unbrowse-ai website screenshot

unbrowse-ai

Unbrowse AI is a platform that enables developers to connect AI agents to a wide range of external services and data sources through a unified API. By providing a simple interface for browsing, searching, and interacting with web content, databases, and third‑party APIs, Unbrowse AI helps accelerate the creation of intelligent applications. The service offers tools for developers to integrate browsing capabilities, manage connections, and leverage AI‑driven automation across domains such as e‑commerce, travel, and knowledge retrieval. It aims to simplify the complexity of web interaction for AI models, delivering a robust, scalable solution for modern AI‑powered workflows.

unbrowse-ai publishes 14 API contracts indexed on the APIs.io network, including Account API, Apps & tools API, Capabilities API, and 11 more. Tagged areas include AI Agents and Developer Tools.

The unbrowse-ai catalog on APIs.io includes 1 JSON-LD context and 1 Spectral governance ruleset.

unbrowse-ai’s developer surface includes authentication, documentation, getting-started guide, pricing, engineering blog, and 31 more developer resources.

55.5/100 strong ▲ 11.7 Agent 55/100 agent ready Heartbeat 100/100 alive Full breakdown ↓
scored 2026-11-13 · rubric v0.28.0 · Show this score on your site →
AccessSelf serve
2 published contracts 5 Agent Skills
AI AgentsDeveloper Tools

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-11-13 · rubric v0.28.0
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/.
Show this score on your site. Kin Score badge preview for unbrowse-ai It updates itself when the score changes. Paste this where you link to your API docs:
<a href="https://apis.io/providers/unbrowse-ai/"><img src="https://apis.io/badge/unbrowse-ai/card.svg" alt="unbrowse-ai on APIs.io — Kin Score by API Evangelist"></a>
Other styles, a README pill and a shields.io endpoint are on the badge page.
Raise your score.
Agent readiness — checks not met, largest first (exact, from this profile):
1 more unmet check in the Agent Readiness table above.
Kin Score — facets with the most composite points still available (weight × headroom):
Each check links to what satisfies it. Publish the artifact, or tell us where it already lives, and the score moves on the next scoring run.
Not sure how this applies to your stack? Ask about any one item. Kin Lane reads every question, looks at your profile and your situation, and replies with what a fix would take — scoped to that one area, priced up front, yours whether you ship it or not. Ask a question →
Ask about:
Unbrowse Ai · a person reads this and replies by email.
or email info@apis.io
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 the provider profile at artifacts.apis.io/unbrowse-ai/apis.yml: open an issue on github.com/api-evangelist/unbrowse-ai to ask a question or point us at an artifact you publish. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

Standards implemented 4

Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.

measured — observed by APIs.io (verified)
measured — observed by APIs.io (verified)
measured — observed by APIs.io (published)
measured — observed by APIs.io (published)

APIs 14

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

unbrowse-ai Account API

Who is signed in and what they have used.

unbrowse-ai Apps & tools API

What the workspace enabled, by app; tool scopes with their own MCP URL (/mcp/{slug}); switch tools off; unpublish and republish.

unbrowse-ai Capabilities API

Find the tools Unbrowse knows (the user's own and the public index).

unbrowse-ai Connected apps API

Apps' own MCP servers (Linear, Notion, GitHub…) and Composio toolkits (Gmail, Calendar…) connected with the person's own account; their tools are called through Unbrowse.

unbrowse-ai Indexing API

Teach Unbrowse a site: it explores the site in the cloud browser and compiles tools.

unbrowse-ai Learning API

Learn a capability from recorded traffic (HAR or traces); read what was learned.

unbrowse-ai Logins & vault API

The password manager: logins go in, only masked hints come out. Sites are signed in to by Unbrowse's browser.

unbrowse-ai Marketplace API

Every app with its tools, public: search, categories, official MCP servers, agent-readiness.

unbrowse-ai Orgs API

For agent builders: an org, its keys, one workspace per end user, and one-time connect links for end users' logins.

unbrowse-ai Pages API

Read any page by URL (scrape): HTML, markdown, text or links, with its real status and timing.

unbrowse-ai Replays API

Recorded browser sessions: list, read, search and ask across them.

unbrowse-ai Runs API

Do a task on a website: start, follow, answer what it needs, cancel.

unbrowse-ai Saved queries API

A question in plain words, compiled once into an API: typed params, a pinned tool, the same shape every call, and an optional cache.

unbrowse-ai Sites API

The public index: 8,000+ sites, each with its own tools and OpenAPI spec.

