Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
find_apisBrowse and filter every API in the catalog.
get_api_artifactsOne API's artifacts, grouped by type.
get_openapiThe primary OpenAPI for this API.
find_similar_apisAPIs that look like this one.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.
All 92 tools →
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/nexusquantum-legal:nexusquantum-legal-byo-screening-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we
store it to create your key and to recognise you if you sign in with another
provider. By signing up you are subscribing to the APIs.io and API Evangelist
newsletters — you can unsubscribe from any issue. See our
Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: Nexus Legal BYO Screening API
version: 1.95.0
description: 'Multi-jurisdictional legal analysis API with a multi-agent architecture and Zero Retention. ## Output language
`language` (and the language implied by the jurisdiction) sets the language the text is written in. For `es` and `en` the delivered text is also measured: when a substantial part of it came back in the other of the two, a block headed `⚠️ LANGUAGE OF THIS REPORT` (`⚠️ IDIOMA DE ESTE INFORME` when `es` was requested) is added at the end of the text. It works the same with any engine, BYO included. - **When there is no block**: it is not a confirmation. Other languages are not measured, and neither is a text too short or too mixed to tell. - **With BYO**: how closely the output follows the request depends on your engine. - **If the output language is essential to your workflow**: check it on your side against the `analysis` string. ## The verdict travels INSIDE the text — read this before you parse a response
Every string this API returns that a lawyer reads — `analysis`, `answer`, `report`, `draft`, `synthesisText`, and the string fields of structured results like `applicableLaw[]` — carries the citation verdict **inline**, not only in the `citationChecks` object beside it. **What you will actually see:**
```
An acknowledgement does not revive a claim already barred: section 29(7) of the
Limitation Act 1980 【✓】. See also [2019] EWHC 3556 (Comm)
【◻ not checked — the reason is in this citation''s note】. ---
DETERMINISTIC CITATION CHECK (against the official corpus)
1 verified · 1 not checked. ◻ **Not checked** — they were not compared against any official corpus…
```
- **Inline marker**: a `【…】` block immediately after each citation, in the response language. The glyph carries the verdict: `✓` verified · `⚠` a warning (e.g. the decision exists but a party you named does not appear in it) · `⛔` broken · `◻` not checked. - **Footer**: a `---` block at the end with the tally and, for anything not clean, the list of citations and why. **Why it is in the text and not only in the JSON.** Whoever copies an answer into an email, a brief or a .docx takes the PROSE. The `citationChecks` object does not travel with it. A verdict that only exists in a field beside the text is a verdict the reader can lose without noticing. **If you parse these strings**: markers are the only `【…】` sequences we emit, so they are safe to strip with a single regex if your pipeline needs the raw prose — but do not strip them from anything a human will read. `citationChecks` remains the machine-readable source of truth for counts and per-citation status; the markers are the same verdict, placed where it cannot get lost. **Idempotent**: annotating an already-annotated text does not duplicate markers or the footer. ## Streaming: `verifiedText` on the `done` event
On SSE routes the client already holds the raw prose by the time the verifier finishes, so the closing `{type:"done"}` event carries `verifiedText`: the same answer with the verdict already in it. **If it is present, render it in place of the concatenated `text_delta` chunks.** It is omitted when there is nothing to annotate, in which case the deltas are already final. The REST wrappers do this for you — `/v1/consulta`, `/v1/chat` and the rest aggregate server-side and hand you the annotated text — so this only concerns you if you consume the SSE stream directly. ## Base capabilities
- **Mode=deep**: the Node A (Claude Opus 4.7) + Node B (DeepSeek V4-Pro) chain audits adversarially. 2 credits. Returns an `audit` object with structured findings (hallucinations, false citations, omissions). - **Direct models**: calls through the providers'' own APIs (Anthropic, DeepSeek) with no proxies — lower latency, better rate limits. - **Stable Stripe-style error format**: `error.type`, `error.code`, `error.request_id`, `error.details` + backward-compat aliases. ## Errors and rate limits
- **Branch on `error.code`.** A code you do not recognise is handled by its `error.type`.'
