# Altair (remote · altairworld.com)

Free TradingAgents equity research reports and Altair pages; paid signals feed via x402 inside MCP.

- Trust score: 80/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `altairworld.com`: 80/100 (this document), [markdown](https://verifymcp.io/servers/com-altairworld-site/altairworld.md), [page](https://verifymcp.io/servers/com-altairworld-site/altairworld)

## Channel facts

- Endpoint: `https://altairworld.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.3.0`

## 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 2026-11-05.

- **Endpoint Security**: 77/100
  - 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 is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1177 tokens (~130/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 57/100
  - Stability check failed: schema churn in the 22 days we've observed: 1 tool removals, 0 breaking changes, 0 auth/transport breaks, 4 additions.
- **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.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Altair MCP server?

Altair is a hosted endpoint at https://altairworld.com/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 com-altairworld-site 'https://altairworld.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-altairworld-site": {
      "url": "https://altairworld.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-altairworld-site": {
      "type": "http",
      "url": "https://altairworld.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-altairworld-site]
url = "https://altairworld.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-altairworld-site": {
      "type": "remote",
      "url": "https://altairworld.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-altairworld-site --url 'https://altairworld.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-altairworld-site:
    url: "https://altairworld.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-altairworld-site": {
      "Transport": "http",
      "Url": "https://altairworld.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-altairworld-site -t streamable-http -u 'https://altairworld.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-altairworld-site": {
      "type": "http",
      "url": "https://altairworld.com/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.

### 2026-11-04 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53.

### 2026-11-02 (score 79, +1)

- [security] Tool “get_market_indicators” rewrote its description, which is the text the model reads
- [security] Tool “get_ticker_indicators” rewrote its description, which is the text the model reads

### 2026-10-31 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40.

### 2026-10-29 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33.

### 2026-10-28 (score 76, 0)

- [security] Tool “get_research_decisions” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 116 → 128
- [functional] New tool “get_ticker_indicators”
- [cosmetic] “get_research_decisions” added an optional parameter “includePrevious”

### 2026-10-26 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23.

### 2026-10-24 (score 75, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: pass → fail
- [functional] Server version: 3.1.0 → 3.2.0
- [functional] New tool “get_market_indicators”

### 2026-10-23 (score 75, +1)

- [security] Tool “get_market_breadth” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 628 → 786
- [functional] Server version: 2.1.0 → 3.1.0
- [functional] New tool “get_research_decisions”

## MCP tools (9)

### `list_pages` (~30 tokens)

List public pages

Return public Altair page paths, URLs, titles and descriptions. Use this to discover pages before read_page.

### `read_page` (~66 tokens)

Read a public page

Return a public Altair page's full markdown with its path, URL, title and description. Use a path from list_pages when you need the page content.

Input parameters:

- `path` (string, required): Site path from list_pages, e.g. /indicators; 1–2048 characters.

### `get_market_breadth` (~121 tokens)

Get market breadth

Return the latest S&P 500 sector breadth and S&P 500, Nasdaq-100 and PHLX Semiconductor (SOX) constituent percentages above their 20-session simple moving averages, with SPX, NDX and SOX price-index benchmark levels (no dividends). History uses the loader's constituent lists, not point-in-time membership. Optionally choose 1–252 recent trading sessions; default 20.

Input parameters:

- `days` (integer): Recent trading sessions to return in history; integer from 1 to 252, default 20.

### `get_market_indicators` (~148 tokens)

Get market indicators

Return the latest readings of ten factor indicators and TD Sequential 9 (daily and weekly) for the S&P 500 (SPX), Nasdaq-100 (NDX) and PHLX Semiconductor (SOX) price indices: value, reading, bullish/neutral/bearish signal, the rule's bands and the previous session's value and signal, with each rule's source and its 2005–2026 S&P 500 and Nasdaq-100 evidence. Signals are rule readings, not forecasts; several are contrarian, and SOX implied volatility is Cboe's semiconductor ETF index VXSMH. Five-year histories are at /api/market/indicators.

### `get_ticker_indicators` (~165 tokens)

Get ticker indicators

Return latest factor and daily/weekly TD Sequential readings for one Yahoo Finance symbol, with session, price, rules, sources and historical index evidence. Reuses /api/market/indicators?ticker=; no chart histories. Stock implied volatility and variance risk premium are null; VIX term structure, credit and yield curve are shared market context. Evidence is not validated single-stock returns. Signals are rule readings, not forecasts or investment advice; the session may still be open. Each reading includes the previous session's value and signal.

