Vijil

Vijil is an AI agent trust platform (Mayfield-backed, ~$23M raised) that helps enterprises make AI agents reliable, secure, and safe for production. Its Console API and CLI span four products across the agent lifecycle: Diamond (pre-deployment red-team evaluation that returns a Trust Score across reliability, security, and safety), Dome (runtime Guardrails, Guards, and Detectors that defend agent inputs/outputs), Darwin (reinforcement-learning evolution that continuously improves agents), and Depot (hardened models and a secure MCP proxy). The platform is programmable via a JWT-authenticated REST API, the `vijil` CLI, an official `vijil-mcp` MCP server, and Python SDKs.

Vijil publishes 5 APIs on the APIs.io network, including Agent Environment API, Diamond API, Dome API, and 2 more. Tagged areas include Company, Artificial Intelligence, AI Agents, Agent Security, and AI Safety.

Vijil’s developer surface includes documentation, API reference, getting-started guide, quickstart, engineering blog, signup flow, support, and 25 more developer resources.

🌐 Visit website 📡 Source on GitHub

47.8/100 developing ▬ flat Agent 29/100 agent ready saas Full breakdown ↓
scored 2026-09-08 · rubric v0.20.0

1 APIs 1 MCP Servers

Company Artificial Intelligence AI Agents Agent Security AI Safety Trust Red Teaming Guardrails LLM Security Evaluation Observability MCP

Kin Score

Kin Score How this is scored →
scored 2026-09-08 · rubric v0.20.0

Composite quality — 47.8/100 · developing

Contract Quality 11.0 / 23

Developer Ergonomics 12.3 / 18

Access Clarity 9.0 / 18

Operational Transparency 1.5 / 12

Contract Governance 0.5 / 11

Discoverability 6.8 / 9

Create-or-Update Ergonomics 2.8 / 10

Agent readiness — 29/100 · agent ready

Machine-Readable Contract 18 / 18

Agentic Access Contract 10 / 10

Documented Reversibility 6 / 6

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 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 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.

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/vijil: 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 5

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

Vijil Agent Environment API

Agent, persona, policy, and harness management

Vijil Diamond API

Evaluation management and report retrieval

Vijil Dome API

Protection, guardrails, and telemetry

Vijil Red Team API

Red team campaigns

Vijil Teams API

Authentication, users, and team management

Open Collections 29

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

API Collection

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations Agent Environment API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations agent-import API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations auth API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations custom-harnesses API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations dashboard API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations demographics API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations detections API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations Diamond API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations Dome API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations dome-configs API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations evaluation-results API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations evaluation-summaries API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations evaluations API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations evolution API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations genomes API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations harnesses API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations personas API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations policies API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations policy-rules API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations proposals API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations Red Team API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations redteam API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations Teams API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations Telemetry API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations Trust Runtime API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations users API

OPEN COLLECTION

Vijil Console API (Combined) agent-configurations webhooks API

OPEN COLLECTION

Scroll for all 29

MCP Servers 1

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

Vijil MCP Server

Official MCP server for the Vijil AI trust platform. Distributed as the `vijil-mcp` PyPI package, it exposes the Vijil Console CLI surface as MCP tools (stdio transport) for Cla...

