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.
git clone --depth 1 https://github.com/charliebot8888/SafeLinkWrote 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/charliebot8888/safelink/safechain-agent)<a href="https://agentmods.dev/mcp/charliebot8888/safelink/safechain-agent"><img src="https://agentmods.dev/badge/mcp/charliebot8888/safelink/safechain-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/charliebot8888/safelink/safechain-agent"><img src="https://agentmods.dev/badge/mcp/charliebot8888/safelink/safechain-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
safechain-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 12d 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
{ "safechain-agent": { "command": "npx", "args": [ "-y", "safechain-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.
- 12d ago First seen · 9 lines scan A 2df4fa8f860d
safechain-agent is an MCP server published in the GitHub repository charliebot8888/SafeLink (4 stars, last pushed 6mo ago), licensed MIT. 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
aegis-protocol
Trustless escrow for AI agent-to-agent transactions on Base L2 with ERC-8004 identity and USDC. Runs locally from the @aegis-protocol/mcp-server npm package. Needs 4 environment variables to run.
cinderwright-api
Cross-protocol agent payments hub. x402, MPP, L402/Lightning. 1551 services indexed. Runs locally from the cinderwright-mcp-server npm package.
mainstreet
Reputation oracle for AI agents on Base: SAFE/CAUTION/BLOCK + 0-100 score before you pay. x402+MCP. Remote server at avisradar-production.up.railway.app.
diem-agent-workers
Discover privacy-first, bounded Venice-powered micro-work calls with exact x402 USDC prices. Remote server at diem-agent-workers.vercel.app.
cardzero-mcp
MCP Server for CardZero — AI Agent payment wallet on Base (USDC). v0.2 adds ERC-8183 Job (escrow) tools for A2A service delivery. Runs locally from the cardzero-mcp npm package.
base-escrow-mcp
MCP server for AI agents to create and manage P2P escrow deals (ETH or ERC-20) on Base. Trustless trades with dispute resolution — one tool call. Runs locally from the base-escrow-mcp npm package.