SandboxAQ

SandboxAQ (SB Technology, Inc.) builds Large Quantitative Models (LQMs) — AI systems that fuse physics, chemistry and proprietary scientific data — and ships them as commercial platforms with public developer surfaces. Three product lines carry callable APIs: AQtive Guard, a cryptography and non-human-identity posture-management platform (built on the Cryptosense analyzer) exposing a GraphQL API at /api/v2 plus a fleet of language and network sensors; Flint AI, an AI-agent security platform whose Platform API is a documented OpenAPI 3.0.3 contract over an inventory graph of agents, models, tools and MCP servers, paired with the flintai CLI and a Python guardrails SDK; and the SandboxAQ MCP Server, a per-tenant OAuth-protected Model Context Protocol endpoint that exposes the AQCat adsorption and AQPotency proteochemometric potency models as tools for LLM clients.

SandboxAQ publishes 1 API on the APIs.io network: Flint AI Platform API. Tagged areas include Company, Artificial Intelligence, Security, Cryptography, and Post-Quantum Cryptography.

SandboxAQ’s developer surface includes documentation, API reference, getting-started guide, engineering blog, support, signup flow, CLI, and 28 more developer resources.

48.3/100 developing ▬ flat Agent 52/100 agent ready Full breakdown ↓
scored 2026-08-05 · rubric v0.9.1
3 APIs 1 MCP Servers
CompanyArtificial IntelligenceSecurityCryptographyPost-Quantum CryptographyAgentsModel Context ProtocolSimulationDrug DiscoveryMaterials ScienceAI SecurityQuantum

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-08-05 · rubric v0.9.1
Composite quality — 48.3/100 · developing
Contract Quality 12.0 / 25
Developer Ergonomics 16.1 / 20
Commercial Clarity 6.8 / 20
Operational Transparency 2.7 / 13
Governance 1.4 / 12
Discoverability 9.3 / 10
Agent readiness — 52/100 · agent ready
Machine-Readable Contract 18 / 18
Agentic Access Contract 10 / 10
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 0 / 7
Typed Event Surface 0 / 6
Agent Skills 5 / 5
Well-Known Catalog 4 / 4
Consent & Bot Identity 0 / 3
A2A Agent Card 8 / 8
Dry-Run / Simulate Mode 0 / 4
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/sandboxaq: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 3

Individual APIs this provider publishes, each with its own machine-readable definition.

Flint AI Platform API

The Flint AI Platform API gives programmatic access to everything the Flint AI Platform discovers about an organization's AI estate: the agents found in code, the models, tools ...

AQtive Guard API

AQtive Guard is SandboxAQ's cryptography and non-human-identity management platform, built on the Cryptosense analyzer it acquired. Its API is GraphQL, served at /api/v2 and aut...

SandboxAQ MCP Server

A fully managed, per-tenant Model Context Protocol server that exposes SandboxAQ's proprietary scientific AI models as callable tools inside Claude and other MCP clients. It car...

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

sandboxaq-mcp.yml

MCP SERVER

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Sandboxaq Authentication

apiKey/oauth2 · 3 schemes

SECURITY

Sandboxaq Domain Security

TLSv1.3 · HSTS · DNSSEC · DMARC

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Sandboxaq Agentic Access

55 operations · 9 acting

55 operations · 9 acting

AGENTIC

Resources

Get Started 3

Portal, sign-up, and the first successful call

Documentation 4

Reference material describing how the API behaves

Agent Surfaces 5

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Build 5

SDKs, sample code, and the tooling you integrate with

Access & Security 2

Authentication, authorization, and security posture

Operate 2

Status, limits, changes, and where to get help

Commercial 2

Pricing, plans, and the legal terms of use

Company 2

The organization behind the API

Other 5

Properties that don't map to a standard resource type

Source (apis.yml)

