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/miisodev/BrainLLMWrote 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/miisodev/brainllm/brainllm)<a href="https://agentmods.dev/mcp/miisodev/brainllm/brainllm"><img src="https://agentmods.dev/badge/mcp/miisodev/brainllm/brainllm/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/miisodev/brainllm/brainllm"><img src="https://agentmods.dev/badge/mcp/miisodev/brainllm/brainllm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
brainllm 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 1mo 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
{
"brainllm": {
"command": "npx",
"args": [
"-y",
"brainllm"
],
"env": {
"TRILIUM_BASE_URL": "",
"TRILIUM_ETAPI_TOKEN": "",
"TRILIUM_PASSWORD": "",
"BRAINLLM_MODE": "core",
"BRAINLLM_TZ": "",
"BRAINLLM_OWNER_PASSWORD": "",
"BRAINLLM_OAUTH_SECRET": "",
"BRAINLLM_PUBLIC_URL": "",
"BRAINLLM_ALLOW_UNAUTHENTICATED_HTTP": "",
"BRAINLLM_TRUST_PROXY": ""
}
}
}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.
- 1mo ago Changed · +3 lines e952e6332a1b
- 2mo ago First seen · 18 lines scan A 4168c329a5eb
brainllm is an MCP server published in the GitHub repository miisodev/BrainLLM (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
memora
MCP server "memora" as configured in agentic-box/memora. Launched with memora-server. Needs 3 environment variables to run.
titen-memory
Evidence-grounded agent memory with mandatory provenance, on local SQLite or Cloudflare D1. Runs locally from the titen-memory npm package. Needs 2 environment variables to run.
you-md
MCP server "you-md", hosted remotely at mcp.you.md, as configured in brainsparker/you.md.
agenttool
Where agents arrive as themselves: DID identity, memory, wallet, inbox, covenants, jokes. Remote server at api.agenttool.dev.
memory
Gives the agent a persistent knowledge graph it can write facts to and recall across sessions. Runs locally from the @modelcontextprotocol/server-memory npm package.
openlmlib
Local cross-project knowledge and research library for LLM workflows. Runs locally from the openlmlib Python package.