contact:
name: Nexus Legal
email: support@nexusquantum.legal
url: https://legal.nexusquantum.legal/developers
license:
name: Commercial
url: https://nexusquantum.legal/terms
servers:
- url: https://legal.nexusquantum.legal
description: Production
security:
- ApiKeyAuth: []
tags:
- name: BYO-Screening
paths:
/api/v1/screening-providers:
get:
tags:
- BYO-Screening
summary: List the firm's sanctions-screening providers (owner-only) · 0 credits
description: 'Lists YOUR firm''s screening providers. It NEVER returns credentials — only `key_fingerprint` and non-secret fields. Returns `effective_provider` as well, so an empty list is not read as ''there is no screening'': without a provider of yours, screening runs LOCALLY against lists downloaded to our infrastructure, and no party name leaves it. Owner-only firm-scoped. Scope: mcp | * (NOT cases).'
responses:
'200':
description: Providers, plus the effective provider and the locally available lists.
content:
application/json:
schema:
$ref: '#/components/schemas/ScreeningProviderList'
operationId: getApiV1ScreeningProviders
x-operation-id-source: derived
post:
tags:
- BYO-Screening
summary: Register YOUR sanctions-screening provider (owner-only) · 0 credits
description: 'Registers a screening provider under YOUR contract. Why it has to be yours and not ours: screening needs the parties'' REAL names, before anonymisation — a sanctions list does not match `[PERSON_1]`. Sending those names to a third party is a transfer of personal data, and whoever contracts it has to be whoever answers for it. There is therefore NO provider of ours that calls a third party, and its absence is the design. The credential is WRITE-ONLY (AES-256-GCM, never returned). `base_url` is validated against SSRF. Scope: mcp | * (NOT cases).'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/CreateScreeningProviderRequest'
responses:
'201':
description: Provider created (no credential in the response).
content:
application/json:
schema:
$ref: '#/components/schemas/ScreeningProvider'
'400':
description: MISSING_LABEL · MISSING_BASE_URL · MISSING_API_KEY · UNSUPPORTED_KIND · UNSAFE_BASE_URL · INVALID_LISTS · MISPLACED_CREDENTIAL (the credential was sent under another name) · INVALID_JSON
'409':
description: LABEL_ALREADY_EXISTS (a provider with that label already exists for this firm)
'503':
description: CIPHER_UNAVAILABLE — credential encryption is not configured on this deployment. The secret is NOT stored in the clear 'until it is configured'.
operationId: postApiV1ScreeningProviders
x-operation-id-source: derived
/api/v1/screening-providers/{id}:
patch:
tags:
- BYO-Screening
summary: Enable/disable a screening provider or update its declared lists (owner-only) ·…
description: 'Partial update. The CREDENTIAL IS NOT EDITABLE here: to rotate it, delete the provider and create it again, which leaves a trace instead of silently mutating a third party''s key.'
parameters:
- name: id
in: path
required: true
schema:
type: string
format: uuid
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/UpdateScreeningProviderRequest'
responses:
'200':
description: Provider updated (no credential).
content:
application/json:
schema:
$ref: '#/components/schemas/ScreeningProvider'
'400':
description: CREDENTIAL_NOT_EDITABLE · INVALID_ENABLED · INVALID_LISTS · NOTHING_TO_UPDATE · INVALID_JSON
'404':
description: NOT_FOUND (does not exist or does not belong to your firm)
operationId: patchApiV1ScreeningProvidersById
x-operation-id-source: derived
delete:
tags:
- BYO-Screening
summary: Withdraw a screening provider (owner-only) · 0 credits
description: 'Screening is NOT switched off by this: it returns to LOCAL matching. That is the return to the default, not a gap. The response states it in `effective_provider`.'
