Patronus Protect

Patronus Protect, from Casdo Labs GmbH, is an on-device AI firewall that detects prompt injection, PII/DLP, sensitive documents and agentic tool risk in text, public HTTPS webpages, documents and MCP servers before they are used by AI agents, RAG pipelines or LLM applications. It exposes a REST Scan API (control.patronus.studio/api/v1), first-party Rust, TypeScript and Python SDK clients, a local CLI with Codex, Claude Code and DeepSeek plugins, a remote OAuth-protected MCP server and a local stdio MCP server, and the open-source Patronus Ark scanning core.

Patronus Protect publishes 1 API contract indexed on the APIs.io network: Scan API. Tagged areas include AI Safety, Prompt Injection, Security, LLM, and Agent-Native.

Patronus Protect’s developer surface includes getting-started guide, pricing, engineering blog, CLI, changelog, and 19 more developer resources.

🌐 Visit website 📡 Source on GitHub

51.6/100 developing ▬ flat Agent 66/100 agent native Front door AI 6/6 dominant Full breakdown ↓
scored 2026-10-09 · rubric v0.23.0

4 published contracts 1 MCP Servers

AI Safety Prompt Injection Security LLM Agent-Native MCP DLP PII On-Device AI Firewall

What this lets a business do 1

Business capabilities this provider's published APIs can perform, derived from its own contracts. Browse all capabilities →

Cybersecurity Management

BC-620

Scan

Kin Score

Kin Score How this is scored →
scored 2026-10-09 · rubric v0.23.0

Composite quality — 51.6/100 · developing

Contract Quality 9.8 / 19

Developer Ergonomics 11.1 / 15

Access Clarity 6.3 / 15

Operational Transparency 3.1 / 10

Contract Governance 1.6 / 9

Discoverability 5.8 / 8

Regulatory Posture 4.5 / 15

Create-or-Update Ergonomics 0.0 / 10

Agent readiness — 66/100 · agent native

Machine-Readable Contract 18 / 18

Agentic Access Contract 0 / 10

Documented Reversibility 0 / 6

MCP Server 12 / 12

Machine-Readable Auth 10 / 10

Idempotency 9 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 7 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 0 / 6

Agent Skills 5 / 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 6 / 6

Protected Resource Metadata 5 / 5

Registration Without a Human 6 / 6

Agentic Commerce Well-Known Document 0 / 5

Regulatory Posture applies to this provider. Its tags matched the Horizontal (data, software, accessibility, platform) regime, so Regulatory Posture carries 15 points of the composite. If this regime is wrong for your business, say so on your provider repo — the applicability map is public and we will correct it.

Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.

The six quality facets above are damped to 75 points between them, because the conditional facet above carries the other 25. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 75% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.

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/patronus-protect: 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 →

APIs 1

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

Patronus Protect Scan API

The Scan API from Patronus Protect — 2 operation(s) for scan.

MCP Servers 1

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

Patronus Protect MCP Server

Patronus ships an MCP server in two deployments. A remote, OAuth-protected MCP server is served at control.patronus.studio/api/mcp (DCR + PKCE, scopes scan:read/scan:write). A l...

MCP SERVER

Pricing Plans 1

Published pricing tiers and plan structures.

Patronus Protect Plans Pricing

4 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Patronus Protect Rate Limits

0 limits

RATE LIMITS

OpenAPI Overlays 1

Overlays applied on top of this provider's contracts. Each card says who wrote it: a document the provider publishes, or one API Evangelist derived or generated.

Patronus Protect Openapi Overlay

3 actions · documentation · patronus-protect-openapi.json

GENERATED

JSON Schema 1

Standalone JSON Schema definitions for this provider's data models.

Patronus local runtime v1 NDJSON frame

0 properties

JSON SCHEMA

Security Posture 3

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

Patronus Protect Authentication

http/oauth2 · 2 schemes

SECURITY

Patronus Protect Domain Security

TLSv1.3 · DMARC

SECURITY

Patronus Protect Vulnerability Disclosure

security.txt · contact published

SECURITY

Scopes 1

OAuth scopes governing access to this provider's APIs.

Patronus Protect Scopes

2 scopes

SCOPES

Resources

Get Started 2

Portal, sign-up, and the first successful call

DeveloperPortal

DeveloperPortal

GettingStarted

GettingStarted

Documentation 1

Reference material describing how the API behaves

JSONSchema

JSONSchema

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

MCPServer

AgentSkill

LLMsTxt

WellKnown

Design & Contract 1

Pagination, idempotency, versioning, errors, and events

Conformance

Conformance

Build 4

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

Packages

SDKs

CLI

Access & Security 4

Authentication, authorization, and security posture

SecurityTxt

SecurityTxt

VulnerabilityDisclosure

VulnerabilityDisclosure

Security

Security

DomainSecurity

DomainSecurity

Operate 2

Status, limits, changes, and where to get help

RateLimits

RateLimits

ChangeLog

ChangeLog

Commercial 2

Pricing, plans, and the legal terms of use

Pricing

Pricing

Plans

Plans

Company 2

The organization behind the API

Website

Website

Blog

Blog

Other 2

Properties that don't map to a standard resource type

CapabilityMap

CapabilityMap

Overlay

Overlay

Source (apis.yml)