Input parameters:

- `ticker` (string, required): Yahoo Finance symbol, case-insensitive, 1–20 characters after trimming: letters, digits, . - = ^; e.g. NVDA, BRK-B or 0700.HK.

### `list_research_reports` (~157 tokens)

List research reports

Return published TradingAgents report metadata and URLs newest first, the matching total and counts for all tickers. Use this to find reports before read_research_report, optionally filter by ticker and page with limit and offset.

Input parameters:

- `limit` (integer): Maximum reports to return per call; integer from 1 to 100, default 20.
- `offset` (integer): Number of matching reports to skip, e.g. 20 for the next page with limit 20; integer from 0 to 9007199254740991, default 0.
- `ticker` (string): Stock ticker, e.g. NVDA; case-insensitive, 1–32 characters after trimming. Omit to list all tickers.

### `get_research_decisions` (~209 tokens)

Get research decisions

Return every model's final portfolio decision for one ticker on its newest analysis date, or a chosen one: rating, report-time price, price target, confidence, time horizon and executive summary, with report URLs. Set includePrevious to compare each represented model's rating with its nearest earlier analysis date, with both source URLs and explicit missing/unavailable states. Same-date reruns use the latest run-start time; model names are not merged. No explanation of why a rating changed is inferred. Use read_research_report for reasoning.

Input parameters:

- `date` (string): Analysis date YYYY-MM-DD from list_research_reports. Omit for the newest.
- `includePrevious` (boolean): Include each selected model's rating comparison with its nearest strictly earlier analysis date. Default false; not a comparison across models or reruns of the same date.
- `ticker` (string, required): Stock or ETF ticker, e.g. NVDA or SPY; case-insensitive, 1–32 characters after trimming.

### `read_research_report` (~89 tokens)

Read a research report

Return a full TradingAgents report as markdown, its ticker, date, model and URL, and an informational-only disclaimer; sections cover analyst reports, research decisions, trading plans, risk management and portfolio decisions. Use a url from list_research_reports for free access without sign-in.

Input parameters:

- `url` (string, required): A report url returned by list_research_reports; 1–2048 characters.

### `get_research_signals` (~137 tokens)

Buy research signals

Return the latest final portfolio decision per ticker as structured JSON, including report dates, models, source URLs and summaries. Optional tickers and since filters; ten-minute cache. Costs $0.01 USD per call by default via x402 payments inside MCP; the payment challenge gives the current price. Free sample: /api/research/signals/sample.

Input parameters:

- `since` (string): Inclusive minimum analysis date, a valid YYYY-MM-DD date. Omit for all dates.
- `tickers` (string): 1–100 comma-separated uppercase ticker symbols, e.g. NVDA,AAPL. Omit for all tickers.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-altairworld-site/altairworld#diagnostics

## Score history

- 2026-11-05: 80
- 2026-11-04: 80
- 2026-11-03: 79
- 2026-11-02: 79
- 2026-11-01: 78
- 2026-10-31: 78
- 2026-10-30: 77
- 2026-10-29: 77
- 2026-10-28: 76
- 2026-10-27: 76
- 2026-10-26: 76
- 2026-10-25: 75
- 2026-10-24: 75
- 2026-10-23: 75
- 2026-10-22: 74
- 2026-10-21: 74
- 2026-10-20: 73
- 2026-10-19: 73
- 2026-10-18: 75
- 2026-10-17: 74
- 2026-10-16: 74
- 2026-10-15: 73
- 2026-10-14: 73

## Common questions

### What is the Altair MCP server?

Altair is an MCP server listed in the public MCP registry as com.altairworld/site. Free TradingAgents equity research reports and Altair pages; paid signals feed via x402 inside MCP. This page covers its hosted endpoint (https://altairworld.com/mcp).

### Is the Altair MCP server safe to use?

Altair scores 80 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 Altair MCP server expose?

Altair exposes 9 tools: list_pages, read_page, get_market_breadth, get_market_indicators, get_ticker_indicators, and 4 more. Their descriptions and schemas cost roughly 1,122 tokens of context every time the server is loaded.

### Does the Altair MCP server require authentication?

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

### Is the Altair MCP server still maintained?

Altair is still listed as active in the MCP registry. We last reached this channel on 5 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 Altair MCP server?

VerifyMCP ran 13 checks on Altair, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. 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://altairworld.com/mcp
- Website: https://altairworld.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-altairworld-site/altairworld.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-altairworld-site/altairworld/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-altairworld-site/altairworld.json
- HTML version of this page: https://verifymcp.io/servers/com-altairworld-site/altairworld