apis.yml Raw ↑
aid: sandboxaq
name: SandboxAQ
description: 'SandboxAQ (SB Technology, Inc.) builds Large Quantitative Models (LQMs) — AI systems that fuse physics, chemistry
  and proprietary scientific data — and ships them as commercial platforms with public developer surfaces. Three product lines
  carry callable APIs: AQtive Guard, a cryptography and non-human-identity posture-management platform (built on the Cryptosense
  analyzer) exposing a GraphQL API at /api/v2 plus a fleet of language and network sensors; Flint AI, an AI-agent security
  platform whose Platform API is a documented OpenAPI 3.0.3 contract over an inventory graph of agents, models, tools and
  MCP servers, paired with the flintai CLI and a Python guardrails SDK; and the SandboxAQ MCP Server, a per-tenant OAuth-protected
  Model Context Protocol endpoint that exposes the AQCat adsorption and AQPotency proteochemometric potency models as tools
  for LLM clients.'
image: https://cdn.prod.website-files.com/622a3cfaa89636b753810f04/623911fca65004cb868ec3ec_SandboxAQ-social-share.jpg
url: https://raw.githubusercontent.com/api-evangelist/sandboxaq/refs/heads/main/apis.yml
x-type: company
x-source: harvest:secondary-market
specificationVersion: '0.20'
created: '2026-08-02'
modified: '2026-08-02'
tags:
- Company
- Artificial Intelligence
- Security
- Cryptography
- Post-Quantum Cryptography
- Agents
- Model Context Protocol
- Simulation
- Drug Discovery
- Materials Science
- AI Security
- Quantum
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
apis:
- aid: sandboxaq:flint-ai-platform-api
  name: Flint AI Platform API
  description: 'The Flint AI Platform API gives programmatic access to everything the Flint AI Platform discovers about an
    organization''s AI estate: the agents found in code, the models, tools and MCP servers they use, the assets and locations
    behind them, and the issues and rules that apply. The inventory is modelled as a graph, and every entity exposes an edge
    endpoint so callers can traverse from an agent to its models, or from a model back to the agents that call it. Authentication
    is a bearer token created under Settings > API Keys; most paths are scoped to a tenant and a workspace.'
  humanURL: https://docs.flintai.dev/flintai/api-reference/index
  baseURL: https://your-instance.flintai.dev/api/v1
  tags:
  - AI Security
  - Agents
  - Inventory
  - Governance
  - Model Context Protocol
  properties:
  - type: OpenAPI
    url: openapi/sandboxaq-flint-ai-platform-openapi.json
  - type: Documentation
    url: https://docs.flintai.dev/
  - type: APIReference
    url: https://docs.flintai.dev/flintai/api-reference/index
  - type: Authentication
    url: authentication/sandboxaq-authentication.yml
  - type: Overlay
    url: overlays/sandboxaq-flint-ai-platform-overlay.yaml
  - type: ErrorCatalog
    url: errors/sandboxaq-problem-types.yml
  - type: DataModel
    url: data-model/sandboxaq-data-model.yml
- aid: sandboxaq:aqtive-guard-api
  name: AQtive Guard API
  description: AQtive Guard is SandboxAQ's cryptography and non-human-identity management platform, built on the Cryptosense
    analyzer it acquired. Its API is GraphQL, served at /api/v2 and authenticated with an API-KEY header. The published schema
    covers projects, traces, analysis reports, cryptographic instances, keys, certificates, ciphersuites, TLS and SSH handshakes,
    scans, rules, vulnerabilities and slots, plus mutations for the Jira, ServiceNow, CrowdStrike, Tanium and Venafi integrations.
    Sensors (Java, Python, .NET, OpenSSL and PKCS#11 tracers, filesystem and bytecode scanners, a network analyzer) feed traces
    into it, and the cs-api CLI wraps the upload-and-analyze flow.
  humanURL: https://aqtiveguard.sandboxaq.com/docs/api/
  baseURL: https://aqtiveguard.sandboxaq.com/api/v2
  tags:
  - Cryptography
