Search arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.
Nothing to run from here
Nerai is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
tool-list score
16
tools declared
remote
at its publisher
—
calls last 7d
What it does
Geopolitical grounding for AI agents: country risk scores, 3–12 month forecasts with published out-of-sample validation, early warning, maritime chokepoints (Hormuz, Bab el-Mandeb, Suez) with live traffic, sanctions overview and export-control (TradeControl) changes. Every response carries as_of, source and limitations. Free key in seconds at https://neraicorp.com/ai-agents.html (5 countries, 100 calls/month). Pro €490/month or €4,900/year: all 60 countries, 100k calls, all 13 tools. Enterprise from €15,000/year.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http nerai-mcp https://nerai-mcp.neraicorp.workers.dev/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'
# 2 — ask your agent for something these tools do
# list_countries, get_country_risk, get_causal_drivers and 13 more
It needs AUTHORIZATION (Bearer <key>. Get a free key instantly: POST https://nerai-mcp.neraicorp.workers.dev/register {"email":"you@co.com"}): this sends it in the Authorization header from your environment, so export it first — its endpoint answers 401 without it.
Nerai costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Claude Code reads AUTHORIZATION (Bearer <key>. Get a free key instantly: POST https://nerai-mcp.neraicorp.workers.dev/register {"email":"you@co.com"}) from your environment each time it connects and sends it in the Authorization header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx AUTHORIZATION … and open a new terminal (Windows).
claude mcp add --scope user --transport http nerai-mcp https://nerai-mcp.neraicorp.workers.dev/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'Reconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add — but its publisher asks for a key of their own on every call.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: Authorization header — Bearer <key>. Get a free key instantly: POST https://nerai-mcp.neraicorp.workers.dev/register {"email":"you@co.com"}. You set it in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
16 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
List the 60 countries covered by NERAI's daily risk indices (code + name), plus platform metadata (as-of dates, calibration).
No parameter schema on file.
Full NERAI risk read for one country: HMM regime state (Calm/Tension/Crisis with escalation probability and persistence), resilience score, and risk topics as percentiles of the 30-day average vs each series' own history (now / 90d ago / delta), with calibrated shock probabilities at 4/9/13/26-week horizons. Returns the 8 most elevated topics by default; set all_topics=true for all 40, or pass top
| Parameter | Type | Required | Notes |
|---|---|---|---|
| country | string | yes | Country code (e.g. NI, IR, TU) or name (e.g. Nigeria). |
| all_topics | boolean | no | Return all 40 risk topics instead of the top 8. |
| topic | string | no | Filter to topics matching this text (e.g. 'protest', 'military'). |
NERAI's causal network for a country: Granger-significant lead-lag relationships (p<0.01) showing which risk signals lead which others, with the lag in days and F-statistic. Use to explain WHY a risk is building, not just that it is.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| country | string | yes | Country code or name. |
Platform-wide early warning: the series with the highest calibrated shock probabilities right now, and the biggest 90-day percentile movers (risers and fallers) across all 60 countries. The fastest way to ask 'what should I be watching?'
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | number | no | Max rows per list (default 15, max 40). |
Rank countries on a given risk topic by current percentile, with the 90-day change and regime state. Use for portfolio or footprint screening (e.g. 'rank protest risk across our markets').
| Parameter | Type | Required | Notes |
|---|---|---|---|
| topic | string | yes | Risk topic, e.g. protest, military_clash, political_instability, terrorism. |
| countries | array | no | Optional subset of codes/names; omit to rank all 60. |
| limit | number | no | Max rows (default 15). |
Global supply-chain picture: NY Fed GSCPI (with its required notice), country disruption readings and NERAI's supply-disruption forecast board. Chokepoint transit series are not included in this edition (chokepoint_transits is null).
No parameter schema on file.
Benchmark commodity prices from licensed open sources: U.S. EIA daily spot (Brent, WTI, Henry Hub; public domain) with 7- and 30-day changes, and World Bank Pink Sheet monthly averages (European gas, wheat, maize, urea; CC BY 4.0) with the month-on-month change. Each row carries its source and frequency.
No parameter schema on file.
The sanctions picture in one call: restricted-party register counts by list and type, the Russia shadow-fleet enforcement index, Russia economic-impact measures and recent enforcement actions.
