How to Use the Keepcon MCP in Pydantic AI

Q: Why is my Keepcon agent throwing validation errors on profile searches?

The LLM might be guessing the filter syntax for searchprofiles. Pydantic AI catches this mismatch instantly. Check the traceback to see which field the agent hallucinated.

Q: Can I fetch a list of all active users?

Use the listprofiles tool. It returns a structured array of user objects. The framework ensures every object in that array perfectly matches the expected profile model.

Q: How are user IDs protected during Pydantic AI execution?

Social network IDs passed into getprofilebysocialid are strictly validated but never stored at the transport layer. The V8 Isolate Sandbox processes the parameters in an ephemeral memory space that is wiped the millisecond the API returns the profile data.

Build type-safe Keepcon moderation workflows with 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 Keepcon MCP to Pydantic AI

Create your Vinkius account to connect Keepcon 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 Keepcon with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-checked real-time moderation.

The Keepcon MCP Server exposes core semantic analysis directly to your type-safe agents. When the agent calls `moderate_content`, it expects a strict dictionary containing the decision string and an array of tags. Pydantic AI enforces this contract at runtime. If the API returns an unexpected tag format, the framework fails loudly with a validation error. When correcting false positives via `submit_feedback`, you know the payload matches the exact schema the engine requires.

Predictable batch operations.

Managing async moderation queues requires exact sequence execution. The agent starts the process by calling `import_batch` and capturing the specific import ID integer. It then polls `export_results` using that exact ID to fetch the verdicts. Once the data is verified, `acknowledge_results` clears the queue. Because Pydantic validates every step, your agent never tries to acknowledge a batch that hasn't finished processing.

Strict profile lookups.

Identity resolution needs to be exact. The agent uses `get_profile` to fetch a user by their internal ID, or `get_profile_by_social_id` to map a Facebook or Twitter handle to a known record. For broader investigations, `search_profiles` accepts a specific set of filter arguments. If an LLM hallucinates a search parameter that doesn't exist in the Keepcon specification, Pydantic AI blocks the call before it ever hits the network.

Setup guide

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

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

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

Instantiate MCPToolset with your HTTP endpoint string. Pass this toolset into your Agent constructor. Do not use the deprecated MCPServerHTTP class.

The LLM might be guessing the filter syntax for `search_profiles`. Pydantic AI catches this mismatch instantly. Check the traceback to see which field the agent hallucinated.

Use the `list_profiles` tool. It returns a structured array of user objects. The framework ensures every object in that array perfectly matches the expected profile model.

The framework supports both Streamable HTTP and SSE transports for the connection. However, the Keepcon tools themselves return discrete JSON responses rather than streaming text tokens.

Social network IDs passed into `get_profile_by_social_id` are strictly validated but never stored at the transport layer. The V8 Isolate Sandbox processes the parameters in an ephemeral memory space that is wiped the millisecond the API returns the profile data.

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