CheckMCP
‹ directory
62MCP SCORE
D

cosvoice

https://cosvoice.com/mcp
27 tools~5.0k tok/req100% annot.proto 2025-06-18
View public page ›
Xin
Raw JSON ›

Score by pillar

Security ·2076
Tool design ·1856
Schemas / desc ·1646
Reliability ·1480
Context-cost ·1257
Compliance ·1270
Coverage ·870

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

Context-cost

5.0ktokens for tools/list

Paid on every request. Lean footprint for 27 tools.

this server5.0k
median≈ 3k

MCP primitive coverage

the quality score covers tools
27
Tools
0
Resources · none
0
Prompts · none

Why this score — causal attribution

Each penalty: measure → mechanism → effect → Δscore.

Schemas / desc · HIGH−5.4

35% typed+described params → schema = the contract the agent fills in → more malformed calls

Security · HIGH−2.4

[MCP02] outil destructif sans confirmation ni destructiveHint → MCP security flaw → tool: remove_contact

Security · HIGH−2.4

[MCP06] toxic surface: 3 risky capability classes combined → MCP security flaw → tool: (serveur)

Compliance · MEDIUM−1.7

JSON-RPC-compliant errors 1/2 → errors not compliant with the JSON-RPC spec → clients break unpredictably

Compliance · MEDIUM−1.2

capability 'resources' declared but resources/list empty → capabilities inconsistent with real behavior → clients misled

Compliance · MEDIUM−1.2

capability 'prompts' declared but prompts/list empty → inconsistent capabilities → clients misled

Tool design · MEDIUM−1.1

2 clusters consolidables → list/get/search/... repeated on the same object → candidates to merge into composite tools

Compliance · MEDIUM−0.5

proto 2025-06-18 (2 rev. behind 2025-11-25) → outdated protocol version → recent features unavailable, recent clients weakened

Security — OWASP MCP Top 10

MCP02HIGHremove_contact
MCP06HIGH(serveur)

Badge — paste it in your README

MCP Score badge — cosvoice[![MCP Score](https://checkmcp.dev/badge/cosvoice-com.svg?url=https%3A%2F%2Fcosvoice.com%2Fmcp)](https://checkmcp.dev/report?url=https%3A%2F%2Fcosvoice.com%2Fmcp)
Own this server?Get verified — fresh re-audit, badge if you pass ›

About cosvoice — FAQ

Is the cosvoice MCP server safe to use?+
CheckMCP audited cosvoice and gave it an MCP Score of 62/100 (grade D) — weak — significant issues; review the findings before trusting it with sensitive data or tools. 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 cosvoice?+
cosvoice scores 62/100 (grade D) 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 cosvoice expose, and what is its context cost?+
cosvoice exposes 27 tools, and its tools/list response costs roughly 5.0k tokens — paid on every request your agent makes to it. Lower is better for your context budget.
How was cosvoice scored?+
By probing the live MCP endpoint (https://cosvoice.com/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.