Desktop, Cursor, Cline).
Pre-Check Paper: Free, instant submission readiness check returning predicted publication tier (Tier 1–3 probabilities), detected research field, and confidence band — powered by a local 33,000-paper BM25 library with no LLM cost.
Check Duplicate Publication: Cross-references a paper's title/abstract against CrossRef, arXiv, medRxiv, bioRxiv, Unpaywall, and a 900k-paper library to detect duplicates or salami-slicing. Returns a status (likely_published, uncertain, or not_found) with a confidence score. Free.
Recommend Journals: Ranked journal recommendations from a ~1,200-venue index, including letter grade, match percentage, tier, publisher, open-access status, predatory-journal flag, and example similar papers. Free.
Find Research Gaps: Discovers research gaps and surfaces the most-cited and most-recent papers around a query, with LLM-derived cross-paper synthesis. Uses credits; rate-limited to 10 requests/hour.
AI Review Paper (HAKEM): Runs a specialist AI peer-review agent (methodology, language, figures, plagiarism, or literature) on a manuscript, returning a structured editorial decision with score (1–10), verdict, strengths, concerns, and author questions. Uses credits.
Start Article Writer Pipeline: Enqueues an Article Writer job for an existing WriterSession to auto-generate or refine paper sections (introduction, methodology, results, discussion, references, abstract, or a full chain). Returns a job ID immediately. Uses credits.
Get Article Writer Pipeline Status: Polls the status of a running Article Writer pipeline job until it reaches a terminal state (done, failed, or aborted).
Model Context Protocol server for Science AI Journal tools. Use Pre-Check, AI Review, Research Gaps, Journal Recommender, Duplicate Publication Checker, and the Article Writer from inside Claude Desktop, Cursor, Cline, or any MCP-enabled client — without leaving your assistant.
Full docs and screenshots: https://scienceaijournal.com/developers/mcp
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.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
Restart Claude Desktop. The science-ai-journal server 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).
Related MCP server: Scholar Feed MCP Server
Tool | What it does | Cost |
| Tier 1-5 acceptance probability from title + abstract (local FTS5, no LLM) | Free |
| Cross-reference against CrossRef + arXiv + medRxiv + bioRxiv + Unpaywall + a 900k-paper library | Free |
| Ranked target journals from a 1,214-venue index, with predatory-journal flags | Free |
| Synthesised gaps + most-cited + most-recent papers around your query | Credits |
| Single-agent AI peer-review pass on a prepared prompt | Credits |
| Drive the Article Writer pipeline from outside the wizard | Credits |
Env var | Default | Purpose |
| required | Your |
|
| Override for self-hosted or staging environments |
Tools don't appear after editing config: fully quit the host app (not just close the window) and reopen.
401 unauthorized when calling a tool: the key was wrong, revoked, or expired. Mint a fresh one at Settings → API Keys.
429 rate limit on find_research_gaps: you hit the 10-per-hour IP quota. Wait an hour.
npx can'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/).
