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/conn-castle/agent-layer/expected-examplegit clone --depth 1 https://github.com/conn-castle/agent-layerGrade A, and why
example 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 yesterday.
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
{
"example": {
"type": "http",
"url": "https://mcp.example.com?token=${AL_EXAMPLE_TOKEN}",
"headers": {
"Authorization": "Bearer ${AL_EXAMPLE_TOKEN}"
}
}
}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.
- yesterday First seen · 9 lines scan A c445fe3a8182
example is an MCP server published in the GitHub repository conn-castle/agent-layer (10 stars, last pushed 2d 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
chembl
Anthropic's hosted ChEMBL server: lets the agent look up bioactive molecules, targets and assay data. Remote server at mcp.deepsense.ai.
no_human
Autonomous AI software-delivery orchestrator driving the Claude Agent SDK on your own Claude credentials. Runs locally from the no-human Python package.
open-design
MCP stdio server bridging coding agents to Open Design daemon (BYOK flow with full systemPrompt fidelity). Runs locally from the open-design-mcp npm package. Needs 1 environment variable to run.
nightgate-mcp
MCP server exposing NIGHTGATE (Midnight blockchain attestation layer) to AI agents. Runs locally from the @odatano/nightgate-mcp npm package.
arcade
MCP server "arcade", hosted remotely at omni.arcade.dev, as configured in arcadeai-labs/omnimcp.
rust-crate-docs-docker
MCP server "rust-crate-docs-docker" as configured in elasticdotventures/b00t. Runs in Docker (ghcr.io/promptexecution/rust-cargo-docs-rag-mcp:latest).