Field-by-field comparison

Compare the evidence before choosing an MCP.

Each signal stays separate, missing facts remain visible, and the column order follows your selection.

MCPs in this comparison

Uncheck an MCP to remove it. Comparing two or three keeps each signal in its own row.

Open canonical comparison link

Comparable alternatives

Shown only when capability or industry context overlaps.

Side-by-side MCP evidence comparison
Evidence fieldScrapfly MCPShortlist candidatePerplexity MCPMCP100 Recommended
Task fit
Best for
  • Scrape and extract public web content through Scrapfly's hosted MCP service
  • Scrapfly users who need to scrape and extract public web content through scrapfly's hosted mcp service.
  • Current web search and cited question answering with Perplexity APIs
  • Research workflows that need a focused search/reasoning MCP rather than browser automation
Not ideal for
  • Web scraping can implicate site terms, privacy rules, credentials, and anti-bot controls. OAuth2 is preferred for production; API keys must be handled as secrets.
  • Offline or private-network-only workflows
  • Users who want browser control, arbitrary website mutation, or a free unlimited search service
Avoid when
  • Web scraping can implicate site terms, privacy rules, credentials, and anti-bot controls. OAuth2 is preferred for production; API keys must be handled as secrets.
  • You cannot safely store a Perplexity API key
  • You plan to expose the local HTTP transport publicly without adding inbound authentication and explicit host/origin allowlists
Provenance
Provenance details

First-party MCP

Scrapfly · Publisher source ↗

First-party MCP

Perplexity · Publisher source ↗

Maintenance
Maintenance details

Repo: Not documented

Package: Not documented

Repo: Aug 27, 2026

Package: Sep 21, 2026

Popularity evidence
GitHub stars

14

GitHub stars · checked 2026-10-20

2,539

GitHub stars · checked 2026-09-24T04:14:26.310000Z

Package downloads / 30 days

511

package downloads / 30 days · checked 2026-10-20

135,602

package downloads / 30 days · checked 2026-09-24T04:17:38.844000Z

Client coverage
Client coverage detailsNot documented
Claude Code✓ Local stdio
Claude Desktop✓ Local stdio
Codex✓ Local stdio
VS Code✓ Local stdio
Cursor✓ Local stdio
OpenCode✓ Local stdio
Client coverage noteLocal stdio runs on your computer. Streamable HTTP connects to a remotely hosted MCP server.
Access and data
AuthenticationOAuth2, Authorization header/API key, or query-parameter API key. Scrapfly recommends OAuth2 for production and documents zero API-key exposure plus token rotation for OAuth2.Hosted MCP and local stdio use a Perplexity API key. The hosted Streamable HTTP endpoint accepts Authorization: Bearer <API key>. The local HTTP transport uses PERPLEXITY_API_KEY for outbound Perplexity API calls but does not authenticate inbound MCP callers.
CostScrapfly has a free allowance/credits and paid usage plans; scraping/proxy/browser operations consume normal Scrapfly credits according to the service plan.Perplexity API access is pay-as-you-go using separately purchased API credits; a Perplexity Pro subscription is not required. Search/research calls can incur API usage charges.
PermissionsThe MCP grants web scraping/screenshot/account capabilities associated with the authenticated Scrapfly account. OAuth2 supports per-user authentication.The MCP is limited to four Perplexity search/reasoning/research tools. Effective quota and billing exposure are those of the supplied API key; it does not expose unrelated Perplexity account-management actions.
Data handlingNot documented in the reviewed sources. The reviewed Scrapfly MCP docs do not state a specific MCP retention/training policy for scraped content or prompts.Queries are sent to Perplexity's Search API and Agent API and results are returned to the MCP client. Search/research output contains third-party web content and should be treated as untrusted external data.
Limitations
Tradeoffs
  • Shortlist evidence is sufficient for identity, setup and task value; authenticated runtime tool-schema measurement and exhaustive security certification remain out of scope.
  • The four-tool surface is focused and easier to reason about than broad browser MCPs, but requests and usage are billed through the Perplexity API Platform
  • The hosted remote server is easiest to operate; self-hosted HTTP requires the operator to secure inbound access because the server intentionally does not authenticate inbound callers
Risk contextThe MCP can retrieve content from arbitrary websites and use anti-bot/proxy capabilities. Usage can implicate site terms, privacy requirements, robots/access controls, copyrighted content, and account/API costs.Medium. Protect the API key and monitor quota/cost. Web results can contain prompt injection. For self-hosted HTTP, default loopback/deny-all origin/host protections are important because inbound callers are otherwise unauthenticated.
Evidence date
Editorial review2026-10-192026-09-11
Candidate evidence2026-10-202026-09-24T04:25:05.554391Z

Popularity, maintenance, fit, permissions, and client support are independent evidence fields.

Read the evidence method →