Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add mcp/akgithub2028/agent-reliability-and-evaluation-lab/mcp-agentgit clone --depth 1 https://github.com/Akgithub2028/Agent-Reliability-and-Evaluation-LabWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/akgithub2028/agent-reliability-and-evaluation-lab/mcp-agent)<a href="https://agentmods.dev/mcp/akgithub2028/agent-reliability-and-evaluation-lab/mcp-agent"><img src="https://agentmods.dev/badge/mcp/akgithub2028/agent-reliability-and-evaluation-lab/mcp-agent.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
mcp-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{ "mcp-agent": { "command": "uvx", "args": [ "mcp-agent" ] } }
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 8 lines scan A b377e54ed323
mcp-agent is an MCP server published in the GitHub repository Akgithub2028/Agent-Reliability-and-Evaluation-Lab (3 stars, last pushed 13d ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
a2amesh
Secure, auditable, approval-aware, risk-classified, and policy-bound MCP execution bridge for A2A Mesh. Runs locally from the @a2amesh/mcp npm package. Needs 9 environment variables to run.
control-plane
Enterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing. Remote server at mcp.thinkneo.ai.
eva_cli_example
MCP server "evacliexample" as configured in trpc-group/trpc-agent-go. Launched with go run ./mcpserver.
emem
MCP server "emem" as configured in Vortx-AI/emem. Runs in Docker (ghcr.io/vortx-ai/emem:latest). Needs 5 environment variables to run.
peac
PEAC record operations as MCP tools (verify, inspect, decode, issue, bundle). Runs locally from the @peac/mcp-server npm package.
aidress
MCP server for the Aidress AI agent trust registry. Runs locally from the aidress-mcp Python package. Needs 2 environment variables to run.