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/sebastienrousseau/rlgWrote 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/sebastienrousseau/rlg/rlg-mcp)<a href="https://agentmods.dev/mcp/sebastienrousseau/rlg/rlg-mcp"><img src="https://agentmods.dev/badge/mcp/sebastienrousseau/rlg/rlg-mcp/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/sebastienrousseau/rlg/rlg-mcp"><img src="https://agentmods.dev/badge/mcp/sebastienrousseau/rlg/rlg-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
rlg-mcp 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 10d 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
{
"rlg-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/sebastienrousseau/rlg-mcp:0.0.12"
],
"env": {}
}
}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.
- 10d ago First seen · 12 lines scan A 91a1447b74bf
rlg-mcp is an MCP server published in the GitHub repository sebastienrousseau/rlg (5 stars, last pushed 2d 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
clio-mcp
Connect Claude to Clio: 26 tools for matters, contacts, documents, tasks, billing, audit logs. Runs locally from the @oktopeak/clio-mcp npm package. Needs 8 environment variables to run.
cc-audit
MCP server "cc-audit" as configured in ryo-ebata/cc-audit. Launched with ./target/release/cc-audit serve.
mcp-memory-server
Hosted memory for AI agents that learns from outcomes — one key across Claude, Cursor & ChatGPT. Runs locally from the @mnemoverse/mcp-memory-server npm package. Needs 2 environment variables to run.
mcp-victorialogs
MCP server "mcp-victorialogs" as configured in VictoriaMetrics/mcp-victorialogs. Runs in Docker (ghcr.io/victoriametrics/mcp-victorialogs:1.9.0). Needs 3 environment variables to run.
jobgpt-mcp-server
Job search automation, auto apply, resume builder, application tracking, and recruiter outreach. Runs locally from the jobgpt-mcp-server npm package. Needs 1 environment variable to run.
molecare-mcp
Educational dermatology knowledge and lesion tooling. No credentials needed. Not a medical device. Runs locally from the molecare-mcp npm package. Needs 5 environment variables to run.