# Onça Setorial (remote · tamandua.onssa.org)

Brazilian regulator data: CVM filings, dam safety, airline punctuality, rules, enforcement

- Trust score: 68/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `tamandua.onssa.org`: 68/100 (this document), [markdown](https://verifymcp.io/servers/marcioyoshida-onca-setorial/tamandua.md), [page](https://verifymcp.io/servers/marcioyoshida-onca-setorial/tamandua)

## Channel facts

- Endpoint: `https://tamandua.onssa.org/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 403, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1534 tokens (~191/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Onça Setorial MCP server?

Onça Setorial is a hosted endpoint at https://tamandua.onssa.org/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http marcioyoshida-onca-setorial 'https://tamandua.onssa.org/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "marcioyoshida-onca-setorial": {
      "url": "https://tamandua.onssa.org/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "marcioyoshida-onca-setorial": {
      "type": "http",
      "url": "https://tamandua.onssa.org/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.marcioyoshida-onca-setorial]
url = "https://tamandua.onssa.org/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "marcioyoshida-onca-setorial": {
      "type": "remote",
      "url": "https://tamandua.onssa.org/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add marcioyoshida-onca-setorial --url 'https://tamandua.onssa.org/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  marcioyoshida-onca-setorial:
    url: "https://tamandua.onssa.org/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "marcioyoshida-onca-setorial": {
      "Transport": "http",
      "Url": "https://tamandua.onssa.org/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add marcioyoshida-onca-setorial -t streamable-http -u 'https://tamandua.onssa.org/mcp'
```

### Other

```json
{
  "mcpServers": {
    "marcioyoshida-onca-setorial": {
      "type": "http",
      "url": "https://tamandua.onssa.org/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 64, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-11 (score 64)

First indexed and scored.

## MCP tools (8)

### `company_financials` (~219 tokens)

Company financials from CVM filings (DFP/ITR)

Revenue, net income, assets, equity, EBIT, D&A for a Brazilian listed company in your licensed sectors, from its own CVM filings: the annual DFP and the latest quarterly ITR (year-to-date). Derived values (EBITDA, net debt, margins, leverage) are returned separately and labelled estimativa. A company with no CVM filing says so (closed capital or IR-page only) instead of returning numbers. Use for 'what was X's revenue / net income / debt'. Deterministic: computed from official datasets, no model in the loop.

Input parameters:

- `entity` (string, required): Company name or Onça Setorial id, e.g. 'Vale', 'Eletrobras', 'Hypera'.
- `period` (string): Optional. '2025' or '2025-12-31' for the annual DFP; '2T26', '2026Q2' or '2026-06-30' for a quarterly ITR. Default: every statement on file.

### `dam_safety` (~113 tokens)

Mining dam safety per company (ANM SIGBM)

Tailings-dam safety per mining company from ANM's SIGBM register: number of dams, dams at an emergency level or at alert, high risk category (CRI) and high associated potential damage (DPA), and the worst emergency level. Use for 'which mining companies have dams in emergency'. Worst first. Needs the mining sector licensed. Deterministic: computed from official datasets, no model in the loop.

Input parameters:

- `entity` (string): Optional. One company by name, e.g. 'Vale'.

### `airline_punctuality` (~97 tokens)

Airline cancellations and delays (ANAC VRA)

Per airline, from ANAC's latest monthly VRA file: scheduled flights, cancellations and departures more than 15 minutes late, with rates. Use for 'which Brazilian airline cancels or delays most'. Needs the aviation sector licensed. Deterministic: computed from official datasets, no model in the loop.

Input parameters:

- `entity` (string): Optional. One airline by name, e.g. 'Azul', 'LATAM'.

### `regulatory_events` (~143 tokens)

Regulatory acts and deadlines for a sector

For one of your licensed sectors: public consultations and other regulatory deadlines falling due in the next `days`, then the acts published in the current window (Diário Oficial, the sector regulator, Câmara/Senado), each with its lifecycle stage and a link to the act. Use for 'which regulatory deadlines are coming up in energy'. Deterministic: computed from official datasets, no model in the loop.

Input parameters:

- `days` (integer): Optional. Deadline horizon in days, default 90.
- `sector` (string, required): Sector: energy, health, pharmaceutical, telecom, logistics, last_mile, agro, retail, mining or aviation (Portuguese names work too).

### `base_rates` (~152 tokens)

Regulatory base rates (Outcome Ledger), labelled estimativa

How long regulatory processes take and how they end, measured over each regulator's own records (e.g. ANEEL fine → appeal → decision; ANVISA public consultation → published rule): N, median, quartiles and range per figure, with method and limits. Figures are estimativa; a figure below the minimum N is withheld and has no number. Use for 'how long until ANVISA turns a consultation into a rule'. Deterministic: computed from official datasets, no model in the loop.

