How to Use the PMC Open Access (PubMed Central) MCP in CrewAI

Q: How do I add the PMC Open Access (PubMed Central) MCP Server to CrewAI?

Install crewaitools. Use MCPServerHTTP from the crewai.mcp module and pass the Vinkius URL. You can also pass the URL directly into the mcps array on your agent definition.

Q: Can I restrict which PMC Open Access (PubMed Central) tools a CrewAI agent can use?

Yes. Use the toolfilter parameter. Give your citation agent access to exportcitation only, and your discovery agent access to oadiscover.

Q: How do CrewAI agents share data pulled from PMC Open Access (PubMed Central)?

They use shared memory. When one agent runs convertids, the resulting PMID is stored in context for the next agent in the sequence to use.

Deploy specialized CrewAI agents to mine PubMed Central and build autonomous literature review teams.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PMC Open Access (PubMed Central) MCP to CrewAI

Create your Vinkius account to connect PMC Open Access (PubMed Central) to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup PMC Open Access (PubMed Central) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Autonomous literature discovery

The `oa_discover` tool locates full-text resources inside the PMC Open Access Subset. You assign this specific MCP action to a researcher agent in CrewAI, letting it hunt for downloadable archives while ignoring unrelated tasks. A separate analyst agent then takes those findings and runs `oai_get_record`. The first agent finds the paper; the second agent pulls the exact XML metadata. They share the context through CrewAI's memory.

Multi-agent citation formatting

The `export_citation` tool generates BibTeX and RIS formats for any PMC article. A dedicated formatting agent uses this to compile bibliographies without human intervention. If an article is missing a standard identifier, the agent delegates to the `convert_ids` tool. It swaps a raw manuscript ID for a clean PMID, ensuring the final report is mathematically precise.

PMC MCP Server data mining

The `oai_list_records` tool dumps massive batches of OAI records for your CrewAI team to process. A monitor agent watches the execution, ensuring the system does not overwhelm the PMC endpoint. Before starting the dump, a setup agent runs `oai_list_metadata_formats` to confirm the schema. You build hierarchical execution chains that mimic a real medical research department.

Setup guide

Set up PMC Open Access (PubMed Central) MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke PMC Open Access (PubMed Central) tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="PMC Open Access (PubMed Central) Analyst",
    goal="Access and analyze PMC Open Access (PubMed Central) data via MCP.",
    backstory="Expert analyst with direct PMC Open Access (PubMed Central) access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent PMC Open Access (PubMed Central) transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="PMC Open Access (PubMed Central) Analyst",
        goal="Access and analyze PMC Open Access (PubMed Central) data via MCP.",
        backstory="Expert analyst with direct PMC Open Access (PubMed Central) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent PMC Open Access (PubMed Central) transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by PMC (PubMed Central). All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect PMC Open Access (PubMed Central) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about PMC Open Access (PubMed Central) MCP in CrewAI

Install crewai[tools]. Use MCPServerHTTP from the crewai.mcp module and pass the Vinkius URL. You can also pass the URL directly into the mcps array on your agent definition.

Yes. Use the tool_filter parameter. Give your citation agent access to export_citation only, and your discovery agent access to oa_discover.

They use shared memory. When one agent runs convert_ids, the resulting PMID is stored in context for the next agent in the sequence to use.

CrewAI supports stdio, SSE, and Streamable HTTP. For Vinkius endpoints, you will use the HTTP transport.

This MCP Server setup processes manuscript IDs, DOIs, and open-access XML payloads. Every query runs inside an ephemeral, zero-trust container that terminates immediately after your agent receives the response.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript