Parsera for AI agents

Parsera provides AI-powered web extraction with reusable scraper agents for pulling structured data from pages. Developers use it to build repeatable scraping workflows without manual selectors. 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.

Web data and scrapingAPI keyMCP + RESTparsera.org
AUDIT LOG · PARSERAPOLICY: acme-support
09:41:07 · claude · u_8f2read
parsera.list_agents
List Agents✓ allowed · 212ms
09:41:08 · claude · u_8f2read
parsera.extract_data
Extract Data from Webpage✓ allowed · 164ms
09:41:09 · claude · u_8f2write
parsera.create_scraper
Create Scraper✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
parsera.delete_agent
Delete Agent✕ blocked · policy: deny
EVERY PARSERA CALL, ON THE RECORD
01 · USE CASES

What agents do in Parsera.

01

Extract structured data from a page

Pull specific fields from a webpage using an AI-defined extraction schema.

02

Run a saved scraper

Trigger a previously created scraper to run synchronously and return fresh results.

03

Delete a scraper with approval

Remove a scraper agent only after confirming it is no longer part of a workflow.

02 · ACTIONS

15 Parsera actions, graded by risk.

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

read

8

Look things up. Allowed by default.

  • parsera.list_agents
    List Agents
  • parsera.list_scrapers
    List Scrapers
  • parsera.list_llm_specs
    List LLM Specifications
  • parsera.list_proxy_countries
    List Proxy Countries
  • parsera.get_scraper_run_status
    Get Scraper Run Status
  • parsera.extract_data
    Extract Data from Webpage
  • parsera.parse_content
    Parse Content
  • parsera.extract_markdown
    Extract Markdown

write

5

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

  • parsera.create_scraper
    Create Scraper
  • parsera.health_check
    Health Check
  • parsera.run_legacy_agent
    Run Legacy Agent
  • parsera.run_scraper_sync
    Run Scraper Synchronously
  • parsera.run_scraper_async
    Run Scraper Asynchronously

destructive

2

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

  • parsera.delete_agent
    Delete Agent
  • parsera.delete_scraper
    Delete Scraper
03 · HOW IT WORKS

Parsera in three steps.

  1. 01Your users connect ParseraThey add their Parsera api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Scraper” can wait for the user, and “delete Agent” can be denied outright.
  3. 03Any agent can actYour agent calls Parsera 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('parsera', {
  read: 'allow',
  write: 'ask',        // create_scraper
  destructive: 'deny',  // delete_agent
})

# 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 Parsera connects.

Users add their Parsera 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 Parsera 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 Parsera from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Parsera and Arc0, answered.

Q01

Can I use Parsera with Claude, ChatGPT or Cursor?

Yes. Connect Parsera 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 Parsera actions you allow.

Q02

How do users connect Parsera?

Users add their Parsera 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 Parsera actions can my agent take?

15 in total: 8 read, 5 write and 2 destructive, such as “create Scraper”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Parsera?

Yes. Actions like “delete Agent” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Parsera too?

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

Get started

Plug Parsera into your agent.

Your users connect Parsera once, under your brand. Your agent gets 15 actions behind your policies, with every call on the record.

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