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/kostya-pakhomov/graphmindWrote 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/kostya-pakhomov/graphmind/kodik-plugin-graphmind)<a href="https://agentmods.dev/mcp/kostya-pakhomov/graphmind/kodik-plugin-graphmind"><img src="https://agentmods.dev/badge/mcp/kostya-pakhomov/graphmind/kodik-plugin-graphmind.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
graphmind 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 7d 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
{
"graphmind": {
"type": "http",
"url": "http://127.0.0.1:50052/mcp"
}
}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.
- 7d ago First seen · 6 lines scan A 76809719fc1b
graphmind is an MCP server published in the GitHub repository kostya-pakhomov/graphmind (2 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 2026-08-31.
Other mcp servers, from other repositories
afair
MCP server "afair" as configured in afairai/afair. Runs locally from the afair Python package.
prometheus-mcp-server
MCP server "prometheus-mcp-server" as configured in pab1it0/prometheus-mcp-server. Runs in Docker (ghcr.io/pab1it0/prometheus-mcp-server:1.6.2). Needs 14 environment variables to run.
remnic
MCP server "remnic", hosted remotely at localhost, as configured in joshuaswarren/remnic.
mcptoon
Zero-setup MCP client for every AI agent. Sync MCP servers across agents. Token-efficient CLI: 99.8% less tokens on discovery. Zero deps. Runs locally from the mcptoon Python package.
ori-memory
Persistent memory infrastructure for AI agents. Identity, knowledge graph, and search. Runs locally from the ori-memory npm package.
servicenow
MCP server "servicenow" as configured in serac-labs/serac. Runs locally from the servicenow-mcp-stdio npm package.