Can I see the completion results for a specific student?

Yes! Use the `get_training_completion_results` tool. The agent will return completion data and grades for enrolments, allowing you to track individual or aggregate success.

How do I check which groups a member belongs to?

Use the `get_member_group_associations` tool with the member ID. Your agent will fetch all groups the specific member is part of, giving you context on their organizational alignment.

Where do I find my Coassemble User ID and Token?

Log in to Coassemble, navigate to **Settings**, and select **API**. You can generate and copy your User ID and API User Token from that section.

Coassemble MCP Server for Pydantic AI 8 tools — connect in under 2 minutes

Name: Coassemble
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 8 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Coassemble through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Coassemble "
            "(8 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Coassemble?"
    )
    print(result.data)

asyncio.run(main())

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

About Coassemble MCP Server

Connect your Coassemble account to any AI agent and take full control of your online training and LMS through natural conversation. Streamline how you manage learners, courses, and completion results natively.

Pydantic AI validates every Coassemble tool response against typed schemas, catching data inconsistencies at build time. Connect 8 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Course Oversight — List and retrieve details for all training courses in your workspace natively
Enrolment Intelligence — Access and monitor student enrolments and their current progress flawlessly
Member Management — List all workspace members and their contact details securely
Group Logistics — Monitor student groups and manage their course associations flawlessly
Completion Auditing — Retrieve training results and grades for all enrolments to track success flawlessly
Profile Visibility — Access your own user profile and core workspace metadata directly within your workspace

The Coassemble MCP Server exposes 8 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Coassemble to Pydantic AI via MCP

Follow these steps to integrate the Coassemble MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 8 tools from Coassemble with type-safe schemas

Why Use Pydantic AI with the Coassemble MCP Server

Pydantic AI provides unique advantages when paired with Coassemble through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Coassemble integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Coassemble connection logic from agent behavior for testable, maintainable code

Coassemble + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Coassemble MCP Server delivers measurable value.

Type-safe data pipelines: query Coassemble with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Coassemble tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Coassemble and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Coassemble responses and write comprehensive agent tests

Coassemble MCP Tools for Pydantic AI (8)

These 8 tools become available when you connect Coassemble to Pydantic AI via MCP:

enroll_member_in_course

Enroll a specific member into a course or group

get_course_training_details

Get detailed information for a specific course

get_member_group_associations

Get all groups a specific member belongs to

get_training_completion_results

List training results and grades for enrolments

list_coassemble_courses

List all training courses in the Coassemble workspace

list_coassemble_enrolments

List all course enrolments

list_coassemble_groups

List all student groups in the workspace

list_coassemble_members

List all members (users) in the workspace

Example Prompts for Coassemble in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Coassemble immediately.

"List all training courses in my Coassemble workspace."

"Show me the progress for user 'STU_12345'."

"What are the latest completion results?"

Troubleshooting Coassemble MCP Server with Pydantic AI

Common issues when connecting Coassemble to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Coassemble + Pydantic AI FAQ

Common questions about integrating Coassemble MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Coassemble MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.