‹ directory
80MCP SCORE
B
ActualHumanTake
https://actualhumantake.vercel.app/api/mcp
3 tools~576 tok/req0% annot.proto 2026-07-28
Score by pillar
Security ·20100
Tool design ·18100
Schemas / desc ·1646
Reliability ·1480
Context-cost ·1295
Compliance ·1270
Coverage ·850
reliability: LOW (T1 single-shot, not credited - requires T3 >=24h)
Context-cost
576tokens for
tools/listPaid on every request. Lean footprint for 3 tools.
this server576
median≈ 3k
MCP primitive coverage
the quality score covers tools3
Tools
0
Resources · none
0
Prompts · none
Why this score — causal attribution
Each penalty: measure → mechanism → effect → Δscore.
Schemas / desc · HIGH−5.4
0% typed+described params → schema = the contract the agent fills in → more malformed calls
Compliance · MEDIUM−3.6
0 declared annotations → destructiveHint/openWorldHint missing -> worst-case defaults → the tool is treated as destructive & open-world by clients
Compliance · LOW−0.6
no OAuth discovery (.well-known missing) → RFC 9728/8414 not exposed → auth not auto-discoverable by clients
Badge — paste it in your README
[](https://checkmcp.dev/report?url=https%3A%2F%2Factualhumantake.vercel.app%2Fapi%2Fmcp)Own this server?Get verified — fresh re-audit, badge if you pass ›
About ActualHumanTake — FAQ
Is the ActualHumanTake MCP server safe to use?+
CheckMCP audited ActualHumanTake 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 ActualHumanTake?+
ActualHumanTake 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 ActualHumanTake expose, and what is its context cost?+
ActualHumanTake exposes 3 tools, and its tools/list response costs roughly 576 tokens — paid on every request your agent makes to it. Lower is better for your context budget.
How was ActualHumanTake scored?+
By probing the live MCP endpoint (https://actualhumantake.vercel.app/api/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.