Get started

Context.dev for AI agents

Context.dev scrapes and structures web data for AI applications, covering brand monitoring, extraction, and website intelligence through one unified API. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect Context.devSee the 11 actions ↓
Developer toolsAPI keyMCP + RESTcontext.dev
AUDIT LOG · CONTEXT.DEVPOLICY: acme-support
09:41:07 · claude · u_8f2read
context_dev.list_batches
List Batches✓ allowed · 212ms
09:41:08 · claude · u_8f2read
context_dev.get_brand
Get Brand✓ allowed · 164ms
EVERY CONTEXT.DEV CALL, ON THE RECORD
01 · USE CASES

What agents do in Context.dev.

01

Scrape a page to markdown

Scrape a webpage and return its content as clean markdown for further processing.

02

Extract structured data from a site

Extract structured data from a webpage using a defined schema instead of parsing HTML.

03

Check a brand's monitoring limits

Check monitor limits for a brand before setting up new tracking on a competitor.

02 · ACTIONS

11 Context.dev actions, graded by risk.

Every Context.dev action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

11

Look things up. Allowed by default.

  • context_dev.get_brand
    Get Brand
  • context_dev.list_batches
    List Batches
  • context_dev.list_monitors
    List Monitors
  • context_dev.search_brands
    Search Brands
  • context_dev.get_webdb_usage
    Get WebDB Usage
  • context_dev.get_monitor_limits
    Get Monitor Limits
  • context_dev.get_website_styleguide
    Get Website Styleguide
  • context_dev.list_webdb_collections
    List WebDB Collections
  • context_dev.parse_file
    Parse File
  • context_dev.scrape_webpage_markdown
    Scrape Webpage to Markdown
  • context_dev.extract_structured_web_data
    Extract Structured Web Data

write

0

Create and change things. Allow, or ask the user first.

  • No write actions.

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Context.dev in three steps.

  1. 01Your users connect Context.devThey add their Context.dev api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Context.dev through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('context_dev', {
  read: 'allow',
  write: 'ask',        
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Context.dev connects.

Users add their Context.dev api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Context.dev connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Context.dev from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More developer tools apps.

GitHub896 actionsSupabase129 actions0CodeKit8 actionsAbly25 actionsAbstract3 actionsAddressfinder17 actionsAddresszen2 actionsAlchemy36 actions
ALL DEVELOPER TOOLS APPS →
07 · FAQ

Context.dev and Arc0, answered.

Q01

Can I use Context.dev with Claude, ChatGPT or Cursor?

Yes. Connect Context.dev to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Context.dev actions you allow.

Q02

How do users connect Context.dev?

Users add their Context.dev api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Context.dev actions can my agent take?

11 in total: 11 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Context.dev?

Yes. Allow read actions and deny writes in the Context.dev policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Context.dev too?

Yes. The same Context.dev connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Context.dev into your agent.

Your users connect Context.dev once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.

Connect Context.devBrowse all apps →

Free to build · MCP + REST · Audit log on every plan