parameters:
- name: id
in: path
required: true
schema:
type: string
format: uuid
responses:
'200':
description: 'Withdrawn. `effective_provider` says what you fall back TO, and it is looked up rather than assumed: `local` when local lists are populated, `none` when they are not and screening therefore returns nothing.'
content:
application/json:
schema:
type: object
properties:
deleted:
type: string
format: uuid
effective_provider:
type: string
enum:
- local
- none
requestId:
type: string
'404':
description: NOT_FOUND
operationId: deleteApiV1ScreeningProvidersById
x-operation-id-source: derived
components:
schemas:
UpdateScreeningProviderRequest:
type: object
description: 'Partial update. The CREDENTIAL CANNOT BE UPDATED HERE: silently mutating a third party''s key leaves the row with the same creation date and the same label, and nobody knows when it changed or who changed it. Delete and recreate instead, which leaves a trace. Sending `api_key` returns CREDENTIAL_NOT_EDITABLE.'
properties:
enabled:
type: boolean
lists:
type: array
items:
type: string
ScreeningProviderList:
type: object
description: 'List response. `effective_provider` exists so an EMPTY `data` is not ambiguous: without a provider of yours, screening does not stop existing — it runs against local lists; and if those are not populated either, it is not ''configure one'', it is ''not offered yet''.'
properties:
data:
type: array
items:
$ref: '#/components/schemas/ScreeningProvider'
effective_provider:
type: string
enum:
- byo
- local
- none
description: '`byo` = a provider of yours is enabled · `local` = matched against lists downloaded to our infrastructure, no name leaves it · `none` = local lists are not populated in this deployment, so screening returns nothing at all.'
local_lists:
type: array
items:
type: string
description: Lists available for local matching. Empty when `effective_provider` is `none`.
requestId:
type: string
ScreeningProvider:
type: object
description: 'The firm''s OWN sanctions-screening provider (BYO). Non-secret projection: it NEVER returns the credential, only `key_fingerprint`. Firm-scoped, bound to the key''s `firm_owner_id`.'
properties:
id:
type: string
format: uuid
label:
type: string
description: How you will recognise this provider later (1–60).
kind:
type: string
enum:
- opensanctions_compatible
description: Shape of the provider's API. Covers any endpoint exposing an equivalent /match.
base_url:
type: string
description: Your provider's endpoint (validated against SSRF).
key_fingerprint:
type:
- string
- 'null'
description: 'NON-reversible hash of the credential (e.g. `sha256:a1b2c3d4`). Not head+tail: on a short key, showing start and end reveals almost all of it. The credential itself NEVER leaves.'
lists:
type: array
items:
type: string
description: 'The lists YOU declare as contracted. Shown to the reader verbatim. We do NOT verify them: the report says ''according to what your provider covers'', never ''this is covered''.'
enabled:
type: boolean
last_verified_at:
type:
- string
- 'null'
format: date-time
created_at:
type: string
format: date-time
updated_at:
type: string
format: date-time
CreateScreeningProviderRequest:
type: object
required:
- label
- base_url
- api_key
description: 'Registers YOUR screening provider, under YOUR contract. `api_key` is WRITE-ONLY: it travels in the body, is encrypted AES-256-GCM and is never returned. Sending it under any other name (`apiKey`, `token`, `key`…) is rejected with MISPLACED_CREDENTIAL rather than stored without it: the row would be created credential-less and fail on its first call with a transport error that says nothing about why.'
properties:
label:
type: string
description: Required, 1–60 characters.
kind:
type: string
enum:
- opensanctions_compatible
description: Default `opensanctions_compatible`.
base_url:
type: string
description: Required; validated against SSRF.
api_key:
type: string
description: WRITE-ONLY. Required. Never returned.
lists:
type: array
items:
type: string
description: Up to 20 entries, 80 characters each.
enabled:
type: boolean
description: Default true.
securitySchemes:
ApiKeyAuth:
type: http
scheme: bearer
bearerFormat: nlk_...