MIT
Pre-submission duplicate-publication and salami-slicing check. Cross-references the title + abstract against CrossRef, arXiv, medRxiv, bioRxiv, Unpaywall, and a 900k-paper institutional library in ~30 seconds. Returns a status (likely_published, uncertain, or not_found) with a confidence score and message. Free. Use before submission to catch accidental duplicates or to confirm a preprint hasn't been formally published yet.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | Paper title (required). | |
| abstract | No | Paper abstract — improves match accuracy. | |
| doi | No | Known DOI for the paper, if any. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, the description fully discloses behavior: it cross-references title+abstract against six sources, returns specific fields (status, confidence, message), takes ~30 seconds, and is free. No destructive actions implied, and no contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no wasted words. The first sentence states purpose and sources, the second provides output and usage advice. Front-loaded with key information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description completely covers purpose, input significance, sources, timing, cost, return format, and usage context. No gaps identified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Parameter schema has 100% coverage with descriptions. The description adds value by explaining that abstract improves match accuracy and DOI is optional, going beyond the schema's basic field definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: a pre-submission duplicate-publication check. It specifies the verb 'check' and the resource 'duplicate publication', and distinguishes it from siblings like find_research_gaps or hakem_review_paper by focusing on cross-referencing against multiple databases.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use before submission to catch accidental duplicates or to confirm a preprint hasn't been formally published yet.' This provides clear when-to-use guidance. It does not mention when not to use or alternatives, but sibling tools do not overlap significantly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Surface research gaps + the most-cited and most-recent papers around a query. Returns cross-paper synthesis gaps first (LLM-derived, grounded in ≥ 2 papers), then catalogue-level single-paper gaps. Plus a field overview and ≤ 50 top-cited and ≤ 50 most-recent papers. Uses Science AI Journal credits; rate-limited to 10 requests/hour per IP. Use for early-stage research discovery, literature gap identification, and proposal scoping.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Research query (≥ 10 chars). Free-form prose or a title + abstract joined by newline. | |
| field | No | Optional field bias (e.g. 'computer_science', 'biology'). | |
| departmentId | No | Optional departmentId to enable methodology-alignment hints (boosts gaps whose text matches your discipline's KPI / question vocabulary). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses the tool's behavior: uses Science AI Journal credits, rate-limited to 10 requests/hour/IP, and describes the output composition comprehensively. This is thorough for a read-heavy research tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at four sentences, each carrying important information: purpose, outputs, usage constraints, and recommended use cases. No fluff or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite lacking an output schema, the description thoroughly explains what the tool returns: cross-paper synthesis gaps, single-paper gaps, field overview, up to 50 top-cited and 50 most-recent papers. This is complete for a research gap tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides descriptions for all three parameters (100% coverage), so the baseline is 3. The description does not add additional semantic details beyond what the schema offers; it simply references the query and field without elaborating.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: surfacing research gaps along with top-cited and most-recent papers. It details the outputs (cross-paper synthesis gaps, single-paper gaps, field overview, top papers) which distinguishes it from sibling tools that focus on different aspects like publication checking or writing pipeline.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit use cases: 'early-stage research discovery, literature gap identification, and proposal scoping.' It also mentions rate limits and credit usage, giving clear context for when to use. It does not explicitly state when not to use or compare to alternatives, but the context is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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'.
| Name | Required | Description | Default |
|---|---|---|---|
| sessionId | Yes | ||
| section | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It mentions terminal statuses but does not describe non-terminal states, the response structure, or error behavior (e.g., if no job exists). This leaves some gaps in behavioral understanding.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: first states the core function, second gives usage instructions and terminal statuses. Every word is purposeful, no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of an output schema, the description should clarify the response format. It only mentions terminal statuses but not how they are returned (e.g., as a status field). Also missing details on error handling or what a non-terminal response looks like, which is important for a polling tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description names the parameters 'sessionId' and 'section' but adds no meaning beyond what the input schema provides. The schema has 0% description coverage, so the description should compensate, but it only restates the parameter names and the enum values implicitly. It does not explain what 'section' represents or provide usage context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it "Return the latest writer-pipeline job for a (sessionId, section)." It specifies the verb 'Return', the resource 'latest writer-pipeline job', and the required parameters. This clearly distinguishes it from sibling tools like start_writer_pipeline and others.