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/frankchu91/mindbase-llm-wikiWrote 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/frankchu91/mindbase-llm-wiki/plugin-mb)<a href="https://agentmods.dev/mcp/frankchu91/mindbase-llm-wiki/plugin-mb"><img src="https://agentmods.dev/badge/mcp/frankchu91/mindbase-llm-wiki/plugin-mb/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/frankchu91/mindbase-llm-wiki/plugin-mb"><img src="https://agentmods.dev/badge/mcp/frankchu91/mindbase-llm-wiki/plugin-mb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mb 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
{
"mb": {
"command": "npx",
"args": [
"-y",
"mindbase-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.
- 1mo ago First seen · 9 lines scan A ae01761cf033
mb is an MCP server published in the GitHub repository frankchu91/mindbase-llm-wiki (133 stars, last pushed 3d 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 2026-08-30.
Other mcp servers, from other repositories
link
MCP server for Link local agent memory — remember, recall, search, context, and graph traversal. Runs locally from the link-mcp Python package.
accreta
MCP server "accreta" as configured in francescofioredev/accreta. Launched with accreta mcp. Needs 1 environment variable to run.
llm-wiki
MCP server "llm-wiki" as configured in cobusgreyling/llm-wiki. Runs llm_wiki.mcp_server with python. Needs 1 environment variable to run.
wikikit
MCP server "wikikit" as configured in AvalancheAI-labs/agent-wiki-kit. Runs locally from the wikikit Python package.
wikimcp
Git-backed multi-user wiki MCP server — LTM for any AI. Runs locally from the wikimcp Python package.
memforge
MCP server "memforge" as configured in shno-labs/mem-forge. Launched with sh -lc root=$CLAUDE_PLUGIN_ROOT; if [ -z "$root" ]; then root=$PLUGIN_ROOT; fi; . Needs 1 environment variable to run.