Parsehub
ParseHub is a web scraping tool that allows users to extract data from websites without coding.
Verdict
Common use cases
- Check scraping project status during standups
- List active crawls before planning new runs
- Confirm project IDs for API automation
- Audit which datasets are ready to download
Integration
- Vendor
- Parsehub
- Category
- other
- Auth
- API_KEY
- Tools
- 1
- Composio slug
parsehub
Tools
- Get Projects
Tool to retrieve all projects for the authenticated user. use after confirming account's api key.
Setup
Setup guide
- 11. Open your Switchy workspace and navigate to Settings > Integrations. 2. Find ParseHub in the MCP directory and click Connect. 3. You'll be prompted to enter your ParseHub API key — grab it from your ParseHub account under Settings > API. 4. Paste the key into Switchy and click Authorize. 5. Switchy confirms the connection by fetching your project list in the background. 6. Open any Space and type '@ParseHub get my projects' to test — you should see a list of your active scraping projects with their names and IDs. 7. If the list appears, the integration is live and ready for queries.
What teammates see: by default, memories from Parsehub are scoped to the Space (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.
Works well with
Top models
Compatibility data appears once enough Spaces have used this MCP together with a given model.
How Switchy teams use it
Starter prompts
List All Projects
@ParseHub show me all my projects with their current status and last run datesOpen in a Space →
Find Project by Name
@ParseHub find the project called 'Competitor Pricing Monitor' and give me its project IDOpen in a Space →
Check Recent Activity
@ParseHub list projects that ran in the last 7 days and tell me how many rows each collectedOpen in a Space →
Audit Idle Projects
@ParseHub show me projects that haven't run in over 30 days so I can archive themOpen in a Space →
Prepare Download List
@ParseHub which projects have finished runs waiting to be downloaded as CSV or JSONOpen in a Space →
Example outputs
Illustrative - representative of the model's voice and quality, not literal recordings.
@parsehub show me all my active scraping projects and their last run times
Found 4 projects in your ParseHub account: 'Product Catalog Monitor' (last run 2 hours ago, 1,247 rows extracted), 'Competitor Pricing Tracker' (last run 6 hours ago, 89 rows), 'Job Listings Scraper' (last run yesterday, 342 rows), and 'News Aggregator' (last run 3 days ago, 156 rows). The Product Catalog project is set to run every 4 hours; the others are manual-trigger only.
This example demonstrates the core read capability of the MCP — listing projects with their metadata. ParseHub's API returns project tokens, template IDs, and run history, but the MCP currently exposes only the project-list endpoint. You'll need the ParseHub dashboard to configure scraping rules or trigger new runs.
@parsehub which of my projects haven't run in the last week, and what data sources are they targeting?
Two projects haven't run in 7+ days: 'News Aggregator' (last run 3 days ago, scraping techcrunch.com article headlines) and 'Event Calendar Scraper' (last run 11 days ago, targeting meetup.com event pages). Both are configured for manual runs. The News Aggregator has 8 historical runs totaling 1,200+ rows; the Event Calendar has only 2 test runs with 23 rows combined.
This synthesis example pairs the MCP's project data with the AI's filtering logic. The MCP retrieves all projects in one call; the AI reasons over timestamps and metadata. Useful for auditing stale scrapers, but the MCP doesn't expose run-triggering or template-editing — those require the ParseHub UI or separate API calls outside this integration.
@parsehub I need to know if my 'Competitor Pricing Tracker' project is still working — when did it last succeed and how many rows came back?
The 'Competitor Pricing Tracker' last ran successfully 6 hours ago, extracting 89 rows. The project is configured to scrape pricing tables from three competitor domains. Historical runs show consistent row counts (85-92 rows per run over the past month), suggesting the target sites haven't changed structure. No failed runs in the last 30 days.
This example highlights how the MCP surfaces run health at a glance — helpful for monitoring scrapers that feed downstream dashboards. However, the single-tool limitation means you can't inspect individual row data, re-run a project, or debug failures through this MCP. For deeper troubleshooting, you'll still need ParseHub's web interface or their full REST API.
Use-case deep-dives
When Parsehub fits weekly competitor price tracking
A 3-person e-commerce team needs to track competitor pricing every Monday morning before their pricing sync. Parsehub works here if you've already built the scraping projects in their visual editor—the MCP just pulls the latest run data via API key auth. The single "Get Projects" tool retrieves project status and results, so your team can pipe fresh competitor data into a Switchy chat without opening the Parsehub dashboard. The threshold: this only makes sense if you're already a Parsehub customer with active projects. If you're starting from scratch, you still need to configure scraping rules in their UI first. For teams running 2-5 recurring scrapes weekly, the MCP saves 10 minutes per check-in by keeping the data in your workspace.
Parsehub MCP for quarterly industry reports
A 6-person strategy consultancy pulls industry data from 8-10 public sources every quarter for client decks. They've set up Parsehub projects to scrape trade association sites, regulatory filings, and competitor blogs. The MCP's "Get Projects" tool lets them query all project statuses in one Switchy session, then export the combined dataset for analysis. This beats logging into Parsehub separately because the team can cross-reference scraped data with internal notes in the same chat thread. The catch: Parsehub's free tier caps you at 5 projects, so teams scraping more than that need a paid plan. If your research cadence is monthly or faster, the MCP justifies itself by centralizing data retrieval. For one-off scrapes, just use the Parsehub dashboard directly.
When the Parsehub MCP streamlines talent pipeline checks
A 2-person recruiting team at a startup monitors 4 niche job boards daily to see where competitors are hiring. They've configured Parsehub to scrape new postings overnight, then use the MCP each morning to pull fresh results into Switchy alongside their ATS notes. The single-tool limitation means you can only retrieve project data—you can't trigger new scrapes or modify projects from the MCP. That's fine for a daily review workflow where scrapes run on schedule. The boundary: if you need to adjust scraping rules mid-week (a job board redesigns its layout), you're back in the Parsehub UI anyway. For teams with stable scraping configs and a regular check-in rhythm, the MCP cuts 5 minutes off each review by skipping the dashboard login.
Frequently asked
What does the Parsehub MCP do in Switchy?
It lets your team retrieve web scraping project data from Parsehub directly in Switchy conversations. You can list all projects tied to your account and check their status without switching to the Parsehub dashboard. This is useful when you need to reference scraped data or confirm a scraping job finished before pulling results into your workflow.
Do I need a Parsehub API key to connect this MCP?
Yes. You'll need to generate an API key from your Parsehub account settings and paste it into Switchy during setup. The key authenticates all requests, so anyone on your team who connects it must have access to your Parsehub account or use a shared key. Parsehub doesn't use OAuth, so key rotation is manual.
Can this MCP trigger new scraping runs or download scraped data?
No. The current implementation only retrieves your project list. It won't start new scraping jobs, fetch the actual scraped data, or modify project settings. If you need to download results or trigger runs, you'll still use Parsehub's web interface or hit their API directly outside Switchy.
Why use this MCP instead of just logging into Parsehub?
It saves context switching when you're already working in Switchy. If your team discusses scraped data in conversations, you can confirm which projects exist and their names without opening another tab. That said, for anything beyond listing projects, you'll still need the Parsehub dashboard or their full API.
Who on the team should connect the Parsehub MCP?
Whoever manages your web scraping projects or needs to reference Parsehub data in Switchy conversations. Since it uses an API key, that person needs account access. If multiple people need it, you can share the key, but remember that usage and rate limits apply to the entire Parsehub account, not per Switchy user.