Scroll for all 14

Agent Skills 5

Packaged agent skills for driving this provider's APIs from an AI assistant.

Terms of Service 1

What its API terms permit and prohibit, quoted from its own page.

unbrowse-ai

11 quoted statements, read from unbrowse-ai's own page on 2026-11-10.

TERMS

Privacy & Data 1

Its role, the data it processes, retention and transfers, quoted from its own privacy page.

unbrowse-ai

18 quoted statements, read from unbrowse-ai's own page on 2026-11-10.

PRIVACY

Eligibility 1

Who may sign up and where, quoted from its own terms.

unbrowse-ai

4 quoted statements, read from unbrowse-ai's own page on 2026-11-10.

ELIGIBILITY

AI Preferences 1

Its stance on AI training, inference and agents, quoted from its own pages.

unbrowse-ai

1 quoted statement, read from unbrowse-ai's own page on 2026-11-10.

AI PREFS

Data License 1

How its data and outputs may be reused, quoted from its own terms.

unbrowse-ai

2 quoted statements, read from unbrowse-ai's own page on 2026-11-10.

LICENSE

Semantic Vocabularies 1

JSON-LD contexts and semantic vocabularies used across these APIs.

Unbrowse Ai Context

10 classes · 48 properties

JSON-LD

Spectral Rules 1

Spectral governance rulesets for linting and validating these APIs. Counts are the severity each rule declares, not results of running them.

unbrowse-ai API Rules

18 rules · 15 error-severity 2 warn-severity 1 info-severity

SPECTRAL

JSON Schema 7

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

EgressResponse

5 properties

JSON SCHEMA

Object

0 properties

JSON SCHEMA

RunRequest

10 properties

JSON SCHEMA

Run

9 properties

JSON SCHEMA

SessionReuse

7 properties

JSON SCHEMA

Sharing

7 properties

JSON SCHEMA

ToolScope

7 properties

JSON SCHEMA

Scroll for all 7

Security Posture 3

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

unbrowse-ai Authentication

2 schemes

SECURITY

unbrowse-ai Domain Security

TLSv1.3 · DMARC

SECURITY

unbrowse-ai Vulnerability Disclosure

no policy recorded

SECURITY

Scopes 1

OAuth scopes governing access to this provider's APIs.

unbrowse-ai Scopes

1 scope · authorizationCode

1 scopes

SCOPES

Agentic Access (API Evangelist recommendations) 1

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

unbrowse-ai Agentic Access

176 operations · 86 acting · 6 human-in-the-loop

176 operations · 86 acting

AGENTIC

Resources

Get Started 3

Portal, sign-up, and the first successful call

Documentation 2

Reference material describing how the API behaves

Agent Surfaces 5

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 8

Pagination, idempotency, versioning, errors, and events

Scroll for all 8

Build 1

SDKs, sample code, and the tooling you integrate with

Access & Security 6

Authentication, authorization, and security posture

Commercial 5

Pricing, plans, and the legal terms of use

Company 2

The organization behind the API

Other 4

Properties that don't map to a standard resource type

Source (apis.yml)

