Skip to content
mcp/skillhub

Compare · Web Search

Exa vs Perplexity API Platform MCP Server

Exa exposes 2 tools and adds about 564 tokens to every model turn. Perplexity API Platform exposes 4 tools and adds about 1,420. Perplexity API Platform costs 2.5× as much context. Measured by connecting to each server and counting its tool list, not from the README.

Exaexa-labsPerplexity API Platformperplexityai
Context tax~564 tok/turn(leaner)~1,420 tok/turn
Tools24
Cost per 1,000 turns (Claude Sonnet 5.5, uncached)$1.13$2.84
Security score97/100100/100
Cold start—732 ms
RunsLocal or hostedLocal (stdio)
Needs keysNone declaredNone declared
FreshnessActiveActive
GitHub stars5.1k2.6k
LicenseMITMIT
Official MCP registryYesYes

Install in Claude Code

Exa

claude mcp add exa -- npx -y exa-mcp-server
Cursor, VS Code, Claude Desktop, Windsurf

Perplexity API Platform

claude mcp add perplexity-ai -- npx -y @perplexity-ai/mcp-server
Cursor, VS Code, Claude Desktop, Windsurf

Tools

By name, from each server's live tool list. The same name can still behave differently.

Only in Exa · 2

  • web_search_exa
  • web_fetch_exa

In both · 0

  • none

Only in Perplexity API Platform · 4

  • perplexity_ask
  • perplexity_research
  • perplexity_reason
  • perplexity_search

Questions

Which uses fewer tokens, Exa or Perplexity API Platform?
Exa: its tool definitions take about 564 tokens per turn against 1,420 for Perplexity API Platform (2.5× more). Tool definitions are resent on every model turn.
Do Exa and Perplexity API Platform have the same tools?
No tool names overlap: Exa has 2 tools and Perplexity API Platform has 4.
Are Exa and Perplexity API Platform hosted or local?
Exa: local or hosted. Perplexity API Platform: local (stdio).

Token counts use the o200k tokenizer on each server's tool definitions as an agent receives them; clients that load tools lazily pay less. Prices are Claude Sonnet 5.5 input at $2/MTok. Want to check one yourself? Run npx mcpskillhub test <package> — how it works.