Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

OpenNash Earnings

REMOTE · EARNINGS.OPENNASH.COM

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

+3 this week 79 Trust /100

Last scanned (44 minutes ago)

Scores higher than 74% of remote servers

Reachable. Last reached 22 Nov 2026.

Category Finance and Payments

Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Endpoint Security80
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • 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. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability79
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • 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. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management37
  • Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +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.

  • 19 Nov 26 +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.

  • 16 Nov 26 +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.

  • 14 Nov 26 −6
    • 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 security
    • Schema quality: pass → fail ▼ functional
    • Tool coverage: 71% → 100% ▲ functional
    • Server version: 1.1.0 → 1.2.0 functional
    • “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” cosmetic
  • 13 Nov 26 +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.

  • 12 Nov 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 11 Nov 26 81

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 22 Nov 2026 · Probed https://earnings.opennash.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=opennash.com CN=WE1,O=Google Trust Services,C=US 10 Nov 2026 8 Feb 2027 ECDSA 256 ECDSA-SHA256 56a8ad784e89fb920e3e2db5fb659f7f
SANs: opennash.com, *.opennash.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of earnings.opennash.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
opennash.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
content-security-policy frame-ancestors 'self'; base-uri 'self'; object-src 'none'
x-content-type-options nosniff
referrer-policy strict-origin-when-cross-origin
permissions-policy geolocation=(), microphone=(), camera=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://earnings.opennash.com/mcp Verified 200
http (plaintext) http://earnings.opennash.com/mcp HTTPS enforced 308 https://earnings.opennash.com/mcp
MCP tools · 10 exposed · ~1,422 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
fetch ~84

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).

NameTypeReqDescription
idstringyesAn id returned by search, such as quarter:NVDA/2027-q2
NameTypeReqDescription
idstringyes–
metadataobjectyes–
textstringyes–
titlestringyes–
urlstringyes–

No examples provided.

get_company ~88

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.

NameTypeReqDescription
tickerstringyesTicker or company name, such as NVDA, Nvidia, BCS or Barclays
NameTypeReqDescription
ciknumber|null––
countrystring|null––
currencystring|null––
exchangestring|null––
fiscal_year_endstring|null––
irstring|null––
kpi_quartersnumberyes–
latest_quarterstring|null––
legal_namestring|null––
namestringyes–
next_expectedstring|null––
notestring––
quartersarrayyes–
sectorstring|null––
tickerstringyes–
urlstringyes–

No examples provided.

get_kpis ~165

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).

NameTypeReqDescription
limitinteger–Number of quarters, 1-16, default 16
metricstring–One metric, or omit for all
tickerstringyesTicker or company name, such as NVDA, Nvidia, BCS or Barclays
NameTypeReqDescription
currencystringyes–
namestringyes–
notestringyes–
quartersarrayyes–
tickerstringyes–

No examples provided.

get_quarter ~181

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.

NameTypeReqDescription
quarterstring–Fiscal quarter key from get_company, such as 2027-q2. Omit for the latest.
sectionsarray–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
tickerstringyesTicker or company name, such as NVDA, Nvidia, BCS or Barclays
NameTypeReqDescription
currencystring|null––
documents–––
filedstringyes–
filing_urlstringyes–
fynumberyes–
guidance–––
guidance_check–––
has_transcriptbooleanyes–
headlinestring|null––
keystringyes–
labelstringyes–
metrics–––
notestring––
overviewarray––
period_endstringyes–
qnumberyes–
qa–––
qa_totalnumber––
quarterstringyes–
questions–––
quotes–––
recording–––
segments–––
takeaways–––
tickerstringyes–
topics–––
urlstringyes–

No examples provided.

get_transcript ~169

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.

NameTypeReqDescription
limitinteger–Number of paragraphs, 1-150, default 40
offsetinteger–Where to start, default 0; pass next_offset from the previous page
quarterstring–Fiscal quarter key from get_company, such as 2027-q2. Omit for the latest.
tickerstringyesTicker or company name, such as NVDA, Nvidia, BCS or Barclays
NameTypeReqDescription
labelstringyes–
next_offsetnumber|null––
notestring––
offsetnumber––
paragraphsarrayyes–
quarterstringyes–
recordingstring|null––
tickerstringyes–
totalnumberyes–
transcript_quartersarray––
urlstringyes–

No examples provided.

list_companies ~201

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.

NameTypeReqDescription
countrystring–Home country, such as United States, Singapore or United Kingdom
limitinteger–Number of companies, 1-200, default 50
offsetinteger–Where to start, default 0; pass next_offset from the previous page
querystring–Words in the name, ticker, sector, country or exchange, such as 'bank singapore' or 'Barclays'
sectorstring–Sector, such as Banking, Insurance, Semiconductors or Software; loose matches work ('Banks')
NameTypeReqDescription
next_offsetnumber|null––
notestring––
offsetnumberyes–
resultsarrayyes–
totalnumberyes–

No examples provided.

list_recent ~87

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.

NameTypeReqDescription
daysinteger–Days back, 1-120, default 14
limitinteger–Number of results, 1-100, default 25
NameTypeReqDescription
notestring––
resultsarrayyes–

No examples provided.

search ~129

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.

NameTypeReqDescription
querystringyesA question or words, such as 'What did Nvidia guide for next quarter?'
NameTypeReqDescription
notestring––
resultsarrayyes–

No examples provided.

search_earnings ~161

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.

NameTypeReqDescription
kindstring–Only takeaways, outlook statements, management quotes or analyst questions
limitinteger–Number of results, 1-20, default 10
querystringyesWords or a question; filler words are ignored
tickerstring–Only this company: ticker or name
NameTypeReqDescription
matchstring––
notestring––
resultsarrayyes–

No examples provided.

search_transcripts ~157

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.

NameTypeReqDescription
limitinteger–Number of results, 1-20, default 10
querystringyesWords or a question; filler words are ignored
tickerstring–Only this company: ticker or name
NameTypeReqDescription
matchstring––
notestring––
resultsarrayyes–

No examples provided.

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.

remote · earnings.opennash.com

# add to Claude Code
claude mcp add --transport http com-opennash-earnings-opennash-earnings 'https://earnings.opennash.com/mcp'
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.