Kagi MCP Server vs Perplexity MCP Server

Kagi MCP Server

MCP Servers

Perplexity MCP Server

MCP Servers

Tagline

Kagi MCP Server

Official Kagi Search MCP server: search and extract the web from any MCP-compatible agent.

Perplexity MCP Server

Official MCP server for Perplexity's Sonar search, research, and reasoning APIs

Pricing

Kagi MCP Server

Paid· Free: $0 USD · Team: $4 USD per user/month · Enterprise: $21 USD per user/month

Perplexity MCP Server

Paid· Free: $ 0 USD · Team: $ 4 USD per user/month · Enterprise: $ 21 USD per user/month

Lowest paid tier

Kagi MCP Server

$4 USD per user/month · Team

captured 2026-10-27

Perplexity MCP Server

$4 USD per user/month · Team

captured 2026-10-08

Free trial

Kagi MCP Server

Not listed

Perplexity MCP Server

Yes

API

Kagi MCP Server

Yes

Perplexity MCP Server

Yes

Open source

Kagi MCP Server

Yes · MIT

Perplexity MCP Server

Yes · MIT

GitHub stars

Kagi MCP Server

552

checked 2026-10-29

Perplexity MCP Server

2,595

checked 2026-10-29

Last GitHub push

Kagi MCP Server

2026-10-28

Perplexity MCP Server

2026-10-21

First commit

Kagi MCP Server

2024-12

Perplexity MCP Server

2025-03

Model used

Kagi MCP Server

—

Perplexity MCP Server

Perplexity Sonar family (via Agent and Search API presets)

Best for

Kagi MCP Server

Engineers using Claude Code, Claude Desktop, or other MCP clients who already pay for Kagi and want their agent to search and read the web through Kagi's cleaner index instead of a generic SERP API.

Perplexity MCP Server

Developers and agent builders who want first-party, cited web search and deep research inside Claude Desktop, Cursor, VS Code, or a custom MCP client without wiring their own search + LLM stack.

Not for

Kagi MCP Server

Hobbyists who want a free web-search MCP, or teams that need summarizer/FastGPT tools today, or shops that require an on-prem search stack with no third-party API dependency.

Perplexity MCP Server

Teams that need offline or air-gapped retrieval, want to search a private corpus, or are cost-sensitive about agents that call research tools in loops.

Editorial score

Kagi MCP Server

—

Perplexity MCP Server

—

Use cases

Kagi MCP Server

agent web search groundingClaude Code documentation lookupdeep-research pipelinesURL to Markdown extraction for RAGnews and video search from an LLMKagi lens-scoped queries in agentscitation gathering for research assistantscoding agent error-message lookups

Perplexity MCP Server

grounded web search inside Claude Desktopcited research briefs in Cursorup-to-date library docs lookup for coding agentsdeep-research reports with source URLsmulti-step reasoning over live web contentdomain-filtered news monitoringrecency-constrained fact checkscustom MCP agent with real-time browsingself-hosted search tool via Docker

Pros

Kagi MCP Server

• Official, first-party MCP server maintained by Kagi (not a community wrapper)
• Two clean tools that cover the 90% agent case: search and full-page Markdown extraction
• Both hosted (mcp.kagi.com) and local (uvx/Docker) deployment modes
• Documented setup recipes for Claude Desktop, Claude Code, Codex CLI, Kiro, OpenCode, Smithery
• MIT-licensed Python code, easy to fork or audit
• Rides Kagi's ad-free, spam-de-boosted index rather than generic SERP APIs
• Supports Kagi lenses and filters so agents can scope searches to news, docs, etc.

Perplexity MCP Server

• Official first-party server, so tool contracts and citations stay in sync with Perplexity's API
• Four distinct tools cover raw search, fast ask, deep research, and reasoning without changing endpoints
• Remote hosted endpoint (api.perplexity.ai/mcp) means zero-install setup for most MCP clients
• Returns structured citations and source URLs, which agents can surface or verify
• Presets hide model churn — callers pick intent, not a model string that may be deprecated
• MIT-licensed reference implementation you can fork, self-host, or embed in a Docker image
• Recency and domain filters on perplexity_search let you scope agents to fresh or trusted sources

Cons

Kagi MCP Server

• Requires a paid Kagi API key with pay-per-use billing; not usable free
• FastGPT and Universal Summarizer tools are currently absent (rewrite in progress)
• Python + uv toolchain assumption raises the bar vs. a single-binary MCP server
• Small surface area: no built-in caching, batching, or spend controls beyond Kagi's invoice cap
• Hosted endpoint means your queries and Bearer token traverse Kagi infra, not a concern for everyone but worth noting for regulated workloads

Perplexity MCP Server

• API usage is metered and can get expensive fast if agents call perplexity_research in a loop
• Deep-research preset can take several minutes per call, which stresses MCP client timeouts
• Legacy model names were removed, so older client configs pointing at sonar-pro/sonar-reasoning-pro break
• Quality depends entirely on Perplexity's retrieval — you can't swap in a private index or your own crawler
• Rate limits and cost visibility live in Perplexity's dashboard, not the MCP surface
• Only four tools exposed; more niche Perplexity API features (async jobs, spaces) aren't wrapped yet

Website

Kagi MCP Server

github.com

Perplexity MCP Server

github.com

Editorial score: rule-based, 0–10, from AI-assisted profile inputs (see /methodology) — not a user rating; “—” means unscored. “Not listed” means we have no record of it, not that it is absent. GitHub figures and prices carry the date they were checked or captured; prices are shown as published, unconverted.