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/geondongkim/geond-agent-protocolWrote 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/geondongkim/geond-agent-protocol/mcp_clients-geond)<a href="https://agentmods.dev/mcp/geondongkim/geond-agent-protocol/mcp_clients-geond"><img src="https://agentmods.dev/badge/mcp/geondongkim/geond-agent-protocol/mcp_clients-geond/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/geondongkim/geond-agent-protocol/mcp_clients-geond"><img src="https://agentmods.dev/badge/mcp/geondongkim/geond-agent-protocol/mcp_clients-geond.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
geond 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 11d 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
{
"geond": {
"command": "uv",
"args": [
"--directory",
"C:/path/to/geond-agent-protocol",
"run",
"geond-mcp"
],
"env": {
"GEOND_DATABASE_PROFILE": "local",
"GEOND_DATABASE_URL": "postgresql://geond:geond_dev_password@localhost:55432/geond",
"GEOND_PRIVACY_MODE": "redacted-cloud",
"GEOND_EMBEDDING_PROVIDER": "openai",
"GEOND_EMBEDDING_MODEL": "text-embedding-3-small"
}
}
}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.
- 11d ago First seen · 18 lines scan A 8d822473a563
geond is an MCP server published in the GitHub repository geondongkim/geond-agent-protocol (3 stars, last pushed 18d ago), licensed Apache-2.0. 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
roam-code
MCP server "roam-code" as configured in Cranot/roam-code. Launched with roam mcp. Needs 1 environment variable to run.
emulo
Mine your local AI coding session logs into a personal profile your agent loads before every task. Runs locally from the emulo Python package.
memex
Zettelkasten-based agent memory system with bidirectional links. Runs locally from the @touchskyer/memex npm package. Needs 1 environment variable to run.
agentmap
The TS/JS-accurate repo map for coding agents: ts-morph import/symbol/call graph + MCP query tools. Runs locally from the @raymondchins/agentmap npm package.
codemap
MCP server "codemap" as configured in stainless-code/codemap. Launched with bun src/index.ts mcp --watch --root ${workspaceFolder}.
code-graph
Model Context Protocol SDK. Runs locally from the mcp Python package.