‹ directory
81MCP SCORE
B

vend

https://extract.paypercall.dev/mcp
8 tools~1.0k tok/req0% annot.proto 2026-07-28
View public page ›
Xin
Raw JSON ›

Score by pillar

Security ·20100
Tool design ·1885
Schemas / desc ·1666
Reliability ·1480
Context-cost ·1295
Compliance ·1258
Coverage ·870

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

Context-cost

1.0ktokens for tools/list

Paid on every request. Lean footprint for 8 tools.

this server1.0k
median≈ 3k

MCP primitive coverage

the quality score covers tools
8
Tools
0
Resources · none
0
Prompts · none

Why this score — causal attribution

Each penalty: measure → mechanism → effect → Δscore.

Schemas / desc · HIGH5.4

0% typed+described paramsschema = the contract the agent fills inmore malformed calls

Compliance · MEDIUM3.6

0 declared annotationsdestructiveHint/openWorldHint missing -> worst-case defaultsthe tool is treated as destructive & open-world by clients

Compliance · MEDIUM1.2

capability 'resources' declared but resources/list emptycapabilities inconsistent with real behaviorclients misled

Compliance · MEDIUM1.2

capability 'prompts' declared but prompts/list emptyinconsistent capabilitiesclients misled

Compliance · LOW0.6

no OAuth discovery (.well-known missing)RFC 9728/8414 not exposedauth not auto-discoverable by clients

Badge — paste it in your README

MCP Score badge — vend[![MCP Score](https://checkmcp.dev/badge/extract-paypercall-dev.svg?url=https%3A%2F%2Fextract.paypercall.dev%2Fmcp)](https://checkmcp.dev/report?url=https%3A%2F%2Fextract.paypercall.dev%2Fmcp)

About vend — FAQ

Is the vend MCP server safe to use?+
CheckMCP audited vend and gave it an MCP Score of 81/100 (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 vend?+
vend scores 81/100 (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 vend expose, and what is its context cost?+
vend exposes 8 tools, and its tools/list response costs roughly 1.0k tokens — paid on every request your agent makes to it. Lower is better for your context budget.
How was vend scored?+
By probing the live MCP endpoint (https://extract.paypercall.dev/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.