How to Use the Mem AI (Knowledge Workspace) MCP in Pydantic AI

Q: How do I initialize the Mem AI (Knowledge Workspace) toolset in Pydantic AI?

Use the unified MCPToolset class pointing to your Vinkius HTTP endpoint, then pass it directly into your Agent constructor. This replaces the deprecated HTTP server classes.

Q: How does Pydantic AI validate search results from Mem AI (Knowledge Workspace)?

When calling searchmems, the framework maps the raw API response directly to your defined Pydantic models. This MCP Server setup ensures that any unexpected fields or missing data types will trigger a schema validation error instantly.

Q: What should I do before updating an existing note?

Always have your agent run getmem first to retrieve the current content. Since updatemem replaces the entire text, this step prevents your agent from accidentally wiping out existing data.

Build type-safe agents with Pydantic AI that search, structure, and edit your Mem AI knowledge base with zero runtime schema errors.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mem AI (Knowledge Workspace) MCP to Pydantic AI

Create your Vinkius account to connect Mem AI (Knowledge Workspace) to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Mem AI (Knowledge Workspace) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate your workspace notes at runtime

When your Pydantic AI agent pulls down notes using `get_mem`, the framework enforces strict type validation on the incoming JSON payload. If the Mem response doesn't match your expected schema, the system raises a loud validation error immediately. This prevents your agent from processing corrupted text or missing metadata fields. You can reliably parse complex Mem documents without worrying about silent failures or unexpected API formats.

Structure your MCP Server collections safely

Creating and organizing Mem collections requires clean, structured inputs. Your Pydantic AI agent uses `create_collection` and `add_mem_to_collection` with fully typed parameters, ensuring that every folder mapping is valid before the API is hit. This type-safety guarantees that your Mem knowledge base taxonomy remains clean. You won't end up with broken references or orphaned notes due to malformed string parameters.

Prevent accidental note destruction

Modifying notes can be risky, especially since `update_mem` replaces absolute Mem text values. Pydantic AI forces you to validate the current note content fetched via `get_mem` before pushing any changes back to the Mem server. For highly destructive actions like `delete_mem`, you can set up strict validation models to ensure the agent only targets specific, non-critical Mem IDs. This keeps your production data safe from erratic agent behavior.

Setup guide

Set up Mem AI (Knowledge Workspace) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "mem-ai-knowledge-workspace-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Mem AI (Knowledge Workspace) tools.",
)

result = await agent.run("List recent Mem AI (Knowledge Workspace) transactions")
print(result.output)

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 Mem.ai. 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 Mem AI (Knowledge Workspace) 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 Mem AI (Knowledge Workspace) MCP in Pydantic AI

Use the unified `MCPToolset` class pointing to your Vinkius HTTP endpoint, then pass it directly into your `Agent` constructor. This replaces the deprecated HTTP server classes.

When calling `search_mems`, the framework maps the raw API response directly to your defined Pydantic models. This MCP Server setup ensures that any unexpected fields or missing data types will trigger a schema validation error instantly.

Yes, the framework is completely model-agnostic. You can run local LLMs or proprietary models to execute these MCP tools like `list_collection_mems` and analyze your workspace data.

Always have your agent run `get_mem` first to retrieve the current content. Since `update_mem` replaces the entire text, this step prevents your agent from accidentally wiping out existing data.

We route your traffic through an ephemeral V8 sandbox that clears all memory on execution. Your raw knowledge vectors and personal notes are never stored or cached on our servers, keeping your workspace completely private.

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