# OpenNash Earnings (remote · earnings.opennash.com)

Earnings results, outlook, KPIs and call transcripts for ~400 US, Asian and European companies.

- Trust score: 79/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-22

## Components

- remote · `earnings.opennash.com`: 79/100 (this document), [markdown](https://verifymcp.io/servers/com-opennash-earnings-opennash-earnings/earnings.md), [page](https://verifymcp.io/servers/com-opennash-earnings-opennash-earnings/earnings)

## Channel facts

- Endpoint: `https://earnings.opennash.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.2.0`

## 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 2026-11-22.

- **Endpoint Security**: 80/100
  - 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.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 79/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1715 tokens (~155/item across 11 items; 10 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 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.
  - 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 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 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 OpenNash Earnings MCP server?

OpenNash Earnings is a hosted endpoint at https://earnings.opennash.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-opennash-earnings-opennash-earnings 'https://earnings.opennash.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-opennash-earnings-opennash-earnings": {
      "url": "https://earnings.opennash.com/mcp"
    }
  }
}
```

### VS Code

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

### Codex

```toml
[mcp_servers.com-opennash-earnings-opennash-earnings]
url = "https://earnings.opennash.com/mcp"
```

### opencode

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

### OpenClaw

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

### Hermes

```yaml
mcp_servers:
  com-opennash-earnings-opennash-earnings:
    url: "https://earnings.opennash.com/mcp"
```

### Netclaw

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

### Vellum

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

### Other

```json
{
  "mcpServers": {
    "com-opennash-earnings-opennash-earnings": {
      "type": "http",
      "url": "https://earnings.opennash.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.

### 2026-11-21 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 77, +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.

### 2026-11-14 (score 76, −6)

- [security regression] Authorization: pass → partial
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “fetch” rewrote its description, which is the text the model reads
- [security] Tool “get_company” rewrote its description, which is the text the model reads
- [security] Tool “get_kpis” rewrote its description, which is the text the model reads
- [security] Tool “get_quarter” rewrote its description, which is the text the model reads
- [security] Tool “get_transcript” rewrote its description, which is the text the model reads
- [security] Tool “list_companies” rewrote its description, which is the text the model reads
- [security] Tool “list_recent” rewrote its description, which is the text the model reads
- [security] Tool “search” rewrote its description, which is the text the model reads
- [security] Tool “search_earnings” rewrote its description, which is the text the model reads
- [security] Tool “search_transcripts” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 71% → 100%
- [functional] Server version: 1.1.0 → 1.2.0
- [cosmetic] “get_quarter” added an optional parameter “sections”
- [cosmetic] “list_companies” added an optional parameter “country”
- [cosmetic] “list_companies” added an optional parameter “limit”
- [cosmetic] “list_companies” added an optional parameter “offset”
- [cosmetic] “list_companies” added an optional parameter “query”
- [cosmetic] “search_earnings” added an optional parameter “kind”
- [cosmetic] “fetch” reworded the description of “id”
- [cosmetic] “get_company” reworded the description of “ticker”
- [cosmetic] “get_kpis” reworded the description of “limit”
- [cosmetic] “get_kpis” reworded the description of “metric”
- [cosmetic] “get_kpis” reworded the description of “ticker”
- [cosmetic] “get_quarter” reworded the description of “ticker”
- [cosmetic] “get_transcript” reworded the description of “limit”
- [cosmetic] “get_transcript” reworded the description of “offset”
- [cosmetic] “get_transcript” reworded the description of “ticker”
- [cosmetic] “list_companies” reworded the description of “sector”
- [cosmetic] “list_recent” reworded the description of “days”
- [cosmetic] “list_recent” reworded the description of “limit”
- [cosmetic] “search” reworded the description of “query”
- [cosmetic] “search_earnings” reworded the description of “limit”
- [cosmetic] “search_earnings” reworded the description of “query”
- [cosmetic] “search_earnings” reworded the description of “ticker”
- [cosmetic] “search_transcripts” reworded the description of “limit”
- [cosmetic] “search_transcripts” reworded the description of “query”
- [cosmetic] “search_transcripts” reworded the description of “ticker”

### 2026-11-13 (score 82, +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 81, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-11 (score 81)

First indexed and scored.

## MCP tools (10)

### `search` (~129 tokens)

Search

One search across companies, summarised results and call transcripts, for open questions (ChatGPT deep research and connectors use this with fetch). Companies named in the question (by ticker or name) scope the search. Returns up to 20 ids with a title and snippet; pass an id to fetch for the full text. With other MCP clients, prefer search_earnings (themes in results) or search_transcripts (exact words on calls), which take a ticker and return the text directly.