apis.yml Raw ↑
aid: unbrowse-ai
name: unbrowse-ai
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  gated: none
  gated_source:
  - onboarding
  label: Self-serve signup
  confidence: low
  source:
  - authentication
  - security
  generated: '2026-11-13'
  method: derived
image: https://unbrowse.ai/og.jpg
description: Unbrowse AI is a platform that enables developers to connect AI agents to a wide range of external services and
  data sources through a unified API. By providing a simple interface for browsing, searching, and interacting with web content,
  databases, and third‑party APIs, Unbrowse AI helps accelerate the creation of intelligent applications. The service offers
  tools for developers to integrate browsing capabilities, manage connections, and leverage AI‑driven automation across domains
  such as e‑commerce, travel, and knowledge retrieval. It aims to simplify the complexity of web interaction for AI models,
  delivering a robust, scalable solution for modern AI‑powered workflows.
url: https://artifacts.apis.io/unbrowse-ai/apis.yml
x-type: company
x-source: harvest:mcp-registry
x-tier: profiled
x-tier-reason: enrichment pass 2026-10-30 (modular-v1; was harvest)
specificationVersion: '0.20'
created: '2026-10-30'
modified: '2026-10-30'
tags:
- AI Agents
- Developer Tools
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: X-MCPManifest
  url: mcp/unbrowse-ai-hosted-mcp.yml
- type: SecurityTxt
  url: well-known/unbrowse-ai-blog-security.txt
- type: AgenticAccess
  url: agentic-access/unbrowse-ai-agentic-access.yml
- type: Spectral
  url: rules/unbrowse-ai-rules.yml
- type: JSONLD
  url: json-ld/unbrowse-ai-context.jsonld
- type: Vocabulary
  url: vocabulary/unbrowse-ai-vocabulary.yml
- type: AgentSkill
  url: skills/_index.yml
- type: DataModel
  url: data-model/unbrowse-ai-data-model.yml
- type: Idempotency
  url: conventions/unbrowse-ai-conventions.yml
- type: Conventions
  url: conventions/unbrowse-ai-conventions.yml
- type: Authentication
  url: authentication/unbrowse-ai-authentication.yml
- type: ErrorCatalog
  url: errors/unbrowse-ai-problem-types.yml
- type: Conformance
  url: conformance/unbrowse-ai-conformance.yml
- type: LLMsTxt
  url: llms/unbrowse-ai-llms.txt
- type: WellKnown
  url: well-known/unbrowse-ai-well-known.yml
- type: Hosts
  url: hosts/unbrowse-ai-hosts.yml
- type: Vendors
  url: vendors/unbrowse-ai-vendors.yml
- type: Security
  url: https://unbrowse.ai/security
- type: Login
  url: https://blog.unbrowse.ai/login
- type: OAuthScopes
  url: scopes/unbrowse-ai-scopes.yml
- type: VulnerabilityDisclosure
  url: security/unbrowse-ai-vulnerability-disclosure.yml
- type: DomainSecurity
  url: security/unbrowse-ai-domain-security.yml
- type: Website
  url: https://unbrowse.ai/
- type: DeveloperPortal
  url: https://unbrowse.ai/docs
- type: Documentation
  url: https://unbrowse.ai/docs
- type: GettingStarted
  url: https://unbrowse.ai/docs/quickstart
- type: Pricing
  url: https://unbrowse.ai/pricing
- type: Blog
  url: https://unbrowse.ai/blog
- type: GitHubOrganization
  url: https://github.com/unbrowse-ai
- type: TermsOfService
  url: https://unbrowse.ai/terms
- type: PrivacyPolicy
  url: https://unbrowse.ai/privacy
- type: UsageTerms
  url: terms/unbrowse-ai-terms-of-service.yml
- type: DataProcessing
  url: privacy/unbrowse-ai-privacy-policy.yml
- type: Eligibility
  url: eligibility/unbrowse-ai-eligibility.yml
- type: AIPreferences
  url: ai-preferences/unbrowse-ai-ai-preferences.yml
- type: DataLicense
  url: data-license/unbrowse-ai-data-license.yml
apis:
- aid: unbrowse-ai:unbrowse-ai-account-api
  name: unbrowse-ai Account API
  description: Who is signed in and what they have used.
  humanURL: https://unbrowse.ai/docs
  baseURL: https://api.unbrowse.ai
  tags:
  - Account
  properties:
  - type: OpenAPI
