‹ directory
94MCP SCORE
A
agentstack (www.agentstack.tech)
https://www.agentstack.tech/mcp
2 tools4 resources74 prompts~1.5k tok/req100% annot.proto 2026-07-28
Score by pillar
Security ·20100
Tool design ·18100
Schemas / desc ·16100
Reliability ·14100
Context-cost ·1281
Compliance ·12100
Coverage ·860
reliability: LOW (T1 single-shot, not credited - requires T3 >=24h)
Context-cost
1.5ktokens for
tools/listPaid on every request. Lean footprint for 2 tools.
this server1.5k
median≈ 3k
MCP primitive coverage
the quality score covers tools2
Tools
4
Resources
74
Prompts
Badge — paste it in your README
[](https://checkmcp.dev/report?url=https%3A%2F%2Fwww.agentstack.tech%2Fmcp)Own this server?Get verified — fresh re-audit, badge if you pass ›
About agentstack (www.agentstack.tech) — FAQ
Is the agentstack (www.agentstack.tech) MCP server safe to use?+
CheckMCP audited agentstack (www.agentstack.tech) and gave it an MCP Score of 94/100 (grade A) — strong — no blocking security or design issues were found. 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 agentstack (www.agentstack.tech)?+
agentstack (www.agentstack.tech) scores 94/100 (grade A) 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 agentstack (www.agentstack.tech) expose, and what is its context cost?+
agentstack (www.agentstack.tech) exposes 2 tools, and its tools/list response costs roughly 1.5k tokens — paid on every request your agent makes to it. Lower is better for your context budget.
How was agentstack (www.agentstack.tech) scored?+
By probing the live MCP endpoint (https://www.agentstack.tech/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.