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

Kagi Search MCPPerplexity MCP

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

Comparable alternatives

Shown only when capability or industry context overlaps.

Side-by-side MCP evidence comparison
Evidence field	Kagi Search MCPMCP100 Selected	Perplexity MCPMCP100 Selected
Task fit
Best for	Web/news/media search with Kagi's index Fetching page content as Markdown through a focused two-tool surface	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	Teams that require OAuth instead of bearer API keys Workloads that need browser automation or site mutation	Offline or private-network-only workflows Users who want browser control, arbitrary website mutation, or a free unlimited search service
Avoid when	You cannot safely store or pass a Kagi API key You need a broader crawl/browser automation toolset	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 Kagi Inc. · Publisher source ↗	First-party MCP Perplexity · Publisher source ↗
Maintenance
Maintenance details	Repo: Not documented Package: Not documented	Repo: Jul 30, 2026 Package: Jul 27, 2026
Popularity evidence
GitHub stars	Not documented	2,519 GitHub stars · checked 2026-09-08
Package downloads / 30 days	No reliable download data	137,187 package downloads / 30 days · checked 2026-09-08
Client coverage
Client coverage details	Not documented	Claude Code✓ Local stdio Claude Desktop✓ Local stdio Codex✓ Local stdio VS Code✓ Local stdio Cursor✓ Local stdio OpenCode✓ Local stdio
Client coverage note	Local stdio runs on your computer. Streamable HTTP connects to a remotely hosted MCP server.
Access and data
Authentication	Hosted and local modes use a Kagi API key; hosted HTTP uses Authorization: Bearer <key>. OAuth2 is not supported yet.	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.
Cost	Kagi API billing is separate from a Kagi subscription and depends on API usage.	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.
Permissions	The MCP exposes Kagi search and page extraction only; it does not provide browser-control or general write actions.	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 handling	Search queries and extraction URLs are sent to Kagi; returned web content should be treated as untrusted external data.	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	Small tool surface reduces complexity, but it is narrower than full web-automation MCPs Hosted and self-hosted modes still send search/extraction requests to Kagi APIs	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 context	Medium. Main concerns are API-key handling, query privacy, untrusted web content, and cost/rate usage rather than destructive side effects.	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 review	2026-09-11	2026-09-11
Candidate evidence	2026-09-11T00:00:00.000Z	2026-08-14T18:46:26.000Z

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

Read the evidence method →