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/bintangtimurlangit/threads-mcp/graphifygit clone --depth 1 https://github.com/bintangtimurlangit/threads-mcpGrade 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": {
"command": "graphify-mcp",
"args": [
"graphify-out/graph.json",
"--transport",
"stdio"
]
}
}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 · 10 lines scan A bf06800b2679
graphify is an MCP server published in the GitHub repository bintangtimurlangit/threads-mcp (0 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
toolport
MCP server "toolport" as configured in tsouth89/toolport. Runs ${CLAUDE_PLUGIN_ROOT}/bin/launch-gateway.mjs with node.
vorim-mcp-server
AI agent identity, permissions, trust scores, and tamper-evident audit trails via Vorim AI. Runs locally from the @vorim/mcp-server npm package. Needs 2 environment variables to run.
warp-ozbridge
OzBridge: run Warp Oz agents from any MCP client — Claude Code, Cursor, Codex, VS Code. Runs locally from the @sena-labs/oz-mcp-server npm package.
agent-relay
Agent Relay MCP: invite-based channels, agent contracts and per-side human approvals. Runs locally from the @cloud1map/agent-relay-mcp npm package. Needs 1 environment variable to run.
sayba-platform
Sayba AI Agent Social Platform MCP Server — 26 tools, 27 skills, 100+ API endpoints (register, post, comment, vote, DM+inbox, notifications, goals, memory, XC wallet, skill market, social, heartbeat, item exchange, agent zone, skill update check). Runs locally from the sayba-platform npm package. Needs 1 environment…
council
Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer. Runs locally from the tokonomix-council-mcp npm package. Needs 1 environment variable to run.