Input parameters:

- `query` (string, required): A question or words, such as 'What did Nvidia guide for next quarter?'

Output parameters:

- `note` (string)
- `results` (array)

### `fetch` (~84 tokens)

Fetch

Full text for an id from search: company:TICKER (profile, quarter list, latest results), quarter:TICKER/KEY (one quarter's results) or passage:TICKER/KEY#t-N (about 25 transcript paragraphs around the moment).

Input parameters:

- `id` (string, required): An id returned by search, such as quarter:NVDA/2027-q2

Output parameters:

- `id` (string)
- `metadata` (object)
- `text` (string)
- `title` (string)
- `url` (string)

### `list_companies` (~201 tokens)

List companies

Find covered companies and their tickers, latest quarter and next expected report date, sorted by name. Filter by query (name, ticker, sector, country or exchange words), sector or country. Pages of 50 by default (up to 200); total and next_offset tell you whether there are more. Unknown sectors or countries return an error that lists the valid ones.

Input parameters:

- `country` (string): Home country, such as United States, Singapore or United Kingdom
- `limit` (integer): Number of companies, 1-200, default 50
- `offset` (integer): Where to start, default 0; pass next_offset from the previous page
- `query` (string): Words in the name, ticker, sector, country or exchange, such as 'bank singapore' or 'Barclays'
- `sector` (string): Sector, such as Banking, Insurance, Semiconductors or Software; loose matches work ('Banks')

Output parameters:

- `next_offset` (number|null)
- `note` (string)
- `offset` (number)
- `results` (array)
- `total` (number)

### `get_company` (~88 tokens)

Get company

A company's profile (sector, country, reporting currency, fiscal year end, next expected report) and every quarter we have, newest first, with the quarter keys get_quarter and get_transcript take, and whether each has a transcript. Accepts a ticker or a name.

Input parameters:

- `ticker` (string, required): Ticker or company name, such as NVDA, Nvidia, BCS or Barclays

Output parameters:

- `cik` (number|null)
- `country` (string|null)
- `currency` (string|null)
- `exchange` (string|null)
- `fiscal_year_end` (string|null)
- `ir` (string|null)
- `kpi_quarters` (number)
- `latest_quarter` (string|null)
- `legal_name` (string|null)
- `name` (string)
- `next_expected` (string|null)
- `note` (string)
- `quarters` (array)
- `sector` (string|null)
- `ticker` (string)
- `url` (string)

### `get_kpis` (~165 tokens)

Get KPI history

Quarterly KPI history calculated from SEC XBRL filings, newest first, in USD: revenue, gross_profit, operating_income, net_income, eps_diluted, operating_cash_flow, capex, free_cash_flow, rd_expense, gross_margin, operating_margin, net_margin (margins in percent, EPS in USD per share). Only SEC filers have it; for other companies use get_quarter. limit is the number of quarters (1-16, default 16).

Input parameters:

- `limit` (integer): Number of quarters, 1-16, default 16
- `metric` (string): One metric, or omit for all
- `ticker` (string, required): Ticker or company name, such as NVDA, Nvidia, BCS or Barclays

Output parameters:

- `currency` (string)
- `name` (string)
- `note` (string)
- `quarters` (array)
- `ticker` (string)

### `get_quarter` (~181 tokens)

Get quarter

One quarter's results: headline, overview, reported figures (metrics: value as printed, number in currency units, ISO currency, unit currency|per_share|percent) with their source sentence, segments, outlook, a check of last quarter's outlook against what was reported, takeaways, management quotes, analyst Q&A and documents. Omit quarter for the latest; get_company lists the keys.

Input parameters:

- `quarter` (string): Fiscal quarter key from get_company, such as 2027-q2. Omit for the latest.
- `sections` (array): Only these parts (identity fields always come back), such as ["qa"] for every analyst question. Default: all, with Q&A cut to about 8k characters
- `ticker` (string, required): Ticker or company name, such as NVDA, Nvidia, BCS or Barclays

Output parameters:

- `currency` (string|null)
- `documents`
- `filed` (string)
- `filing_url` (string)
- `fy` (number)
- `guidance`
- `guidance_check`
- `has_transcript` (boolean)
- `headline` (string|null)
- `key` (string)
- `label` (string)
- `metrics`
- `note` (string)
- `overview` (array)
- `period_end` (string)
- `q` (number)
- `qa`
- `qa_total` (number)
- `quarter` (string)
- `questions`
- `quotes`
- `recording`
- `segments`
- `takeaways`
- `ticker` (string)
- `topics`
- `url` (string)

### `get_transcript` (~169 tokens)

Get transcript

An earnings call transcript with speakers, timestamps and links, one page at a time: 40 paragraphs or about 12k characters by default, whichever comes first (limit up to 150). Pass next_offset as offset for the next page; total is the paragraph count. To find one moment, search_transcripts is cheaper than paging.

