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/josix/agent-flow/graphifygit clone --depth 1 https://github.com/josix/agent-flowGrade A, and why
graphify 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
{
"graphify": {
"type": "stdio",
"command": "${CLAUDE_PLUGIN_ROOT}/scripts/start-graphify-mcp.sh"
}
}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 · 6 lines scan A db95a5420bde
graphify is an MCP server published in the GitHub repository josix/agent-flow (7 stars, last pushed 17d 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
dos-kernel
Dispatch Operating System — the domain-free trust substrate for fleets of autonomous agents (verdict spine, ship oracle, structured refusal, lane arbiter, correlation spine). Runs locally from the dos-kernel Python package. Needs 1 environment variable to run.
claude-code-bridge
Local-first, cross-machine MCP relay for independent coding agents. Runs locally from the claude-code-bridge Python package. Needs 2 environment variables to run.
madrox
MCP server "madrox" as configured in barkain/madrox. Launched with bash ${CLAUDE_PLUGIN_ROOT}/start_plugin.sh. Needs 1 environment variable to run.
shift-mcp-server
Lightweight coordination layer for multiple AI agents working on the same codebase simultaneously. Runs locally from the @cyanheads/shift-mcp-server npm package. Needs 1 environment variable to run.
mcp-server-and-agent
MCP server "mcp-server-and-agent" as configured in moclamzw/mcp-server-and-agent. Runs locally from the mcp-server-and-agent Python package.
mcp
Persistent memory for AI agents, governed by the human and stored on their own machine. Runs locally from the @mnemosyne_os/mcp npm package. Needs 2 environment variables to run.