No parameter schema on file.
Chokepoint vessel picture from licensed sources. Live AIS vessel counts are NOT available in this edition (available=false, counts null). Where published, the Strait of Hormuz carries Copernicus Sentinel-1 radar vessel presence (30-day rolling, % vs the 2025 same-orbit baseline): vessels present in radar scenes, not transits.
No parameter schema on file.
Risk state of the 8 monitored maritime corridors (Hormuz, Suez, Red Sea/Bab-el-Mandeb, Black Sea, Malacca, Taiwan Strait, E. Mediterranean, South China Sea): GDELT-based threat/activity scores, phase, news and sanctions intensity, NERAI read. Transit and cost-pressure fields are kept for compatibility but are null in this edition.
No parameter schema on file.
NERAI CHPL circumvention-corridor intensity scores (0-100, ordinal) for Russia-bound diversion routes of controlled microelectronics, with goods and watch items.
No parameter schema on file.
NERAI's open calibrated forecasts (binary questions with probabilities and horizons) across sanctions, geopolitical risk, chokepoints, maritime, supply-chain and conflict. Every open question is re-scored every 2 days, so each one carries its probability history, the change since it was filed and since the last review, and the reason the latest review gave. Set include_archive to also return close
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | Optional filter: sanctions, geopolitical-risk, chokepoints, maritime, supply-chain, military-conflict or modern-mercantilism. |
| movers_only | boolean | no | Only forecasts repriced by 2pp or more at the latest review. |
| include_archive | boolean | no | Also return closed forecasts (resolved / past horizon / retired). |
Look up an HS code against the Common High Priority List — the goods the US, EU, UK and Japan jointly identify as most frequently diverted. Requires a six-digit code: a four-digit heading returns the CHPL subheadings it contains and asks for HS6, because the goods within one heading differ materially and NERAI does not infer a classification it was not given.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| hs_code | string | yes | HS code, ideally six digits (e.g. 854233). |
Published enforcement actions (ECJU compound settlements, OFSI penalties, BIS denial orders, OFAC civil penalties) that share features with a described shipment. A case qualifies only if it shares the commodity or the behaviour AND the destination or route — shared geography alone is not a precedent. Returns the shared features and a link to the authority's own published action. The score counts s
| Parameter | Type | Required | Notes |
|---|---|---|---|
| product_family | string | no | e.g. Semiconductors & electronics, Aviation & aerospace, Dual-use & military. |
| destination | string | no | — |
| transit | string | no | — |
| red_flag | string | no | e.g. third-country routing, concealment / false documents. |
| include_unreviewed | boolean | no | Include auto-extracted cases. Default false: unreviewed cases must not be quoted to a client. |
What NERAI's transaction layer currently covers: register size and per-source health, enforcement corpus size by authority, CHPL vintage, and which checks require the platform rather than this connector. Use it to know what a full assessment would add.
No parameter schema on file.
Latest official trade-control / sanctions changes from the NERAI TradeControl Action Desk: UK Sanctions List & US CSL diffs and CELEX-anchored EU Official Journal acts, each with legal instrument and source link.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| jurisdiction | string | no | Optional filter: UK, US or EU. |
| limit | number | no | Max records (default 10, max 25). |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Nerai or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 96 / 100
Release 1.1.0 · scanned 20 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digestefd230992efc2ee4fcdfdec1eff71ab136260ee0a249065b77eaea3d4075136e
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_countries | no tags | |
| get_country_risk | no tags | |
| get_causal_drivers | no tags | |
| get_early_warning | no tags | |
| compare_countries | no tags | |
| get_supply_chain_risk | no tags | |
| get_commodities | no tags | |
| get_sanctions_overview | no tags | |
| get_live_chokepoint_traffic | no tags | |
| get_maritime_corridors | no tags | |
| get_circumvention_corridors | no tags | |
| get_forecast_desk | no tags | |
| check_commodity_controls | no tags | |
| find_enforcement_precedent | no tags | |
| get_transaction_intelligence_status | no tags | |
| get_tradecontrol_changes | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestefd230992efc2ee4
Scanned2026-10-20
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.1.0.
1.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Nerai can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.