MCP SERVER

Security Posture 3

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

Vijil Authentication

http/cookie · 2 schemes

SECURITY

Vijil Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Vijil Trust Center

SOC 2

SECURITY

Agentic Access 1

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

Vijil Agentic Access

149 operations · 68 acting · 2 human-in-the-loop

149 operations · 68 acting

AGENTIC

Resources

Get Started 4

Portal, sign-up, and the first successful call

DeveloperPortal

GettingStarted

Quickstart

SignUp

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 6

MCP servers, agent skills, and machine-readable catalogs

MCPServer

LLMsTxt

AgentSkill

AgentSkill

AgentSkill

AgenticAccess

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Conventions

ErrorCatalog

Lifecycle

Conformance

DataModel

Build 4

SDKs, sample code, and the tooling you integrate with

SourceCode

Packages

SDKs

CLI

Access & Security 4

Authentication, authorization, and security posture

TrustCenter

Compliance

Authentication

DomainSecurity

Operate 2

Status, limits, changes, and where to get help

Support

Support

Deprecation

Deprecation

Commercial 2

Pricing, plans, and the legal terms of use

TermsOfService

TermsOfService

PrivacyPolicy

PrivacyPolicy

Company 2

The organization behind the API

Blog

Blog

Website

Website

Other 1

Properties that don't map to a standard resource type

Overlay

Overlay

Source (apis.yml)