    url: openapi/unbrowse-ai-account-api-openapi.yml
  - type: JSONSchema
    url: json-schema/unbrowse-ai-sharing-schema.json
  - type: JSONSchema
    url: json-schema/unbrowse-ai-session-reuse-schema.json
- aid: unbrowse-ai:unbrowse-ai-apps-tools-api
  name: unbrowse-ai Apps & tools API
  description: What the workspace enabled, by app; tool scopes with their own MCP URL (/mcp/{slug}); switch tools off; unpublish
    and republish.
  humanURL: https://unbrowse.ai/docs
  baseURL: https://api.unbrowse.ai
  tags:
  - Apps & tools
  properties:
  - type: OpenAPI
    url: openapi/unbrowse-ai-apps-tools-api-openapi.yml
  - type: JSONSchema
    url: json-schema/unbrowse-ai-tool-scope-schema.json
- aid: unbrowse-ai:unbrowse-ai-capabilities-api
  name: unbrowse-ai Capabilities API
  description: Find the tools Unbrowse knows (the user's own and the public index).
  humanURL: https://unbrowse.ai/docs
  baseURL: https://api.unbrowse.ai
  tags:
  - Capabilities
  properties:
  - type: OpenAPI
    url: openapi/unbrowse-ai-capabilities-api-openapi.yml
  - type: JSONSchema
    url: json-schema/unbrowse-ai-object-schema.json
- aid: unbrowse-ai:unbrowse-ai-connected-apps-api
  name: unbrowse-ai Connected apps API
  description: Apps' own MCP servers (Linear, Notion, GitHub…) and Composio toolkits (Gmail, Calendar…) connected with the
    person's own account; their tools are called through Unbrowse.
  humanURL: https://unbrowse.ai/docs
  baseURL: https://api.unbrowse.ai
  tags:
  - Connected Apps
  tags_raw:
  - Connected apps
  properties:
  - type: OpenAPI
    url: openapi/unbrowse-ai-connected-apps-api-openapi.yml
  - type: JSONSchema
    url: json-schema/unbrowse-ai-object-schema.json
- aid: unbrowse-ai:unbrowse-ai-indexing-api
  name: unbrowse-ai Indexing API
  description: 'Teach Unbrowse a site: it explores the site in the cloud browser and compiles tools.'
  humanURL: https://unbrowse.ai/docs
  baseURL: https://api.unbrowse.ai
  tags:
  - Indexing
  properties:
  - type: OpenAPI
    url: openapi/unbrowse-ai-indexing-api-openapi.yml
  - type: JSONSchema
    url: json-schema/unbrowse-ai-object-schema.json
- aid: unbrowse-ai:unbrowse-ai-learning-api
  name: unbrowse-ai Learning API
  description: Learn a capability from recorded traffic (HAR or traces); read what was learned.
  humanURL: https://unbrowse.ai/docs
  baseURL: https://api.unbrowse.ai
  tags:
  - Learning
  properties:
  - type: OpenAPI
    url: openapi/unbrowse-ai-learning-api-openapi.yml
  - type: JSONSchema
    url: json-schema/unbrowse-ai-object-schema.json
- aid: unbrowse-ai:unbrowse-ai-logins-vault-api
  name: unbrowse-ai Logins & vault API
  description: 'The password manager: logins go in, only masked hints come out. Sites are signed in to by Unbrowse''s browser.'
  humanURL: https://unbrowse.ai/docs
  baseURL: https://api.unbrowse.ai
  tags:
  - Logins & vault
  properties:
  - type: OpenAPI
    url: openapi/unbrowse-ai-logins-vault-api-openapi.yml
  - type: JSONSchema
    url: json-schema/unbrowse-ai-object-schema.json
- aid: unbrowse-ai:unbrowse-ai-marketplace-api
  name: unbrowse-ai Marketplace API
  description: 'Every app with its tools, public: search, categories, official MCP servers, agent-readiness.'
  humanURL: https://unbrowse.ai/docs
  baseURL: https://api.unbrowse.ai
  tags:
  - Marketplace
  properties:
  - type: OpenAPI
    url: openapi/unbrowse-ai-marketplace-api-openapi.yml
  - type: JSONSchema
    url: json-schema/unbrowse-ai-object-schema.json
- aid: unbrowse-ai:unbrowse-ai-orgs-api
  name: unbrowse-ai Orgs API
  description: 'For agent builders: an org, its keys, one workspace per end user, and one-time connect links for end users''
    logins.'
  humanURL: https://unbrowse.ai/docs
  baseURL: https://api.unbrowse.ai
  tags:
  - Organization
  tags_raw:
  - Orgs
