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.

ShockAtlas

REMOTE · SHOCKATLAS.COM

Economic exposure to climate and geopolitical shocks: signals, data series, reviewed dossiers.

Available components

+3 this week 75 Trust /100

Last scanned (21 hours ago)

Scores higher than 62% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Data and Analytics

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 Usability58
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1590 tokens (~159/item across 10 items; 10 tools + 0 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 Management47
  • Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage78
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 35% of tool parameters carry a description.Partial
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 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 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.

  • 20 Nov 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “get_offers” rewrote its description, which is the text the model reads security
  • 18 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 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 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.

  • 14 Nov 26 +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.

  • 12 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: 1272 → 1526 ▼ functional
    • New tool “get_watch” functional
  • 11 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 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.

  • 8 Nov 26 0
    • Stability: unverified → 0.03 ▲ functional
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 21 Nov 2026 · Probed https://shockatlas.com/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.shockatlas.com CN=YR1,O=Let's Encrypt,C=US 31 Oct 2026 29 Jan 2027 RSA 2048 SHA256-RSA 6c8e68d4e55487d7761bcc21ad2f9113a1d
SANs: *.shockatlas.com, shockatlas.com
CN=YR1,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA a20253f15f2691c05dc1ce13b9bcca4e
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of shockatlas.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
shockatlas.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=63072000
x-content-type-options nosniff
x-frame-options DENY
referrer-policy no-referrer
permissions-policy camera=(), microphone=(), geolocation=()

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://shockatlas.com/api/mcp Verified 200
http (plaintext) http://shockatlas.com/api/mcp HTTPS enforced 308 https://shockatlas.com/api/mcp
MCP tools · 10 exposed · ~1,159 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
get_dossier ~135

The dossier. Without a key, a preview: the question, the causal chain as link ends with a status per link (observed, consistent, untested, contradicted), two constants with their source quotes, the review verdict, and counts for the rest (constants, constraints, alternatives, conjectures, trajectories). A member key opens the complete dossier: every constant, bounded constraints, alternatives with their discriminators, checks, falsifiers, paths and implications.

NameTypeReqDescription
keystring–A member key (dfk1…), issued with the plan; omit it for the free sample
slugstringyes–

No output schema declared.

No examples provided.

get_edition ~76

The published edition in full: title, lead, the "In 30 seconds" brief when the edition has one, the three vectors, the text blocks with each paragraph labelled FACT, HYPOTHESIS or SCENARIO, the indicators to watch, and the figures recomputed at build time.

NameTypeReqDescription
slugstringyes–

No output schema declared.

No examples provided.

get_export ~94

With a member key: three signed links, valid seven days, to the complete export of one signal (bundle.json with the full dossier, counter-analysis and every series; organisations.csv; series.csv). Without a key it answers MEMBER_KEY_REQUIRED with the Premium plan.

NameTypeReqDescription
keystring–A member key (dfk1…), issued with the plan; omit it for the free sample
slugstringyes–

No output schema declared.

No examples provided.

get_offers ~65

What is for sale and how a person pays: one analysis as files, paid once (a checkout link per analysis that you can hand to your user), and Premium, 49 USD per month, every published analysis with a member key. An agent cannot pay by itself here.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_organisation ~61

An organisation named in the atlas and every documented exposure it has, across signals: direction (exposed, beneficiary, competitor, adjacent), evidenced or deduced, decision type, and the dated verbatim quote it rests on.

NameTypeReqDescription
slugstringyes–

No output schema declared.

No examples provided.

get_series ~120

One series with its publisher, source URL, SHA-256 of the collected file, licence (rights) and observations: the last twelve without a key (sample: true, observations_total says how many exist), all of them with a member key. A restricted series returns observations_withheld: true and no values for everyone: read it at source_url.

NameTypeReqDescription
keystringyes–
member_keystring–A member key (dfk1…), issued with the plan; omit it for the free sample
slugstringyes–

No output schema declared.

No examples provided.

get_signal ~133

The same object as /api/atlas/<slug>: the signal, every series with its provenance, licence and observations (the last twelve without a key, all of them with a member key), the edition's vectors, figures and watch list, the dated hypotheses, the organisations with their verbatim evidence, the reasoning dossier under analysis (public part, or complete with a member key), the offers, and an access block saying which of the two you got.

NameTypeReqDescription
keystring–A member key (dfk1…), issued with the plan; omit it for the free sample
slugstringyes–

No output schema declared.

No examples provided.

get_watch ~178

Public gauges and trigger feeds read live from their publishers and refreshed every three hours, independent of any analysis: river levels on the Rhine, Danube, Elbe and Mississippi, flow on the Rhône, the official Mississippi stage forecast, orange and red disaster alerts (GDACS) and US sanctions and export-control documents (Federal Register). Without a key each point answers with its latest daily value and its change over seven days; a member key adds thirty daily values and the forecast. Optional filter: group (Rhine, Danube, Elbe, Mississippi, Rhône). Each point names its publisher and licence under sources; a point whose source did not answer carries an error and no value.

NameTypeReqDescription
groupstring––
keystring–A member key (dfk1…), issued with the plan; omit it for the free sample

No output schema declared.

No examples provided.

list_signals ~168

Every published signal: slug, title, date, mechanism, geography codes, series keys with whether their values are redistributable, counts of organisations and hypotheses, the edition title, a summary of the reviewed dossier (verdict, counts, contradicted links) and the URLs to read it. Each signal has its place in the classification tree (domain › sector › chain); the tree itself, with the sectors not covered yet, comes back as taxonomy. Optional filters: q (text in title or slug), mechanism, geography (ISO code), domain and filiere (the sector id; ids from the tree).

NameTypeReqDescription
domainstring––
filierestring––
geographystring––
mechanismstring––
qstring––

No output schema declared.

No examples provided.

subscribe_newsletter ~129

Asks the free weekly edition for one email address. The address receives a single confirmation link and nothing else until its owner clicks it (double opt-in); one request per address per hour. Call it only for a person who asked to receive the editions, and say so with consent: true. The paid plan cannot be subscribed here: get_offers.premium.subscribe_url is where a person signs in and subscribes.

NameTypeReqDescription
consentbooleanyestrue: the owner of this address asked for the editions
emailstringyesThe address of the person who asked for the free weekly

No output schema declared.

No examples provided.

Install

How do I install the ShockAtlas MCP server?

ShockAtlas is a hosted endpoint at https://shockatlas.com/api/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 · shockatlas.com

# add to Claude Code
claude mcp add --transport http com-shockatlas-atlas 'https://shockatlas.com/api/mcp'
Common questions

What is the ShockAtlas MCP server?

ShockAtlas is an MCP server listed in the public MCP registry as com.shockatlas/atlas. Economic exposure to climate and geopolitical shocks: signals, data series, reviewed dossiers. This page covers its hosted endpoint (https://shockatlas.com/api/mcp).

Is the ShockAtlas MCP server safe to use?

ShockAtlas scores 75 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 ShockAtlas MCP server expose?

ShockAtlas exposes 10 tools: list_signals, get_signal, get_edition, get_dossier, get_series, and 5 more. Their descriptions and schemas cost roughly 1,159 tokens of context every time the server is loaded.

Does the ShockAtlas MCP server require authentication?

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

Is the ShockAtlas MCP server still maintained?

ShockAtlas 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 ShockAtlas MCP server?

VerifyMCP ran 13 checks on ShockAtlas, 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.