Input parameters:

- `limit` (integer): Number of paragraphs, 1-150, default 40
- `offset` (integer): Where to start, default 0; pass next_offset from the previous page
- `quarter` (string): Fiscal quarter key from get_company, such as 2027-q2. Omit for the latest.
- `ticker` (string, required): Ticker or company name, such as NVDA, Nvidia, BCS or Barclays

Output parameters:

- `label` (string)
- `next_offset` (number|null)
- `note` (string)
- `offset` (number)
- `paragraphs` (array)
- `quarter` (string)
- `recording` (string|null)
- `ticker` (string)
- `total` (number)
- `transcript_quarters` (array)
- `url` (string)

### `search_transcripts` (~157 tokens)

Search transcripts

Exact words said on earnings calls (full-text, verbatim): each hit has the speaker, a snippet and a link to the moment, plus the ticker and quarter key for get_transcript. Use it for 'what did the CEO say about X'. Only calls with a published transcript are searched (about 300 quarters); for themes across all companies, use search_earnings. Filler words are ignored; when every word together finds little, hits with any of the words are added.

Input parameters:

- `limit` (integer): Number of results, 1-20, default 10
- `query` (string, required): Words or a question; filler words are ignored
- `ticker` (string): Only this company: ticker or name

Output parameters:

- `match` (string)
- `note` (string)
- `results` (array)

### `search_earnings` (~161 tokens)

Search earnings notes

Themes across companies' summarised results (all ~400 companies, not only those with transcripts): takeaways, outlook statements, management quotes and analyst questions with answers, newest-ranked by relevance. Use it for 'which companies talk about tariffs / AI capex / deposit costs'. Filter by ticker and kind. Filler words are ignored; when every word together finds little, hits with any of the words are added.

Input parameters:

- `kind` (string): Only takeaways, outlook statements, management quotes or analyst questions
- `limit` (integer): Number of results, 1-20, default 10
- `query` (string, required): Words or a question; filler words are ignored
- `ticker` (string): Only this company: ticker or name

Output parameters:

- `match` (string)
- `note` (string)
- `results` (array)

### `list_recent` (~87 tokens)

List recent results

Quarterly results reported in the last N days (default 14, up to 120), newest first, with the ticker and quarter key for get_quarter. limit 1-100, default 25.

Input parameters:

- `days` (integer): Days back, 1-120, default 14
- `limit` (integer): Number of results, 1-100, default 25

Output parameters:

- `note` (string)
- `results` (array)

## Diagnostics

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

## Score history

- 2026-11-22: 79
- 2026-11-21: 79
- 2026-11-20: 78
- 2026-11-19: 78
- 2026-11-18: 77
- 2026-11-17: 77
- 2026-11-16: 77
- 2026-11-15: 76
- 2026-11-14: 76
- 2026-11-13: 82
- 2026-11-12: 81
- 2026-11-11: 81

## Common questions

### What is the OpenNash Earnings MCP server?

OpenNash Earnings is an MCP server listed in the public MCP registry as com.opennash.earnings/opennash-earnings. Earnings results, outlook, KPIs and call transcripts for ~400 US, Asian and European companies. This page covers its hosted endpoint (https://earnings.opennash.com/mcp).

### Is the OpenNash Earnings MCP server safe to use?

OpenNash Earnings scores 79 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 OpenNash Earnings MCP server expose?

OpenNash Earnings exposes 10 tools: search, fetch, list_companies, get_company, get_kpis, and 5 more. Their descriptions and schemas cost roughly 1,422 tokens of context every time the server is loaded.

### Does the OpenNash Earnings MCP server require authentication?

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

### Is the OpenNash Earnings MCP server still maintained?

OpenNash Earnings is still listed as active in the MCP registry. We last reached this channel on 22 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 OpenNash Earnings MCP server?

VerifyMCP ran 13 checks on OpenNash Earnings, 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://earnings.opennash.com/mcp
- Website: https://earnings.opennash.com/agents/
- Changelog RSS feed: https://verifymcp.io/servers/com-opennash-earnings-opennash-earnings/earnings.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-opennash-earnings-opennash-earnings/earnings/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-opennash-earnings-opennash-earnings/earnings.json
- HTML version of this page: https://verifymcp.io/servers/com-opennash-earnings-opennash-earnings/earnings