name: Patronus Protect
aid: patronus-protect
description: Patronus Protect, from Casdo Labs GmbH, is an on-device AI firewall that detects prompt injection, PII/DLP, sensitive
  documents and agentic tool risk in text, public HTTPS webpages, documents and MCP servers before they are used by AI agents,
  RAG pipelines or LLM applications. It exposes a REST Scan API (control.patronus.studio/api/v1), first-party Rust, TypeScript
  and Python SDK clients, a local CLI with Codex, Claude Code and DeepSeek plugins, a remote OAuth-protected MCP server and
  a local stdio MCP server, and the open-source Patronus Ark scanning core.
url: https://patronus.studio/
created: '2026-09-20'
modified: '2026-09-20'
tags:
- AI Safety
- Prompt Injection
- Security
- LLM
- Agent-Native
- MCP
- DLP
- PII
- On-Device
- AI Firewall
tags_raw:
- AI Safety
- Prompt Injection
- Security
- LLM
- agent-native
- MCP
- DLP
- PII
- On-Device
- AI Firewall
apis:
- aid: patronus-protect:patronus-protect-scan-api
  name: Patronus Protect Scan API
  description: The Scan API from Patronus Protect — 2 operation(s) for scan.
  humanURL: https://docs.patronus.studio/api-reference/
  baseURL: https://control.patronus.studio/api/v1
  tags:
  - Scans
  tags_raw:
  - Scan
  properties:
  - type: OpenAPI
    url: openapi/patronus-protect-scan-api-openapi.yml
  - type: Documentation
    url: https://docs.patronus.studio/api-reference/
  - type: APIReference
    url: https://docs.patronus.studio/api-reference/
  - type: ToolCrosswalk
    url: mcp/patronus-protect-tool-crosswalk.yml
  - type: Authentication
    url: authentication/patronus-protect-authentication.yml
  - type: OAuthScopes
    url: scopes/patronus-protect-scopes.yml
  - type: RateLimits
    url: rate-limits/patronus-protect-rate-limits.yml
  - type: ErrorCatalog
    url: errors/patronus-protect-problem-types.yml
  - type: DataModel
    url: data-model/patronus-protect-data-model.yml
  - type: Conventions
    url: conventions/patronus-protect-conventions.yml
common:
- type: RateLimits
  url: rate-limits/patronus-protect-rate-limits.yml
- type: CapabilityMap
  url: capabilities/patronus-protect-capability-edges.yml
  name: Patronus Protect Business Capability Map
- type: Overlay
  url: overlays/patronus-protect-openapi-overlay.yaml
- type: MCPServer
  url: mcp/patronus-protect-mcp.yml
- type: Website
  url: https://patronus.studio/
- type: DeveloperPortal
  url: https://docs.patronus.studio/
- type: GettingStarted
  url: https://patronus-protect.github.io/patronus-security/getting-started/quickstart/
- type: Pricing
  url: https://patronus.studio/pricing
- type: Blog
  url: https://patronus.studio/blog
- type: GitHubOrganization
  url: https://github.com/patronus-protect
- type: Packages
  url: packages/patronus-protect-packages.yml
- type: SDKs
  url: packages/patronus-protect-packages.yml
- type: CLI
  url: cli/patronus-protect-cli.yml
- type: AgentSkill
  url: skills/_index.yml
- type: LLMsTxt
  url: llms/patronus-protect-llms.txt
- type: JSONSchema
  url: json-schema/patronus-protect-runtime-v1.schema.json
- type: Conformance
  url: conformance/patronus-protect-conformance.yml
- type: Plans
  url: plans/patronus-protect-plans-pricing.yml
- type: ChangeLog
  url: changelog/patronus-protect-changelog.yml
- type: WellKnown
  url: well-known/patronus-protect-well-known.yml
- type: SecurityTxt
  url: well-known/patronus-protect-security.txt
- type: VulnerabilityDisclosure
  url: security/patronus-protect-vulnerability-disclosure.yml
- type: Security
  url: security/patronus-protect-vulnerability-disclosure.yml
- type: DomainSecurity
  url: security/patronus-protect-domain-security.yml
maintainers:
- FN: Casdo Labs GmbH
  email: team@patronus.studio
  url: https://patronus.studio
x-enrichment:
  date: '2026-09-20'
  status: enriched
  artifacts_added: 26
  pass: local-v3

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/patronus-protect"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/patronus-protect/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/patronus-protect/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.