How to Use the Forj MCP in Pydantic AI

Q: How do I configure Forj with Pydantic AI?

Install pydantic-ai-slimmcp. Initialize MCPToolset with your HTTP endpoint URL, then pass it in the toolsets array to your Agent.

Q: Why use Pydantic AI for Forj instead of a basic API wrapper?

Runtime validation. If listgroupmembers returns unexpected fields, Pydantic AI throws a strict error instead of letting your agent guess how to handle the broken data.

Q: Is it safe to process Forj activity logs through this server?

Yes. When your agent runs getuseractivity, it pulls sensitive behavioral logs. Vinkius processes this inside a strict V8 Isolate Sandbox, ensuring those logs are destroyed immediately after Pydantic AI parses them.

Type-safe Forj community management with the Forj MCP Server and Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Forj MCP to Pydantic AI

Create your Vinkius account to connect Forj 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 Forj with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe group queries with Pydantic AI

Silent API failures destroy automated Forj community management. When you connect the Forj MCP Server to Pydantic AI, every response from `get_group` or `list_groups` gets validated against strict models at runtime. If the API returns a malformed group object, your agent fails loudly with a validation error. You never have to worry about your agent hallucinating a group ID and passing bad data into `add_user_to_group`. Correctness is guaranteed.

Search members with model-agnostic precision

Finding users across a large Forj community requires exact data structures. Your agent uses `find_user` to locate specific emails, and Pydantic AI ensures the returned profile matches your exact schema expectations. Because Pydantic AI is model-agnostic, you can swap between Anthropic for complex reasoning on `get_user_activity` and a cheaper local model for routine `search_users` queries. The tool execution remains perfectly consistent either way.

Audit pending requests and webhooks

You can't afford silent errors when managing Forj community access. Your agent can pull `list_pending_requests` to review who wants into your groups, trusting that the payload structure is exactly what your code expects. It can also run `list_webhooks` to ensure your external notifications are active. If the Forj endpoint changes its response format, Pydantic AI catches it immediately, preventing your agent from making blind administrative decisions.

Setup guide

Set up Forj 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": {
        "forj-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Forj 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 Forj. 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 Forj 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 Forj MCP in Pydantic AI

Install pydantic-ai-slim[mcp]. Initialize MCPToolset with your HTTP endpoint URL, then pass it in the toolsets array to your Agent.

Runtime validation. If list_group_members returns unexpected fields, Pydantic AI throws a strict error instead of letting your agent guess how to handle the broken data.

Yes. The framework is completely model-agnostic. You can run get_account_details using Ollama just as easily as you can with GPT-4.

Yes. You can connect using Streamable HTTP or SSE transports, depending on how your specific Python backend is architected.

Yes. When your agent runs get_user_activity, it pulls sensitive behavioral logs. Vinkius processes this inside a strict V8 Isolate Sandbox, ensuring those logs are destroyed immediately after Pydantic AI parses them.

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