  - Security
  - Post-Quantum Cryptography
  - Certificates
  - Non-Human Identity
  properties:
  - type: GraphQL
    url: graphql/sandboxaq-aqtive-guard.graphql
  - type: Documentation
    url: https://aqtiveguard.sandboxaq.com/docs/
  - type: APIReference
    url: https://aqtiveguard.sandboxaq.com/docs/api/reference/
  - type: GettingStarted
    url: https://aqtiveguard.sandboxaq.com/docs/getting-started/
  - type: ChangeLog
    url: https://aqtiveguard.sandboxaq.com/docs/changelog/
  - type: CLI
    url: cli/sandboxaq-cli.yml
- aid: sandboxaq:mcp-server
  name: SandboxAQ MCP Server
  description: A fully managed, per-tenant Model Context Protocol server that exposes SandboxAQ's proprietary scientific AI
    models as callable tools inside Claude and other MCP clients. It carries the aqcat tool (dense adsorption energy screening
    powered by the AQCat25-EV2 machine-learning potential) and the four AQPotency tools (single-pair potency prediction, library
    screening, panel scanning and selectivity) built on a proteochemometric model. Transport is Streamable HTTP; authentication
    is OAuth only — no static API keys are issued or accepted.
  humanURL: https://docs.aisim.sandboxaq.com/mcp
  baseURL: https://mcp.{tenant}.aisim.sandboxaq.com
  tags:
  - Model Context Protocol
  - Agents
  - Simulation
  - Drug Discovery
  - Materials Science
  properties:
  - type: MCPServer
    url: mcp/sandboxaq-mcp.yml
  - type: ToolCrosswalk
    url: mcp/sandboxaq-tool-crosswalk.yml
  - type: Documentation
    url: https://docs.aisim.sandboxaq.com/mcp
common:
- type: AgenticAccess
  url: agentic-access/sandboxaq-agentic-access.yml
- type: DomainSecurity
  url: security/sandboxaq-domain-security.yml
- type: Website
  url: https://www.sandboxaq.com/
- type: DeveloperPortal
  url: https://docs.flintai.dev/
- type: Documentation
  url: https://docs.flintai.dev/
- type: APIReference
  url: https://docs.flintai.dev/flintai/api-reference/index
- type: GettingStarted
  url: https://docs.flintai.dev/flintai/cli/guides/scan-quickstart
- type: Blog
  url: https://www.sandboxaq.com/blog
- type: GitHubOrganization
  url: https://github.com/sandbox-quantum
- type: Support
  url: https://docs.aisim.sandboxaq.com/contact
- type: SignUp
  url: https://www.sandboxaq.com/
- type: TermsOfService
  url: https://www.sandboxaq.com/legal/terms-conditions
- type: PrivacyPolicy
  url: https://www.sandboxaq.com/legal/privacy-policy
- type: Products
  url: https://www.sandboxaq.com/products
- type: SecondaryMarket
  url: https://www.hiive.com/securities/sandboxaq-stock
- type: OpenAPI
  url: openapi/sandboxaq-flint-ai-platform-openapi.json
- type: GraphQL
  url: graphql/sandboxaq-aqtive-guard.graphql
- type: Protobuf
  url: grpc/sandboxaq-sandwich-sandwich.proto
- type: AgentCard
  url: a2a/sandboxaq-a2a.yml
- type: AgentSkill
  url: skills/_index.yml
- type: LLMsTxt
  url: llms/sandboxaq-llms.txt
- type: MCPServer
  url: mcp/sandboxaq-mcp.yml
- type: ToolCrosswalk
  url: mcp/sandboxaq-tool-crosswalk.yml
- type: Packages
  url: packages/sandboxaq-packages.yml
- type: SDKs
  url: packages/sandboxaq-packages.yml
- type: CLI
  url: cli/sandboxaq-cli.yml
- type: WellKnown
  url: well-known/sandboxaq-well-known.yml
- type: Conventions
  url: conventions/sandboxaq-conventions.yml
- type: Conformance
  url: conformance/sandboxaq-conformance.yml
- type: ErrorCatalog
  url: errors/sandboxaq-problem-types.yml
- type: Authentication
  url: authentication/sandboxaq-authentication.yml
- type: Lifecycle
  url: lifecycle/sandboxaq-lifecycle.yml
- type: ChangeLog
  url: changelog/sandboxaq-changelog.yml
- type: DataModel
  url: data-model/sandboxaq-data-model.yml
- type: Overlay
  url: overlays/sandboxaq-flint-ai-platform-overlay.yaml
x-enrichment:
  date: '2026-08-02'
  status: enriched
  artifacts_added: 39
  pass: local-v1