Bring Micro Payments
to OpenAI Agents SDK
Learn how to connect FynCom to OpenAI Agents SDK and start using 6 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the FynCom MCP Server?
Connect your FynCom account to any AI agent and take full control of your user incentives and reward operations through natural conversation.
What you can do
- Reward Orchestration — Send instant cryptocurrency or fiat rewards to users or email addresses programmatically to incentivize engagement and feedback
- Campaign Management — Access and monitor your active reward campaigns and retrieve detailed performance and lead metadata in real-time
- Lead Engagement Tracking — Add leads to specific reward workflows programmatically from your AI agent to trigger automated incentives and follow-ups
- Wallet Intelligence — Check your real-time rewards wallet balance directly through your agent to ensure uninterrupted delivery of user incentives
- Transaction Oversight — Get a comprehensive overview of your reward history and campaign health using natural language commands
How it works
1. Subscribe to this server
2. Retrieve your API Key from your FynCom dashboard (Settings > API)
3. Start managing your user rewards from Claude, Cursor, or any MCP client
No more manual payment processing for small incentives. Your AI acts as your dedicated rewards and engagement coordinator.
Who is this for?
- Growth Marketers — automate the delivery of incentives for survey completions and product feedback using natural language queries
- Customer Success Managers — reward key customer actions and track engagement patterns more efficiently without leaving your workspace
- Product Developers — integrate real-time reward systems and incentive intelligence into custom applications through automated AI actions
Built-in capabilities (6)
Pass data in JSON. Add a lead to a reward campaign
Get specific campaign details
Check current rewards wallet balance
List active reward campaigns
List history of sent rewards
Pass data as a JSON string. Send a reward or incentive
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 6 tools from FynCom through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries FynCom, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
FynCom in OpenAI Agents SDK
FynCom and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect FynCom to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for FynCom in OpenAI Agents SDK
The FynCom 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. All 6 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* 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
How Vinkius secures
FynCom for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the FynCom MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I find my FynCom API Key?
Log in to your FynCom dashboard and navigate to the Settings > API section to generate or copy your unique key.
Can I check my wallet balance via AI?
Yes! Use the get_wallet_balance tool to retrieve your current rewards budget and ensured you have sufficient funds for your campaigns.
How do I add a lead to a reward campaign?
Use the add_reward_lead tool by providing the campaign_id and a JSON string with the lead's email and other required details.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.