aid: vijil
name: Vijil
description: 'Vijil is an AI agent trust platform (Mayfield-backed, ~$23M raised) that helps enterprises make AI agents reliable,
  secure, and safe for production. Its Console API and CLI span four products across the agent lifecycle: Diamond (pre-deployment
  red-team evaluation that returns a Trust Score across reliability, security, and safety), Dome (runtime Guardrails, Guards,
  and Detectors that defend agent inputs/outputs), Darwin (reinforcement-learning evolution that continuously improves agents),
  and Depot (hardened models and a secure MCP proxy). The platform is programmable via a JWT-authenticated REST API, the `vijil`
  CLI, an official `vijil-mcp` MCP server, and Python SDKs.'
url: https://raw.githubusercontent.com/api-evangelist/vijil/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- mayfield
x-tier: active
x-tier-reason: enriched-real-api
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: true
  label: Hosted service · you call their endpoint
  confidence: high
  source:
  - openapi
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source:
  - authentication
  - security
  generated: '2026-09-03'
  method: derived
image: https://cdn.prod.website-files.com/691dbb7207c690a0037cbb28/69bd58689ec57361822b8672_VIJIL-OG.png
specificationVersion: '0.23'
created: '2026-07-17'
modified: '2026-07-21'
tags:
- Company
- Artificial Intelligence
- AI Agents
- Agent Security
- AI Safety
- Trust
- Red Teaming
- Guardrails
- LLM Security
- Evaluation
- Observability
- MCP
tags_raw:
- Company
- AI
- AI Agents
- Agent Security
- AI Safety
- Trust
- Red Teaming
- Guardrails
- LLM Security
- Evaluation
- Observability
- MCP
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
apis:
- aid: vijil:vijil-agent-environment-api
  name: Vijil Agent Environment API
  description: Agent, persona, policy, and harness management
  humanURL: https://docs.vijil.ai/
  baseURL: https://console-api.vijil.ai
  tags:
  - Agent Environment
  properties:
  - type: OpenAPI
    url: openapi/vijil-agent-environment-api-openapi.yml
  - type: APIReference
    url: https://docs.vijil.ai/api-reference
  - type: Documentation
    url: https://docs.vijil.ai/developer-guide/getting-started/introduction
- aid: vijil:vijil-diamond-api
  name: Vijil Diamond API
  description: Evaluation management and report retrieval
  humanURL: https://docs.vijil.ai/
  baseURL: https://console-api.vijil.ai
  tags:
  - Diamond
  properties:
  - type: OpenAPI
    url: openapi/vijil-diamond-api-openapi.yml
  - type: APIReference
    url: https://docs.vijil.ai/api-reference
  - type: Documentation
    url: https://docs.vijil.ai/developer-guide/getting-started/introduction
- aid: vijil:vijil-dome-api
  name: Vijil Dome API
  description: Protection, guardrails, and telemetry
  humanURL: https://docs.vijil.ai/
  baseURL: https://console-api.vijil.ai
  tags:
  - Dome
  properties:
  - type: OpenAPI
    url: openapi/vijil-dome-api-openapi.yml
  - type: APIReference
    url: https://docs.vijil.ai/api-reference
  - type: Documentation
    url: https://docs.vijil.ai/developer-guide/getting-started/introduction
- aid: vijil:vijil-red-team-api
  name: Vijil Red Team API
  description: Red team campaigns
  humanURL: https://docs.vijil.ai/
  baseURL: https://console-api.vijil.ai
  tags:
  - Red Team
  properties:
  - type: OpenAPI
    url: openapi/vijil-red-team-api-openapi.yml
  - type: APIReference
    url: https://docs.vijil.ai/api-reference
  - type: Documentation
    url: https://docs.vijil.ai/developer-guide/getting-started/introduction
- aid: vijil:vijil-teams-api
  name: Vijil Teams API
  description: Authentication, users, and team management
  humanURL: https://docs.vijil.ai/
  baseURL: https://console-api.vijil.ai
  tags:
  - Team
  tags_raw:
  - Teams
  properties:
  - type: OpenAPI
    url: openapi/vijil-teams-api-openapi.yml
  - type: APIReference
    url: https://docs.vijil.ai/api-reference
  - type: Documentation
    url: https://docs.vijil.ai/developer-guide/getting-started/introduction
common:
- type: DeveloperPortal
  url: https://docs.vijil.ai/
- type: Documentation
  url: https://docs.vijil.ai/developer-guide/getting-started/introduction
- type: APIReference
  url: https://docs.vijil.ai/api-reference
- type: GettingStarted
  url: https://docs.vijil.ai/developer-guide/agentic/quickstart
- type: Quickstart
  url: https://docs.vijil.ai/developer-guide/agentic/quickstart
- type: Blog
  url: https://www.vijil.ai/blog
- type: SignUp
  url: https://vijil.ai/try-vijil
- type: Support
  url: https://vijil.ai/contact-us
- type: TermsOfService
  url: https://vijil.ai/policies/terms-of-service
- type: PrivacyPolicy
  url: https://vijil.ai/policies/privacy-policy
- type: TrustCenter
  url: security/vijil-trust-center.yml
- type: Compliance
  url: https://vijil.ai/policies/trust-center
- type: SourceCode
  name: Hugging Face (open models)
  url: https://huggingface.co/vijil
- type: Packages
  url: packages/vijil-packages.yml
- type: SDKs
  url: packages/vijil-packages.yml
- type: CLI
  url: cli/vijil-cli.yml
- type: MCPServer
  url: mcp/vijil-mcp.yml
- type: LLMsTxt
  url: llms/vijil-llms.txt
- type: Authentication
  url: authentication/vijil-authentication.yml
- type: Conventions
  url: conventions/vijil-conventions.yml
- type: ErrorCatalog
  url: errors/vijil-problem-types.yml
- type: Lifecycle
  url: lifecycle/vijil-lifecycle.yml
- type: Deprecation
  url: https://docs.vijil.ai/developer-guide/reference/sdk-migration-guide
- type: Conformance
  url: conformance/vijil-conformance.yml
- type: DataModel
  url: data-model/vijil-data-model.yml
- type: Overlay
  url: overlays/vijil-openapi-overlay.yaml
- type: AgentSkill
  name: Evaluate an agent's trust score with Vijil
  url: skills/vijil-evaluate-agent-trust.md
- type: AgentSkill
  name: Protect an agent at runtime with Vijil Dome
  url: skills/vijil-protect-agent-dome.md
- type: AgentSkill
  name: Run an adversarial red-team campaign with Vijil
  url: skills/vijil-red-team-campaign.md
- type: AgenticAccess
  url: agentic-access/vijil-agentic-access.yml
- type: DomainSecurity
  url: security/vijil-domain-security.yml
- type: Website
  url: https://vijil.ai
x-enrichment:
  date: '2026-07-21'
  status: enriched
  artifacts_added: 19
  pass: local-v1

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/vijil"

All providers

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

Every operation they expose

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

How their score was established

curl "https://apis.io/api/v1/providers/vijil/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.