Mindgard website screenshot

Mindgard

Mindgard is a UK-based offensive AI security company (London/Lancaster, spun out of Lancaster University) that provides an automated AI red-teaming and security testing platform for large language models, AI agents, and generative AI systems. Mindgard's platform combines AI Discovery and Recon (mapping the AI attack surface and shadow AI usage), continuous AI Red Teaming against evolving attacker techniques, AI Assessment, AI Runtime Protection, and Model Scanning, backed by a research-led attack library covering jailbreaks (ActorAttack, Crescendo, EvilConfidant, PersonGPT, DevModeV2, AsciiArtAttack, AntiGPT), prompt-injection techniques (Ascii85, AnsiEscaped, AnsiRaw and others), and policy/violation testing (MaliciousGeneration, PromptAlignment). Developers and security teams integrate Mindgard via a public REST API (projects, tests, multi-turn tests, datasets, findings, reconnaissance), a Python CLI (`pip install mindgard`), a Python SDK, a Burp Suite extension, and a GitHub Action for adding red-team checks to MLOps pipelines. The company also maintains and contributes to open-source security tooling including PyRIT integrations, an OpenAI-compatible LLM-Guard proxy, a chatbot API wrapper for testing web chatbots, and proof-of-concept vulnerability demonstrations (document RCE in LangChain agents, hidden audio jailbreaks, prompt-jailbreak demos). Mindgard's commercial model is enterprise SaaS with platform and services tiers; pricing is gated behind a sales conversation, and the platform is positioned for security, AppSec, and AI governance teams testing customer-facing or internally deployed AI systems.

Mindgard is profiled on the APIs.io network. Tagged areas include AI Security, AI Red Teaming, LLM Security, Generative AI Security, and Prompt Injection.

Mindgard’s developer surface includes documentation, API reference, GitHub presence, engineering blog, and 22 more developer resources.

🌐 Visit website 📡 Source on GitHub
9.5/100 minimal ▬ flat Agent 0/100 human only Full breakdown ↓
scored 2026-09-08 · rubric v0.20.0
0 APIs
AI SecurityAI Red TeamingLLM SecurityGenerative AI SecurityPrompt InjectionJailbreak TestingAI DiscoveryAI Runtime ProtectionModel ScanningAI GovernanceOffensive SecurityMLOps

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-09-08 · rubric v0.20.0
Composite quality — 9.5/100 · minimal
Contract Quality 0.0 / 25
Developer Ergonomics 3.8 / 20
Access Clarity 0.0 / 20
Operational Transparency 0.7 / 13
Contract Governance 0.0 / 12
Discoverability 5.0 / 10
Agent readiness — 0/100 · human only
Machine-Readable Contract 0 / 18
Agentic Access Contract 0 / 10
Documented Reversibility 0 / 6
MCP Server 0 / 12
Machine-Readable Auth 0 / 10
Idempotency 0 / 9
Stable Error Semantics 0 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 0 / 7
Typed Event Surface 0 / 6
Agent Skills 0 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
A2A Agent Card 0 / 8
Dry-Run / Simulate Mode 0 / 4
Delegated User Identity 0 / 6
Protected Resource Metadata 0 / 5
Registration Without a Human 0 / 6
Agentic Commerce Well-Known Document 0 / 5
Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero: never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and several others — scorable at all.
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/mindgard: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

Security Posture 1

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

Mindgard Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Documentation 3

Reference material describing how the API behaves

Documentation
Documentation
 APIReference
APIReference
 CLIReference
CLIReference

Design & Contract 1

Pagination, idempotency, versioning, errors, and events

WorkflowIntegrations
WorkflowIntegrations

Build 6

SDKs, sample code, and the tooling you integrate with

PythonSDK
PythonSDK
 AttackLibrary
AttackLibrary
 RemediationLibrary
RemediationLibrary
 GitHub
GitHub
 BurpExtension
BurpExtension
 GitHubAction
GitHubAction

Access & Security 2

Authentication, authorization, and security posture

DomainSecurity
DomainSecurity
 Disclosures
Disclosures

Learn 1

Tutorials, courses, talks, and written guidance

AIAcademy
AIAcademy

Operate 1

Status, limits, changes, and where to get help

Contact
Contact

Company 6

The organization behind the API

Website
Website
 Careers
Careers
 About
About
 LinkedIn
LinkedIn
 Twitter
Twitter
 Blog
Blog

Other 6

Properties that don't map to a standard resource type

Platform
Platform
 EnterpriseSetup
EnterpriseSetup
 PyPI
PyPI
 Research
Research
 Customers
Customers
 Services
Services

