Get started
Early access

ScrapeGraphAI MCP server

Turn a public HTML page into markdown or structured facts, and search for sources when the URL is not yet known. Access is gated: request enablement for your organization before connecting.

Request early accessSee 6 actions ↓
Web data and scrapingAPI keyMCP + RESTscrapegraphai.com
AUDIT LOG · SCRAPEGRAPHAIPOLICY: acme-support
09:41:07 · claude · u_8f2read
scrapegraphai.list_history
List request history✓ allowed · 212ms
09:41:08 · claude · u_8f2read
scrapegraphai.scrape
Scrape page markdown✓ allowed · 164ms
ILLUSTRATIVE POLICY TRACE · NOT A LIVE RECEIPT
01 · USE CASES

Agent workflows for ScrapeGraphAI.

01

Scrape page markdown

Use when an agent needs readable markdown from one public HTML page. Costs 1 credit with fast fetching. Content is bounded with a truncation flag. A timed-out call may still be charged; inspect history before retrying.

02

Extract page data

Use when structured facts are needed from one public HTML page. Optional schema supports up to 20 scalar fields. Returns serialized JSON with a truncation flag. Costs 5 credits; a timed-out call may still be charged. Inspect history before retrying.

03

Search public web pages

Use when sources are unknown: up to 5 HTML results with markdown, at 2 credits per requested result. Non-HTML rejections may still be billed (pending live check). Empty results are valid. A timed-out call may still be charged; inspect history before retrying.

02 · ACTIONS

6 ScrapeGraphAI actions, graded by risk.

These actions come from the Arc0 registry. Your identity, provider permissions and Arc0 policies determine which actions can run.

read

6

Look things up, subject to your permissions.

  • scrapegraphai.scrape
    Scrape page markdown

    Use when an agent needs readable markdown from one public HTML page. Costs 1 credit with fast fetching. Content is bounded with a truncation flag. A timed-out call may still be charged; inspect history before retrying.

  • scrapegraphai.extract
    Extract page data

    Use when structured facts are needed from one public HTML page. Optional schema supports up to 20 scalar fields. Returns serialized JSON with a truncation flag. Costs 5 credits; a timed-out call may still be charged. Inspect history before retrying.

  • scrapegraphai.search
    Search public web pages

    Use when sources are unknown: up to 5 HTML results with markdown, at 2 credits per requested result. Non-HTML rejections may still be billed (pending live check). Empty results are valid. A timed-out call may still be charged; inspect history before retrying.

  • scrapegraphai.get_credits
    Get available credits

    Use when checking whether the connected account has credits before a paid scrape, extraction or search. Returns balance, plan and job quotas. This endpoint costs no credits; it does not identify the account behind the shared API key.

  • scrapegraphai.list_history
    List request history

    Use when finding request IDs or checking a timed-out call before retrying. Returns up to 20 metadata entries, newest first; total spans all pages. sessionId partially matches sessions created outside Arc0: these actions never send a session header.

  • scrapegraphai.get_result
    Get stored request result

    Use when retrieving an earlier scrape, extraction or search by request ID from history. Running requests can have null results; failed requests retain their status. Results are serialized and bounded with a truncation flag. No URLs in the result are followed.

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 · POLICIES AND AUDIT

Control access to ScrapeGraphAI.

After early access is enabled, connect the intended ScrapeGraphAI account, authorize your AI client and set policies for its tools.

Provider permissions and Arc0 policy both apply. Allow reads, require approval for selected writes, or deny destructive actions. The audit log records execution decisions.

Configure policies and approvals

Example policy choices

  • Read actions: allow where authorized

Arc0 MCP endpoint: https://api.arc0.ai/mcp

04 · AUTH AND DATA

How ScrapeGraphAI connects.

Connect ScrapeGraphAI using API key. OAuth grants the provider scopes shown during consent; API keys and other credentials retain the permissions configured at the provider. Arc0 stores credentials in its encrypted vault and does not pass them to the model. Disconnect to remove access through Arc0; revoke a key at the provider to invalidate it there. Token refresh and provider-side revocation depend on the authentication lane and provider.

The connection serves authorized calls through Arc0 MCP and REST. 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 · AI CLIENTS

Use ScrapeGraphAI with your AI client.

Request access to ScrapeGraphAI first. An Arc0 administrator must enable it for your organization before these actions appear. Then authorize your AI client separately. It only receives tools and accounts allowed for that identity.