Input parameters:

- `study` (string): Optional. A study id (e.g. 'aneel_enforcement'), a regulator ('ANVISA') or a sector. Default: every study for your sectors.

### `enforcement_process` (~268 tokens)

One enforcement process's timeline (Outcome Ledger)

The dated steps of ONE sanctioning process from the regulator's own records: an ANEEL auto de infração (issued, received, appeal, decisions, closure), an ANS penalty case (1st and 2nd instance, payment, archiving) or an ANATEL PADO process (phases, dated when first observed). Returns the regulator, the source url, the company only when the record binds it by CNPJ to a tracked company, and each span's days next to that regulator's published base rate (median, quartiles, N; estimativa). Use for 'where is auto 0001/2019-AGEPAN-SFE and is it slow'. Needs the regulator's sector licensed (ANEEL energy, ANS health, ANATEL telecom). Deterministic: computed from official datasets, no model in the loop.

Input parameters:

- `process` (string, required): The process id: ANEEL auto number ('0001/2019-AGEPAN-SFE') or SEI process ('48500.026432/2025-01'), ANS demanda or processo ('33902.499206/2016-46'), or ANATEL PADO process number.
- `regulator` (string): Optional. Restrict the lookup to one regulator.

### `rule_enforcement` (~208 tokens)

ANVISA sanctions citing one rule (Outcome Ledger)

For one ANVISA rule (RDC or IN): its publication date and source, the ANVISA sanctions in the Diário Oficial that cite it as breached (date, act url, and the company only when the act names exactly one company by CNPJ), their count, the lag from publication to the first citing sanction when observable, and, counted apart, refusals of companies' own requests that cite the rule as grounds (these are NOT sanctions). Each act counts once. Use for 'who was sanctioned under RDC 47/2013 and since when'. Needs the pharmaceutical sector licensed. Deterministic: computed from official datasets, no model in the loop.

Input parameters:

- `rule` (string, required): The rule, e.g. 'RDC 47/2013', 'RDC nº 47, de 2013', 'rdc-anvisa-47:2013', 'IN 9/2014'. Without a year, every year on record for that number.

### `consultation_outcome` (~179 tokens)

What one ANVISA public consultation became (Outcome Ledger)

For one ANVISA consulta pública: its opening date and contribution window, whether a norm resulted (only links ANVISA itself publishes; an older norm the consultation revises is shown as prior, not as its result), the norm and its date, days elapsed, and the base rate for context (consultation → norm median days and the share of consultations that produce a norm; estimativa). Use for 'did CP 1.234/2023 become a rule, and how long did it take'. Needs the pharmaceutical sector licensed. Deterministic: computed from official datasets, no model in the loop.

Input parameters:

- `consultation` (string, required): The consultation, e.g. 'CP 1.234/2023', 'Consulta Pública nº 1234, de 2023', 'consulta-publica-1234:2023'.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/marcioyoshida-onca-setorial/tamandua#diagnostics

## Score history

- 2026-11-21: 68
- 2026-11-20: 68
- 2026-11-19: 67
- 2026-11-18: 67
- 2026-11-17: 66
- 2026-11-16: 66
- 2026-11-15: 65
- 2026-11-14: 65
- 2026-11-13: 65
- 2026-11-12: 64
- 2026-11-11: 64

## Common questions

### What is the Onça Setorial MCP server?

Onça Setorial is an MCP server listed in the public MCP registry as io.github.marcioyoshida/onca-setorial. Brazilian regulator data: CVM filings, dam safety, airline punctuality, rules, enforcement. This page covers its hosted endpoint (https://tamandua.onssa.org/mcp).

### Is the Onça Setorial MCP server safe to use?

Onça Setorial scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Onça Setorial MCP server expose?

Onça Setorial exposes 8 tools: company_financials, dam_safety, airline_punctuality, regulatory_events, base_rates, and 3 more. Their descriptions and schemas cost roughly 1,379 tokens of context every time the server is loaded.

### Does the Onça Setorial MCP server require authentication?

No. We connected to Onça Setorial without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Onça Setorial MCP server still maintained?

Onça Setorial is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Onça Setorial MCP server?

VerifyMCP ran 12 checks on Onça Setorial, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Onça Setorial: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://tamandua.onssa.org/mcp
- Repository: https://github.com/marcioyoshida/Signals-Sectorial-Intelligence
- Website: https://tamandua.onssa.org/llms.txt
- Changelog RSS feed: https://verifymcp.io/servers/marcioyoshida-onca-setorial/tamandua.xml
- Changelog JSON feed: https://verifymcp.io/servers/marcioyoshida-onca-setorial/tamandua/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/marcioyoshida-onca-setorial/tamandua.json
- HTML version of this page: https://verifymcp.io/servers/marcioyoshida-onca-setorial/tamandua
