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/NomadsResearch/clarkWrote 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/nomadsresearch/clark/claude-code-clark)<a href="https://agentmods.dev/mcp/nomadsresearch/clark/claude-code-clark"><img src="https://agentmods.dev/badge/mcp/nomadsresearch/clark/claude-code-clark/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/nomadsresearch/clark/claude-code-clark"><img src="https://agentmods.dev/badge/mcp/nomadsresearch/clark/claude-code-clark.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
clark 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 1mo 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
{
"clark": {
"command": "uv",
"args": [
"run",
"--directory",
"/absolute/path/to/clark",
"clark",
"mcp"
],
"env": {
"CLARK_DATABASE_URL": "postgresql://clark:[email protected]:5432/clark",
"GEMINI_API_KEY": "${GEMINI_API_KEY}",
"DEEPSEEK_API_KEY": "${DEEPSEEK_API_KEY}"
}
}
}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.
- 1mo ago First seen · 17 lines scan A d9f51b5ae038
clark is an MCP server published in the GitHub repository NomadsResearch/clark (0 stars, last pushed 2mo 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
ori-memory
Persistent memory infrastructure for AI agents. Identity, knowledge graph, and search. Runs locally from the ori-memory npm package.
waggle
MCP server "waggle" as configured in Abhigyan-Shekhar/Waggle-mcp. Runs ./plugins/waggle/bin/waggle-server-launcher.js with node. Needs 6 environment variables to run.
Waggle-mcp
MCP server that gives LLMs persistent graph-structured memory. Runs locally from the waggle-mcp Python package. Needs 5 environment variables to run.
graft
MCP server "graft" as configured in AEndrix03/Graft. Runs C:/personal/Graft/integrations/mcp-server/server.py with python. Needs 1 environment variable to run.
dakera-mcp
MCP server "dakera-mcp" as configured in Dakera-AI/dakera-mcp. Runs in Docker (ghcr.io/dakera-ai/dakera-mcp:0.9.8).
talamus
MCP server "talamus" as configured in ampres-ai/talamus. Runs locally from the talamus[mcp] Python package.