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/timothywarner-org/claude-architect/githubgit clone --depth 1 https://github.com/timothywarner-org/claude-architectGrade A, and why
github 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 2d 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
{
"github": {
"_comment": "stdio transport with secret. GITHUB_TOKEN expands from environment. The token never lands in git because the value lives in your shell env, not in this file.",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-github"
],
"env": {
"GITHUB_TOKEN": "${GITHUB_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.
- 2d ago First seen · 13 lines scan A f49873769fb2
github is an MCP server published in the GitHub repository timothywarner-org/claude-architect (80 stars, last pushed 1mo 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 2026-08-30.
Other mcp servers, from other repositories
copilotkit-docs
CopilotKit's hosted docs server: lets the agent search CopilotKit documentation and examples. Remote server at mcp.copilotkit.ai.
gitmem
Persistent institutional memory for AI coding agents. Memory that compounds. Runs locally from the gitmem-mcp npm package. Needs 2 environment variables to run.
billing-remote
MCP server "billing-remote", hosted remotely at billing-mcp.internal.example.com, as configured in Connectry-io/connectrylab-architect-cert-mcp. Needs 1 environment variable to run.
connectry-architect-mcp
Free certification prep for the Claude Certified Architect exam by Connectry LABS. Runs locally from the connectry-architect-mcp npm package.
quiz-generator-ai-mcp
Quiz Generator Ai Mcp: generate quiz (Generate a quiz from provided content text.); validate answers (Validate submitted answers against correct answers and retur); generate flashcards (Generate flashcards (front/back pairs) from content for stud); assess difficulty (Assess the difficulty level of content for…
flashcard-ai-mcp
AI-powered flashcard ai MCP server for agents. Supports generate flashcards, quiz me, spaced repetition. By MEOK AI Labs. Runs locally from the flashcard-ai-mcp Python package.