  properties:
  - type: OpenAPI
    url: openapi/unbrowse-ai-orgs-api-openapi.yml
  - type: JSONSchema
    url: json-schema/unbrowse-ai-object-schema.json
- aid: unbrowse-ai:unbrowse-ai-pages-api
  name: unbrowse-ai Pages API
  description: 'Read any page by URL (scrape): HTML, markdown, text or links, with its real status and timing.'
  humanURL: https://unbrowse.ai/docs
  baseURL: https://api.unbrowse.ai
  tags:
  - Pages
  properties:
  - type: OpenAPI
    url: openapi/unbrowse-ai-pages-api-openapi.yml
- aid: unbrowse-ai:unbrowse-ai-replays-api
  name: unbrowse-ai Replays API
  description: 'Recorded browser sessions: list, read, search and ask across them.'
  humanURL: https://unbrowse.ai/docs
  baseURL: https://api.unbrowse.ai
  tags:
  - Replays
  properties:
  - type: OpenAPI
    url: openapi/unbrowse-ai-replays-api-openapi.yml
  - type: JSONSchema
    url: json-schema/unbrowse-ai-object-schema.json
- aid: unbrowse-ai:unbrowse-ai-runs-api
  name: unbrowse-ai Runs API
  description: 'Do a task on a website: start, follow, answer what it needs, cancel.'
  humanURL: https://unbrowse.ai/docs
  baseURL: https://api.unbrowse.ai
  tags:
  - Runs
  properties:
  - type: OpenAPI
    url: openapi/unbrowse-ai-runs-api-openapi.yml
  - type: JSONSchema
    url: json-schema/unbrowse-ai-run-request-schema.json
  - type: JSONSchema
    url: json-schema/unbrowse-ai-egress-response-schema.json
  - type: JSONSchema
    url: json-schema/unbrowse-ai-run-schema.json
- aid: unbrowse-ai:unbrowse-ai-saved-queries-api
  name: unbrowse-ai Saved queries API
  description: 'A question in plain words, compiled once into an API: typed params, a pinned tool, the same shape every call,
    and an optional cache.'
  humanURL: https://unbrowse.ai/docs
  baseURL: https://api.unbrowse.ai
  tags:
  - Saved Queries
  tags_raw:
  - Saved queries
  properties:
  - type: OpenAPI
    url: openapi/unbrowse-ai-saved-queries-api-openapi.yml
  - type: JSONSchema
    url: json-schema/unbrowse-ai-object-schema.json
- aid: unbrowse-ai:unbrowse-ai-sites-api
  name: unbrowse-ai Sites API
  description: 'The public index: 8,000+ sites, each with its own tools and OpenAPI spec.'
  humanURL: https://unbrowse.ai/docs
  baseURL: https://api.unbrowse.ai
  tags:
  - Sites
  properties:
  - type: OpenAPI
    url: openapi/unbrowse-ai-sites-api-openapi.yml
  - type: JSONSchema
    url: json-schema/unbrowse-ai-run-schema.json
x-enrichment:
  date: '2026-10-30'
  status: enriched
  artifacts_added: 45
  pass: modular-v1
  engine: identity=local,contract=local,surfaces=local,docs=local,regulatory=local

unbrowse-ai API — frequently asked questions

Does unbrowse-ai have an API?

Yes. APIs.io lists 14 APIs from unbrowse-ai, including unbrowse-ai Account API, unbrowse-ai Apps & tools API and unbrowse-ai Capabilities API, and 11 more.

Is there an OpenAPI specification for the unbrowse-ai API?

Yes. APIs.io indexes 14 OpenAPI specifications for unbrowse-ai, each linked for download from this page.

How do I authenticate with the unbrowse-ai API?

unbrowse-ai documents its authentication (2 schemes). The details are profiled on APIs.io as unbrowse-ai Authentication.

Is the unbrowse-ai API ready for AI agents?

unbrowse-ai has a Kin Score of 55.5 out of 100 (strong) and an Agent Readiness score of 55.4 (agent-ready), scored by API Evangelist on 2026-11-13.

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/unbrowse-ai"
All providers
curl "https://apis.io/api/v1/providers?limit=25"
Every operation they expose
curl "https://apis.io/api/v1/providers/unbrowse-ai/operations?limit=25"
How their score was established
curl "https://apis.io/api/v1/providers/unbrowse-ai/evidence"

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. See our Privacy Policy and Terms.

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