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly instructs to use after `start_writer_pipeline` and to poll every 5-10 seconds. It also lists terminal statuses, providing clear guidance on when to use and what to expect.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run one of the HAKEM specialist agents (methodology, language, figures, plagiarism, or literature) 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. Uses Science AI Journal credits. For the full 5-agent + synthesis flow, prefer the web UI at scienceaijournal.com/ai-review.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Prepared agent prompt — usually the manuscript text plus any agent-specific framing. The server wraps it in <manuscript> tags to defuse injection, prepends RAG examples if agentType is supplied, and runs the chosen Claude model. | |
| agentType | No | Which HAKEM specialist agent to run. Drives the calibration RAG corpus and the system prompt; defaults to a generic reviewer when omitted. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, the description discloses that the server wraps the prompt in <manuscript> tags, prepends RAG examples when agentType is supplied, runs the Claude model, consumes Science AI Journal credits, and returns a detailed structured output. This gives the agent a clear understanding of the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but not overly long; it contains no fluff. However, it could be slightly restructured for easier scanning, e.g., by separating output fields into a list. Still, every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the output fields and server behavior well, given the tool's complexity and lack of output schema. It might benefit from mentioning authentication requirements or potential error conditions, but it is sufficiently complete for correct agent invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for both parameters. The description adds valuable context: it specifies that the prompt should include manuscript text plus agent-specific framing, explains the server-side handling, and clarifies the meaning of agentType and its default behavior.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool runs a HAKEM specialist agent on a prepared prompt and returns a structured editorial decision with specific fields. It names the five agent types and explicitly contrasts with the full 5-agent flow available on the web UI, distinguishing it from sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains that this tool is for single-agent review and directs users to the web UI for the full multi-agent flow, providing a clear alternative. However, it does not outline when to use this tool versus other siblings like pre_check_paper, but the context is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run a free, zero-LLM-cost pre-submission scoring of an academic paper. Returns predicted publication tier (Tier 1, 2, or 3 probability), the detected research field, and a confidence band. Backed by a local 33,000-paper library via FTS5 BM25. Use this when the user wants a fast sanity-check on whether a paper is ready to submit, or which tier of journal to target. Sub-second response. Free.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | Paper title (required). | |
| abstract | Yes | Paper abstract (required). | |
| keywords | No | Optional author-supplied keywords; comma-separated. | |
| fullText | No | Optional full manuscript text. Pass when available; results are more accurate. | |
| abstractOnly | No | Set to false to score against fullText. Default true. Ignored when fullText is absent. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that the tool is zero-LLM-cost, free, sub-second response, and backed by a local library. This gives the agent confidence that it is a safe read-only operation without side effects, though it does not explicitly state no mutations occur.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: two sentences front-loading the purpose and usage. Every sentence adds value, with no redundant or vague phrasing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (5 parameters, no output schema, no annotations), the description covers the core functionality: what it returns (tier, field, confidence band) and when to use it. It lacks details on error handling or authentication, but for a simple scoring tool, it is adequately complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All 5 parameters have descriptions in the schema (100% coverage), so the schema already provides parameter semantics. The description adds only general context (e.g., returns probabilities, fast) but does not elaborate on parameter-specific details beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: run a pre-submission scoring of an academic paper, returning predicted tier, field, and confidence band. It uses specific verbs and resources, and the use of 'pre-check' differentiates it from siblings like 'check_duplicate_publication' and 'recommend_journals'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells when to use this tool: 'when the user wants a fast sanity-check on whether a paper is ready to submit, or which tier of journal to target.' It does not include when-not-to-use or alternatives, but the context is sufficient for an AI agent to decide.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recommend ranked target journals for a paper from a ~1,200-venue index. Each result includes a letter grade (A-F), a match percentage, tier (1-3), publisher, open-access status, 2-year mean citedness, predatory-journal flag, and 2-3 example similar papers that landed at that venue. Free — runs locally via FTS5 + topic-RAG, no LLM call. Use when the user asks 'where should I submit this paper' or wants to compare target venues before deciding.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | Paper title (required). | |
