Low Risk

focus_expectations

Focus market expectations survey — annual median/mean forecasts from ~150 economists. Filter by indicator (e.g. "IPCA", "Selic", "PIB Total", "Câmbio", "IGP-M") and optionally reference year. Returns latest survey rows with Media, Mediana, Minimo, Maximo, numeroRespondentes.

Part of the Bcb Br server.

focus_expectations is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE BCB BR →

Free to start. No card required.

AI agents call focus_expectations to retrieve information from Bcb Br without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though focus_expectations only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "focus_expectations": {}
  }
}

See the full Bcb Br policy for all 25 tools.

Get this rule live on your own Bcb Br server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY BCB BR →

View all 25 tools →

These attack patterns abuse exactly the kind of access focus_expectations gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so focus_expectations only ever does what you allow.

SECURE BCB BR →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the focus_expectations tool do? +

Focus market expectations survey — annual median/mean forecasts from ~150 economists. Filter by indicator (e.g. "IPCA", "Selic", "PIB Total", "Câmbio", "IGP-M") and optionally reference year. Returns latest survey rows with Media, Mediana, Minimo, Maximo, numeroRespondentes.. It is categorised as a Read tool in the Bcb Br MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on focus_expectations? +

Register the Bcb Br MCP server in PolicyLayer and add a rule for focus_expectations: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Bcb Br. Nothing to install.

What risk level is focus_expectations? +

focus_expectations is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit focus_expectations? +

Yes. Add a rate_limit block to the focus_expectations rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block focus_expectations completely? +

Set action: deny in the PolicyLayer policy for focus_expectations. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides focus_expectations? +

focus_expectations is provided by the Bcb Br MCP server (https://gateway.pipeworx.io/bcb-br/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Bcb Br tool call.

Deterministic rules across all 25 Bcb Br tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.