‹ directory
80MCP SCORE
B

send21

https://send21.io/mcp
14 tools11 resources3 prompts~3.8k tok/req100% annot.proto 2026-07-28
View public page ›
Xin
Raw JSON ›

Score by pillar

Security ·20100
Tool design ·1862
Schemas / desc ·1680
Reliability ·14100
Context-cost ·1251
Compliance ·12100
Coverage ·880

reliability: LOW (T1 single-shot, not credited - requires T3 >=24h)

Context-cost

3.8ktokens for tools/list

Paid on every request. Lean footprint for 14 tools.

this server3.8k
median≈ 3k

MCP primitive coverage

the quality score covers tools
14
Tools
11
Resources
3
Prompts

Suggested composite optimizations

create_payment_request ↔ get_payment_request → renommer pour distinguer

Badge — paste it in your README

MCP Score badge — send21[![MCP Score](https://checkmcp.dev/badge/send21-io.svg?url=https%3A%2F%2Fsend21.io%2Fmcp)](https://checkmcp.dev/report?url=https%3A%2F%2Fsend21.io%2Fmcp)

About send21 — FAQ

Is the send21 MCP server safe to use?+
CheckMCP audited send21 and gave it an MCP Score of 80/100 (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 send21?+
send21 scores 80/100 (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 send21 expose, and what is its context cost?+
send21 exposes 14 tools, and its tools/list response costs roughly 3.8k tokens — paid on every request your agent makes to it. Lower is better for your context budget.
How was send21 scored?+
By probing the live MCP endpoint (https://send21.io/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.