ScrapeGraphAI with Claude

Claude Desktop + Claude Code

  1. In Claude Desktop, add Arc0 through the remote MCP settings and use OAuth. Follow the generic remote-client steps if your account’s interface differs.
  2. For Claude Code, run the command below. Open /mcp, select Arc0, and authenticate in your browser. Select your workspace and review access.
  3. Check the connection with claude mcp get arc0.
claude mcp add --transport http --scope user arc0 https://api.arc0.ai/mcp
Full MCP setup and troubleshooting
All apps for Claude
ScrapeGraphAI with ChatGPT

ChatGPT on the web

  1. Open Plugins in ChatGPT, select the plus button, then Add custom MCP server.
  2. Name it Arc0, enter the server URL below, and choose OAuth. Use dynamic client registration if asked; no Arc0 API key is needed.
  3. Review the notice and select Create as a plugin. Complete Arc0 sign-in, workspace selection and consent, then install and select the plugin in your conversation. Labels and access vary by account; managed workspaces may require administrator approval.
https://api.arc0.ai/mcp
Full MCP setup and troubleshooting
All apps for ChatGPT
ScrapeGraphAI with OpenAI Codex

Codex app + CLI

  1. Run the registration command below. The app and CLI share ~/.codex/config.toml.
  2. Complete browser OAuth, choose your Arc0 workspace, and review access. If authentication does not start, run codex mcp login arc0.
  3. Check codex mcp list, then open a new Codex chat. Inspect an existing arc0 entry before changing it.
codex mcp add arc0 --url https://api.arc0.ai/mcp
Full MCP setup and troubleshooting
All apps for OpenAI Codex
ScrapeGraphAI with Cursor

Remote MCP setup

  1. Add Arc0 in your client’s remote MCP settings using the server URL below.
  2. Choose OAuth, sign in to Arc0, select the intended workspace and review access.
  3. Confirm the server is connected and start with an allowed read. These are generic remote-MCP steps; consult your client’s settings for its current interface.
https://api.arc0.ai/mcp
Full MCP setup and troubleshooting
All apps for Cursor
ScrapeGraphAI with VS Code

Remote MCP setup

  1. Add a remote HTTP MCP server named Arc0 using the URL below.
  2. Use OAuth and finish Arc0 sign-in, workspace selection and consent.
  3. Confirm discovery succeeds before requesting a read. These are generic remote-MCP steps; client UI and availability may differ.
https://api.arc0.ai/mcp
Full MCP setup and troubleshooting
ScrapeGraphAI with Any MCP client

Streamable HTTP

  1. Use a client that supports remote MCP over Streamable HTTP. Add the server URL below and choose OAuth.
  2. For a client without OAuth, use a self-bound API key with execute permission in the X-API-Key header. Store it in secret storage or an environment variable, outside source control. Never send both an API key and an OAuth bearer token.
  3. Use the MCP clients guide for the SDK transport example and Embedded identity for business-managed end users.
https://api.arc0.ai/mcp
Full MCP setup and troubleshooting

After setup, ask your agent to find an allowed read action, load its schema, and execute it on the intended account. Check Activity for the receipt. A connected MCP client alone does not confirm a successful provider call.

06 · RELATED

More web data and scraping apps.

ValyuEarly access · 7 actionsSpiderEarly access · 5 actionsPerplexityEarly access · 5 actionsFirecrawlEarly access · 8 actionsTavilyEarly access · 8 actionsExaEarly access · 9 actionsApifyEarly access · 8 actionsScrapeCreatorsEarly access · 6 actions
ALL WEB DATA AND SCRAPING APPS →
07 · FAQ

ScrapeGraphAI and Arc0, answered.

Q01

Does ScrapeGraphAI work with Claude Desktop and Claude Code?

Yes, after early access is enabled for your organization and you connect the intended account. Use Arc0’s remote MCP endpoint with OAuth. Claude Code has a documented registration command; Desktop uses the generic remote-client setup.

Q02

Can I use ScrapeGraphAI with OpenAI Codex, ChatGPT and Cursor?

Yes, after early access is enabled for your organization and you connect the intended account. Codex and ChatGPT have setup instructions in Arc0’s MCP clients guide. Cursor uses the generic remote-MCP steps. Tool access remains scoped to the authorized identity.

Q03

Is this the official ScrapeGraphAI MCP server?

This is Arc0’s integration page, not a claim of an official ScrapeGraphAI server. Arc0 adds a shared connection, policy and audit experience across apps. Consult ScrapeGraphAI for its own current MCP offerings.

Q04

Which ScrapeGraphAI actions are supported?

6 registry-defined actions: 6 read, 0 write and 0 destructive. Provider permissions, access enablement and Arc0 policy determine what can execute.

Q05

Which permissions does ScrapeGraphAI need?

Connect ScrapeGraphAI using API key. OAuth grants the provider scopes shown during consent; API keys and other credentials retain the permissions configured at the provider. Arc0 stores credentials in its encrypted vault and does not pass them to the model. Disconnect to remove access through Arc0; revoke a key at the provider to invalidate it there. Token refresh and provider-side revocation depend on the authentication lane and provider.

Q06

Can I restrict writes in ScrapeGraphAI?

You can deny write and destructive actions or require approval. Provider scopes and Arc0 action policies are separate controls; a policy does not grant additional provider permissions.

Q07

What does ScrapeGraphAI through Arc0 cost?

See Arc0 pricing for current connectivity plans. The provider may require its own subscription or charge per request. Arc0 plan allowances do not make third-party data or paid actions free.

Get started

Request ScrapeGraphAI access.

ScrapeGraphAI MCP server: 6 actions including scrape page markdown, extract page data, search public web pages. Request early access through Arc0.

Request early accessBrowse all apps →

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

ScrapeGraphAI and its logo are trademarks of their respective owners. Arc0 is not affiliated with or endorsed by ScrapeGraphAI.