Parsera MCP server
15 operations0 webhooks
Parsera is an AI web scraper you drive with plain instructions. This plugin extracts structured data from pages or raw content, manages reusable extractor and agentic scrapers, runs them synchronously or as pollable async jobs, and tracks run progress and credits.
Try Parsera with your agent
Connect Parsera, then paste this into Claude, ChatGPT or Cursor. For ideas from other apps, see the use cases.
Using Corsair, show me what you can do in Parsera on my account, then run one read-only example and show me the result.
Parsera tools and triggers
Tools are what your agent can do in Parsera through Corsair's MCP server. Triggers are the Parsera events a routine can start from.
Agent
- Create ScraperWrite
Create an empty agentic scraper
agent.createScraper
- Delete ScraperDestructive
Delete an agentic scraper
agent.deleteScraper
- ExtractRead-only
Start a one-shot agentic extraction; answers a task_id to poll, stop or wait on
agent.extract
- Generate ScraperDestructive
Build or regenerate an agentic scraper from a page and an instruction
agent.generateScraper
- Get ScraperRead-only
Read one agentic scraper with its build status and parameters schema
agent.getScraper
- Get TaskRead-only
Read one agentic extraction task with its status and results
agent.getTask
- Stop TaskWrite
Cancel a running agentic extraction
agent.stopTask
Extractor
- Create ScraperWrite
Create an empty extractor scraper
extractor.createScraper
- Delete ScraperDestructive
Delete an extractor scraper
extractor.deleteScraper
- ExtractRead-only
Extract structured data from a URL with the LLM extractor; each call charges credits
extractor.extract
- Get ScraperRead-only
Read one extractor scraper
extractor.getScraper
- ParseRead-only
Parse data from HTML or text content you already have; each call charges credits
extractor.parse
Scrapers
- Get RunRead-only
Read one async scraper run with its progress and results
scrapers.getRun
- RunRead-only
Run a scraper and wait for results; the API defers past five minutes to a pollable run
scrapers.run
- Run AsyncRead-only
Run a scraper asynchronously; answers a run_id to poll
scrapers.runAsync
Connect Parsera to Claude, ChatGPT or Cursor
- 1
Connect Parsera in Corsair
Add your Parsera API key once in Corsair. Corsair stores the credential encrypted and makes the Parsera API calls for your agent, so it never goes into a prompt or a config file. Connect Parsera
If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs Parsera. On a ChatGPT personal plan, connect Parsera here first.
- 2
Add Corsair's MCP server to your agent
Every client uses the same address:
https://mcp.corsair.dev/mcpOpen Customize → Connectors → Add custom connector, paste the address, then select Connect.Add a custom MCP server with the address and choose OAuth. Personal plans get read tools only.Add to CursorOr add this to~/.cursor/mcp.json. Cursor opens Corsair to sign in the first time it connects.{ "mcpServers": { "corsair": { "url": "https://mcp.corsair.dev/mcp" } } }Run this, then run/mcpin Claude Code to sign in.claude mcp add --transport http corsair https://mcp.corsair.dev/mcpCodex, Gemini CLI, VS Code, Zed and other clients with OAuth sign-in work the same way. Clients without it, such as GitHub Copilot's coding agent, use a link's own address and an API key. Setup for every client
- 3
Sign in and choose what needs your approval
Your client opens Corsair to sign in. Pick a link: the apps your agent can use and a mode that decides what it may do without asking. In the default Cautious mode, Parsera's read and write operations run right away and its 3 destructive operations wait for your approval. Strict mode asks before every write and refuses destructive operations, and Read mode allows reads only.
FAQ
Install corsair and @corsair-dev/parsera, add the Parsera plugin, and connect with an API key. Then call methods like corsair.parsera.api.agent.createScraper() from your app. Corsair keeps each tenant isolated.
Yes. Parsera requires an API key from your Parsera account or developer dashboard. Create credentials with access that matches what you automate, then paste them into Corsair or connect through managed auth in Hub.
Yes. One Corsair client can hit Parsera, GitHub, Notion, Stripe, and the rest. Trigger Parsera from a webhook, push updates to Slack, or chain actions across plugins. Same tenant context across integrations, plain TypeScript.
Teams use Corsair for parsera is an AI web scraper you drive with plain instructions. This plugin extracts structured data from pages or raw content, manages reusable extractor and agentic scrapers, runs them synchronously or as pollable async jobs, and tracks run progress and credits. Common builds include sync jobs, admin tooling, and agents that call Parsera APIs from your backend.
The SDK is open source. Self-host and you pay Corsair nothing for the integration layer. Hub bills for hosted auth and execution, not per Parsera API call. Hub has a generous free tier. For hobby projects you can probably run the whole thing on free. Paid plans start to matter with more tenants or heavier traffic.
We maintain @corsair-dev/parsera in the open repo. When Parsera ships API changes, upgrade the package. Your call sites stay typed. You should not need to rewrite the integration layer each time.
No. Corsair does not read your Parsera data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store Parsera data on your behalf.
Yes. Add https://mcp.corsair.dev/mcp as a custom connector or MCP server in Claude, ChatGPT, Cursor, VS Code, Claude Code, Codex or any client that supports remote MCP servers with OAuth sign-in, then sign in to Corsair. On ChatGPT personal plans, custom servers currently get read tools only.
Yes. Put Parsera on a link in Strict mode and every write waits for your approval, while destructive actions are refused. The default Cautious mode asks only before the 3 destructive Parsera operations. You can change a link's mode at hub.corsair.dev/me.