4,000+ servers built on vurb.ts
Vinkius
CrewAIFramework
Stanford PubMed MCP Server

Bring Pubmed
to CrewAI

Learn how to connect Stanford PubMed to CrewAI and start using 16 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.

MCP Inspector GDPR Free for Subscribers
Batch Get ArticlesGet AbstractGet ArticleGet CitationsGet Related ArticlesSearch By AuthorSearch By JournalSearch By MeshSearch ClinicalSearch DrugsSearch Free Full TextSearch GenesSearch PubmedSearch RecentSearch ReviewsSearch Trending

Compatible with every major AI agent and IDE

ClaudeClaude
ChatGPTChatGPT
CursorCursor
GeminiGemini
WindsurfWindsurf
VS CodeVS Code
JetBrainsJetBrains
VercelVercel
+ other MCP clients
Stanford PubMed

What is the Stanford PubMed MCP Server?

Connect to the PubMed E-utilities API from the National Library of Medicine — the gold standard for biomedical literature search.

What you can do

  • Full-Text Search — Search across 36M+ biomedical articles from MEDLINE
  • MeSH Vocabulary — Use Medical Subject Headings for precise, controlled-vocabulary searches
  • Clinical Trials — Filter specifically for clinical trial publications
  • Reviews & Meta-analyses — Find systematic reviews and meta-analyses
  • Gene Search — Search articles mentioning specific genes (TP53, BRCA1, EGFR)
  • Drug Search — Find articles about specific drugs and compounds
  • Citation Tracking — Find articles that cite a given paper
  • Related Articles — Use NCBI's similarity algorithm to discover related literature
  • Abstracts — Retrieve full structured abstracts for quick evaluation
  • Free Full Text — Filter for open access articles available in PubMed Central
  • Batch Retrieval — Fetch multiple articles by PMID in a single request

Who is this for?

  • Medical Researchers — literature reviews, evidence-based medicine
  • PhD Students — comprehensive biomedical search
  • Clinicians — find clinical trial evidence for treatment decisions
  • Pharmacologists — drug interaction and efficacy research

Built-in capabilities (16)

batch_get_articles

Useful for building reading lists, comparing studies, or analyzing a collection of articles from a reference list. Retrieve multiple articles by PMID list

get_abstract

For structured abstracts, returns all sections (Background, Methods, Results, Conclusions). Essential for quickly evaluating whether a paper is relevant without accessing the full text. Get the full abstract text of a PubMed article

get_article

Returns title, all authors, journal name, publication date, volume, issue, pages, DOI, publication types, and language. Get article details by PubMed ID (PMID)

get_citations

Essential for understanding an article's impact, finding follow-up studies, and tracking how findings have been built upon by other researchers. Get articles that cite a given PubMed article

get_related_articles

The algorithm considers title, abstract, MeSH headings, and substances to compute similarity scores. This is often more effective than keyword search for discovering relevant literature. Find related articles using NCBI similarity algorithm

search_by_author

Use "LastName FirstInitial" format for best results (e.g. "Doudna JA", "Zhang F"). Returns the author's publication list with article metadata. Find PubMed articles by author name

search_by_journal

Can be combined with a topic query. Use journal abbreviations or full names (e.g. "Nature", "N Engl J Med", "Lancet", "Cell", "Science", "JAMA", "BMJ"). Find articles published in a specific journal

search_by_mesh

MeSH terms provide precise topic classification. Examples: "Neoplasms", "Diabetes Mellitus", "Machine Learning", "Clustered Regularly Interspaced Short Palindromic Repeats", "COVID-19". Search using MeSH controlled vocabulary terms

search_clinical

This includes Phase I-IV trials, randomized controlled trials, and clinical study reports. Essential for evidence-based medicine and systematic reviews. Search for clinical trial publications

search_drugs

Uses the Substance Name field for precise matching. Examples: "metformin", "pembrolizumab", "remdesivir", "aspirin", "dexamethasone". Search articles mentioning specific drugs or compounds

search_free_full_text

This filters to only return open access or author-deposited articles where the complete manuscript can be read for free. Essential for researchers without institutional journal subscriptions. Search for articles with free full-text available

search_genes

Uses the Gene Name field tag for precise matching. Examples: "TP53", "BRCA1", "EGFR", "KRAS", "MYC". Can be combined with a topic query for more specific results. Search articles mentioning specific genes

search_pubmed

Returns article titles, authors, journals, dates, DOIs, and publication types. Sort options: "relevance" (default), "date", "pub_date", "first_author", "journal". Search 36M+ biomedical articles on PubMed

search_recent

Use this to stay up-to-date with the latest publications in your research area. Default is last 30 days. Find the most recent articles in a field

search_reviews

These are the highest level of evidence synthesis in medicine and provide comprehensive overviews of research on a topic. Search for review articles and meta-analyses

search_trending

This surfaces papers that are generating the most attention and engagement in the research community. Find trending articles in a subject area

Why CrewAI?

When paired with CrewAI, Stanford PubMed becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Stanford PubMed tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.

  • Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools

  • CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the mcps parameter and agents auto-discover every available tool at runtime

  • Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

  • Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

See it in action

Stanford PubMed in CrewAI

AI AgentVinkius
High Security·Kill Switch·Plug and Play
Why Vinkius

Stanford PubMed and 4,000+ other MCP servers. One platform. One governance layer.

Teams that connect Stanford PubMed to CrewAI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.

4,000+MCP Servers ready
<40msCold start
60%Token savings
Raw MCP
Vinkius
Server catalogFind and host yourself4,000+ managed
InfrastructureSelf-hostedSandboxed V8 isolates
Credential handlingPlaintext in configVault + runtime injection
Data loss preventionNoneConfigurable DLP policies
Kill switchNoneGlobal instant shutdown
Financial circuit breakersNonePer-server limits + alerts
Audit trailNoneEd25519 signed logs
SIEM log streamingNoneSplunk, Datadog, Webhook
HoneytokensNoneCanary alerts on leak
Custom domainsNot applicableDNS challenge verified
GDPR complianceManual effortAutomated purge + export
Enterprise Security

Why teams choose Vinkius for Stanford PubMed in CrewAI

The Stanford PubMed MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 16 tools execute in hardened sandboxes optimized for native MCP execution.

Your AI agents in CrewAI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

Stanford PubMed
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

The Vinkius Advantage

How Vinkius secures Stanford PubMed for CrewAI

Every tool call from CrewAI to the Stanford PubMed MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.

< 40msCold start
Ed25519Signed audit chain
60%Token savings
FAQ

Frequently asked questions

01

Do I need an API key?

No. The PubMed E-utilities API is public. An optional free API key from NCBI increases rate limits from 3 to 10 requests per second.

02

What is MeSH?

MeSH (Medical Subject Headings) is the NLM's controlled vocabulary for indexing biomedical articles. It provides standardized terms for precise searching — for example, using 'Neoplasms' will find all cancer-related articles regardless of which synonym the authors used.

03

Can I retrieve full-text articles?

PubMed provides abstracts for all articles and links to free full text when available through PubMed Central. Use the free full-text filter to find open-access articles you can read immediately.

04

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

05

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

06

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

07

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

08

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.

09

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.

10

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

11

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

12

Rate limiting or 429 errors

Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

Explore More MCP Servers

View all →