agentmods.dev

local-knowledge

local-knowledge is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from luutru433-coder/local-knowledge-suite. Its token cost is not measured, scanned A, original, MIT.

A local-knowledge MCP server, a connection that lets an AI coding assistant use a separate local knowledge system.

In plain words
What is it for?
Use it to start the configured local-knowledge service when its required Windows command and environment settings are available.
Why use it?
The description only provides its launch settings and required environment details, so its specific knowledge operations cannot be established from the available information.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it. Also seen: listed in a Claude config.

not rated 0repo 18d ago A scan tokens not measured original MIT

Good fit Use it to start the configured local-knowledge service when its required Windows command and environment settings are available.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/luutru433-coder/local-knowledge-suite/local-knowledge-suite-local-knowledge

Installing this writes the configuration, not the program: `cmd.exe` has to be on your PATH already, or the server will not start.

View source ↗ luutru433-coder/local-knowledge-suite luutru433-coder.github.io
Install

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.

Clone the repo
git clone --depth 1 https://github.com/luutru433-coder/local-knowledge-suite

Installing this writes the configuration, not the program: `cmd.exe` has to be on your PATH already, or the server will not start.

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote 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.

agentmods badge for local-knowledge

README.md
[![agentmods](https://agentmods.dev/badge/mcp/luutru433-coder/local-knowledge-suite/local-knowledge-suite-local-knowledge/github.svg)](https://agentmods.dev/mcp/luutru433-coder/local-knowledge-suite/local-knowledge-suite-local-knowledge)
Your own site
<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/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.

agentmods 80×15 button for local-knowledge

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

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 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.

plugins/local-knowledge-suite/.mcp.json · 19 lines

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"
  }
}
Changes

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.

  1. 1mo ago First seen · 19 lines scan A 07fcfd6c7384

Subscribe to this mod's changes

local-knowledge is an MCP server published in the GitHub repository luutru433-coder/local-knowledge-suite (0 stars, last pushed 18d 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.

Memory and contextPythoncodexknowledge-baselocal-knowledgemcpproject-memory
Related

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.

frankchu91/mindbase-llm-wiki · not measured

lore

Cross-agent semantic memory with knowledge graphs, fact extraction, and MCP integration. Runs locally from the lore-sdk Python package.

agentkitai/lore · not measured

agent-knowledge

Cross-session memory and recall for AI agents — git-synced knowledge base, knowledge graph, confidence scoring, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing. Runs locally from the agent-knowledge npm package.

keshrath/agent-knowledge · not measured

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.

LorgAI/lorg-mcp-server · not measured

context

MCP server "context", hosted remotely at mcp.context.lc, as configured in Supa-Media/context.

Supa-Media/context · not measured

reflect-mcp

Reflection's autonomous runtime — wake, read prior state, do useful work, write back, sleep. Runs locally from the reflect-mcp Python package.

jeffma8888/reflect-mcp · not measured