‹ directory
89MCP SCORE
B
exa-search-server
https://mcp.exa.ai/mcp
2 tools1 resources1 prompts~555 tok/req100% annot.proto 2024-11-05
Score by pillar
Security ·20100
Tool design ·18100
Schemas / desc ·1680
Reliability ·14100
Context-cost ·1289
Compliance ·1286
Coverage ·860
reliability: LOW (T1 single-shot, not credited - requires T3 >=24h)
Context-cost
555tokens for
tools/listPaid on every request. Lean footprint for 2 tools.
ecosystem median ≈ 3k
MCP primitive coverage
the quality score covers tools2
Tools
1
Resources
1
Prompts
Why this score — causal attribution
Each penalty: measure → mechanism → effect → Δscore.
Compliance · MEDIUM−1.6
proto 2024-11-05 (4 rev. behind 2025-11-25) → outdated protocol version → recent features unavailable, recent clients weakened
Suggested composite optimizations
web_search_exa, web_fetch_exa →
query_exa(filter, fields, limit)Badge — paste it in your README
[](https://checkmcp.dev/report?url=https%3A%2F%2Fmcp.exa.ai%2Fmcp)About exa-search-server — FAQ
Is the exa-search-server MCP server safe to use?+
CheckMCP audited exa-search-server and gave it an MCP Score of 89/100 (grade B) — good — only minor issues. The audit runs an OWASP MCP Top 10 security pass (tool poisoning, hardcoded secrets, command injection, the lethal trifecta) against the live endpoint; see the per-pillar breakdown and the "why this score" attribution on this page, and re-audit anytime at checkmcp.dev.
What is the MCP Score of exa-search-server?+
exa-search-server scores 89/100 (grade B) on CheckMCP's vendor-neutral audit across six weighted pillars — security, tool design, schemas, context-cost, compliance and coverage — with reliability measured and shown but not yet credited.
How many tools does exa-search-server expose, and what is its context cost?+
exa-search-server exposes 2 tools, and its tools/list response costs roughly 555 tokens — paid on every request your agent makes to it. Lower is better for your context budget.
How was exa-search-server scored?+
By probing the live MCP endpoint (https://mcp.exa.ai/mcp), inspecting its tools, schemas and protocol compliance, running an OWASP MCP Top 10 security pass, and measuring the token cost of tools/list — then attributing every penalty as measure → mechanism → effect. The methodology is open: checkmcp.dev/#methodology.