Bring Transparency
to OpenAI Agents SDK
Learn how to connect TCE-SP (Audesp) to OpenAI Agents SDK and start using 3 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the TCE-SP (Audesp) MCP Server?
Connect to the TCE-SP Audesp system to audit and analyze public spending across municipalities in the state of São Paulo. This server provides direct access to the official transparency portal data.
What you can do
- Municipality Lookup — List all cities under TCE-SP jurisdiction and retrieve their unique slugs for precise querying
- Expense Analysis — Fetch detailed expense (despesas) records for any municipality, filtered by fiscal year and month
- Revenue Tracking — Access revenue (receitas) data to monitor municipal collections and budget performance
- Fiscal Auditing — Use AI to compare spending patterns and identify fiscal trends across different periods
How it works
- Subscribe to this server
- Enter your API access credentials or token
- Start querying public data from any MCP-compatible client like Claude or Cursor
Who is this for?
- Journalists & Researchers — quickly extract fiscal data for investigative reporting without manual portal navigation
- Public Managers — monitor municipal performance and compare budget execution against historical data
- Citizens & Activists — promote transparency by easily accessing how public resources are being allocated
Built-in capabilities (3)
List expenses for a specific municipality, year, and month
List all municipalities under TCE-SP jurisdiction
List revenues for a specific municipality, year, and month
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 3 tools from TCE-SP (Audesp) through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries TCE-SP (Audesp), 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
TCE-SP (Audesp) in OpenAI Agents SDK
TCE-SP (Audesp) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect TCE-SP (Audesp) 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 | 4,000+ 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 TCE-SP (Audesp) in OpenAI Agents SDK
The TCE-SP (Audesp) 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 3 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
TCE-SP (Audesp) for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the TCE-SP (Audesp) 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 the correct name (slug) for a specific city?
Use the list_municipios tool. It returns a complete list of all municipalities under TCE-SP jurisdiction with their respective slugs needed for expense and revenue queries.
Can I query data for any year and month?
Yes, using list_despesas or list_receitas, you can specify the exercicio (year) and mes (month, 1-12) to get precise historical data for a municipality.
What is the difference between list_despesas and list_receitas?
list_despesas focuses on how the municipality spent its budget (expenses), while list_receitas shows the income and collections (revenues) received by the city.
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.
Explore More MCP Servers
View all →
Synthesia
10 toolsProduce professional AI videos with lifelike avatars that present in 140+ languages without cameras, studios, or actors.
Meilisearch
44 toolsManage your Meilisearch instance — handle indexes, documents, and search configurations directly from your AI agent.
Fireworks AI
6 toolsEmpower LLM applications via Fireworks AI — perform ultra-fast chat completions, generate embeddings and images, and transcribe audio directly from any AI agent.
PHC GO
16 toolsEquip your AI agent to control your PHC GO ERP. Query customers, retrieve real-time stocks, map taxes, and issue documents conversationally.