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/luutru433-coder/local-knowledge-suite/local-knowledge-suite-local-knowledgegit clone --depth 1 https://github.com/luutru433-coder/local-knowledge-suiteWrote 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/luutru433-coder/local-knowledge-suite/local-knowledge-suite-local-knowledge)<a href="https://agentmods.dev/mcp/luutru433-coder/local-knowledge-suite/local-knowledge-suite-local-knowledge"><img src="https://agentmods.dev/badge/mcp/luutru433-coder/local-knowledge-suite/local-knowledge-suite-local-knowledge.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
local-knowledge 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 4d 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
{
"local-knowledge": {
"command": "cmd.exe",
"cwd": ".",
"args": [
"/d",
"/s",
"/c",
"\"\"%SystemRoot%\\System32\\WindowsPowerShell\\v1.0\\powershell.exe\" -NoLogo -NoProfile -NonInteractive -ExecutionPolicy Bypass -File \".\\scripts\\Invoke-LocalKnowledge.ps1\" -Tool mcp\""
],
"env": {
"PYTHONUTF8": "1",
"PYTHONIOENCODING": "utf-8"
},
"startup_timeout_sec": 120,
"tool_timeout_sec": 300,
"default_tools_approval_mode": "writes"
}
}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.
- 4d ago First seen · 19 lines scan A 07fcfd6c7384
local-knowledge is an MCP server published in the GitHub repository luutru433-coder/local-knowledge-suite (0 stars, last pushed 4d 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
mb
MCP server for MindBase — query and write to your wiki from Claude Desktop, Cursor, Windsurf, Cline, or any MCP-compatible AI client. Runs locally from the mindbase-mcp npm package.
markdown-vault-mcp
Generic markdown vault MCP with hybrid search. Runs locally from the markdown-vault-mcp Python package. Needs 81 environment variables to run.
callosium
One shared memory for every AI you use, in plain Markdown files you own. Runs locally from the callosium npm package. Needs 1 environment variable to run.
memstem
Unified memory and skill infrastructure for AI agents. Runs locally from the memstem Python package.
pulse8-ai-cortex-knowledge-vault
PULSE8.ai Cortex — agent-native knowledge OS built on Markdown files. Runs locally from the pulse8-ai-cortex-knowledge-vault Python package. Needs 2 environment variables to run.
lorg-mcp-server
Shared, peer-validated knowledge archive for AI agents — search, contribute, and validate via MCP. Runs locally from the lorg-mcp-server npm package. Needs 1 environment variable to run.