| abstract | Yes | Paper abstract (required, can be empty string). | |
| fullText | No | Optional full manuscript text for higher-signal matching. | |
| keywords | No | Optional author keywords; comma-separated. High-signal topic input. | |
| field | No | Detected research field for a topical boost (optional). | |
| filters | No | Optional filter object. excludePredatory drops Beall's-archive matches; openAccessOnly keeps only OA journals; minTier sets a Tier 1/2/3 floor. | |
| sort | No | Sort mode. "best" (default) maximises relevance; "fastest" prefers fast-decision venues; "highestIf" sorts by 2-year mean citedness; "mostAccepting" prefers higher published-volume venues. | |
| maxResults | No | How many recommendations to return. Default 10, cap 25. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses that it's free, runs locally via FTS5 + topic-RAG with no LLM call, and lists output fields. Missing details on error handling or side effects, but these are minor for a read-only tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with a clear front-loaded purpose and a concise list of output fields. Every word serves a purpose, no wasted text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite no output schema, the description details all output fields (grade, match %, tier, etc.). With 8 parameters including a nested filter, the description covers the tool's functionality comprehensively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with each parameter having a description. The description adds no additional meaning beyond summarizing the schema. Baseline of 3 is appropriate as it repeats but does not enrich.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Recommend ranked target journals for a paper from a ~1,200-venue index,' specifying the verb, resource, and scope. This directly differentiates it from sibling tools like check_duplicate_publication or find_research_gaps.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states usage context: 'Use when the user asks "where should I submit this paper" or wants to compare target venues before deciding.' This provides clear guidance, though it doesn't mention when not to use or alternatives, which is acceptable given distinct siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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'. Uses Science AI Journal credits.
| Name | Required | Description | Default |
|---|---|---|---|
| sessionId | Yes | WriterSession id you already own. Create one via the web UI at /writer first; the MCP server does not own the session-creation flow today. | |
| section | No | Which section to run. Default 'step_7_5' (the code-search → adapt → verify → simulate chain). | |
| language | No | Simulation language override (python | r | matlab | ...). | |
| force | No | If true, abort any existing queued/running job for this (sessionId, section) and enqueue fresh. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses immediate return with jobId, ~5s claim time, default section, credit usage. Schema adds force behavior. No annotations exist so description carries full burden, and it does well.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, front-loaded with key action, no filler. Efficient and clear.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers enqueue action, return type, timing, default, credits, and references sibling for polling. Lacks error handling details but sufficient for a simple tool with clear sibling.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% parameters with descriptions. Description adds minimal value: default section elaboration. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the action (enqueue a writer-pipeline job) and resource (existing WriterSession). Distinguishes from sibling get_writer_pipeline_status by describing the polling pattern.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit context: requires existing WriterSession, default section, and references sibling for polling. Schema description adds prerequisite (create session via web UI). No explicit exclusion for concurrent jobs, but force parameter is described.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.3check_duplicate_publicationfind_research_gapsget_writer_pipeline_statushakem_review_paperpre_check_paperrecommend_journalsstart_writer_pipelineEach tool has a clear, distinct purpose: duplicate checking, research gaps, journal recommendations, paper pre-check, expert review, and writer pipeline status/start. No significant overlap, and tools like check_duplicate_publication and pre_check_paper serve different aspects of pre-submission.
All tool names follow a consistent verb_noun pattern with underscores (e.g., check_duplicate_publication, find_research_gaps, start_writer_pipeline). Even hakem_review_paper integrates a proper noun but still follows the same structure. No mixing of styles or conventions.
7 tools is well-scoped for an academic research workflow server, covering pre-submission checks, gap analysis, journal recommendations, review, and writing pipeline. Not too few to be trivial, nor too many to be overwhelming.
The tool set covers the main pre-submission and review stages comprehensively, but lacks tools for editing, submitting, or tracking submissions beyond the writer pipeline. Minor gaps exist, such as no cancel or update for the pipeline, but core workflows are well-represented.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools.
Catch AI-fabricated citations (real DOI + fake title). Retraction, open-access, 10,000+ CSL styles.
Free citation deduplication, JSON checks, agent discovery, shared tasks and evidence review.
Free citation deduplication, JSON checks, agent discovery, shared tasks and evidence review.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/SelfPy/science-ai-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server