Source (apis.yml)

apis.yml Raw ↑ 
aid: mindgard
name: Mindgard
description: Mindgard is a UK-based offensive AI security company (London/Lancaster, spun out of Lancaster University) that
  provides an automated AI red-teaming and security testing platform for large language models, AI agents, and generative
  AI systems. Mindgard's platform combines AI Discovery and Recon (mapping the AI attack surface and shadow AI usage), continuous
  AI Red Teaming against evolving attacker techniques, AI Assessment, AI Runtime Protection, and Model Scanning, backed by
  a research-led attack library covering jailbreaks (ActorAttack, Crescendo, EvilConfidant, PersonGPT, DevModeV2, AsciiArtAttack,
  AntiGPT), prompt-injection techniques (Ascii85, AnsiEscaped, AnsiRaw and others), and policy/violation testing (MaliciousGeneration,
  PromptAlignment). Developers and security teams integrate Mindgard via a public REST API (projects, tests, multi-turn tests,
  datasets, findings, reconnaissance), a Python CLI (`pip install mindgard`), a Python SDK, a Burp Suite extension, and a
  GitHub Action for adding red-team checks to MLOps pipelines. The company also maintains and contributes to open-source security
  tooling including PyRIT integrations, an OpenAI-compatible LLM-Guard proxy, a chatbot API wrapper for testing web chatbots,
  and proof-of-concept vulnerability demonstrations (document RCE in LangChain agents, hidden audio jailbreaks, prompt-jailbreak
  demos). Mindgard's commercial model is enterprise SaaS with platform and services tiers; pricing is gated behind a sales
  conversation, and the platform is positioned for security, AppSec, and AI governance teams testing customer-facing or internally
  deployed AI systems.
type: Index
deliveryModel:
  model: unknown
  open_source: false
  commercial: false
  callable_host: false
  label: Delivery model not determined — needs a product licence on record
  confidence: low
  source:
  - none
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source: []
  generated: '2026-07-22'
  method: derived
position: Producing
access: 3rd-Party
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/mindgard.png
tags:
- AI Security
- AI Red Teaming
- LLM Security
- Generative AI Security
- Prompt Injection
- Jailbreak Testing
- AI Discovery
- AI Runtime Protection
- Model Scanning
- AI Governance
- Offensive Security
- MLOps
url: https://raw.githubusercontent.com/api-evangelist/mindgard/refs/heads/main/apis.yml
created: '2026-05-25'
modified: '2026-05-25'
specificationVersion: '0.23'
apis: []
common:
- type: DomainSecurity
  url: security/mindgard-domain-security.yml
- type: Website
  url: https://mindgard.ai
- type: Platform
  url: https://mindgard.ai/platform
- type: Documentation
  url: https://docs.mindgard.ai
- type: APIReference
  url: https://docs.mindgard.ai/api-reference/projects/list-projects
- type: CLIReference
  url: https://docs.mindgard.ai/user-guide/cli-reference
- type: PythonSDK
  url: https://docs.mindgard.ai/user-guide/python-sdk
- type: AttackLibrary
  url: https://docs.mindgard.ai/attack-library/jailbreaks/overview
- type: RemediationLibrary
  url: https://docs.mindgard.ai/remediation-library/anonymization-of-data
- type: WorkflowIntegrations
  url: https://docs.mindgard.ai/user-guide/workflow-integrations
- type: EnterpriseSetup
  url: https://docs.mindgard.ai/user-guide/enterprise-setup
- type: GitHub
  url: https://github.com/Mindgard
- type: PyPI
  url: https://pypi.org/project/mindgard/
- type: BurpExtension
  url: https://github.com/Mindgard/mindgard-burp-extension
- type: GitHubAction
  url: https://github.com/Mindgard/mindgard-github-action-example
- type: Research
  url: https://mindgard.ai/blog
- type: Customers
  url: https://mindgard.ai/customers
- type: Disclosures
  url: https://mindgard.ai/disclosures
- type: Services
  url: https://mindgard.ai/services
- type: AIAcademy
  url: https://mindgard.ai/ai-academy
- type: Careers
  url: https://mindgard.ai/careers
- type: Contact
  url: https://mindgard.ai/contact
- type: About
  url: https://mindgard.ai/about
- type: LinkedIn
  url: https://www.linkedin.com/company/mindgard
- type: Twitter
  url: https://twitter.com/mindgardai
- type: Blog
  url: https://mindgard.ai/blog
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com

Work with this as data

Every provider 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 providers

9 MCP tools reach this
  • find_providersBrowse and filter every provider in the catalog.
  • get_provider_artifactsEvery artifact this provider publishes, grouped by type.
  • get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
  • get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
  • get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
  • get_provider_ratingPRO — composite, band, trend and facet scores.
  • 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 provider 
curl "https://apis.io/api/v1/providers/mindgard"
All providers 
curl "https://apis.io/api/v1/providers?limit=25"
Every operation they expose 
curl "https://apis.io/api/v1/providers/mindgard/operations?limit=25"
How their score was established 
curl "https://apis.io/api/v1/providers/mindgard/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

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. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.