agentmods.dev

KIP

KIP is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from ldclabs/KIP. Its token cost is not measured, scanned A, original, MIT.

A local MCP server for knowledge graphs, which connect related facts so an agent can retain and explain information over time. It runs through the KIP package and requires a backend URL and API key.

In plain words
What is it for?
Use it to enable local memory persistence, knowledge updates, and explainable interactions after supplying the required server settings.
Why use it?
It provides a way to store and evolve connected knowledge instead of relying only on the current conversation.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 81repo yesterday A scan tokens not measured original MIT

Good fit Use it to enable local memory persistence, knowledge updates, and explainable interactions after supplying the required server settings.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/ldclabs/kip/kip-mcp-server-kip
View source ↗ ldclabs/KIP anda.ai
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/ldclabs/KIP

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 KIP

README.md
[![agentmods](https://agentmods.dev/badge/mcp/ldclabs/kip/kip-mcp-server-kip.svg)](https://agentmods.dev/mcp/ldclabs/kip/kip-mcp-server-kip)
Your own site
<a href="https://agentmods.dev/mcp/ldclabs/kip/kip-mcp-server-kip"><img src="https://agentmods.dev/badge/mcp/ldclabs/kip/kip-mcp-server-kip.svg" alt="Measured on agentmods" 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

KIP 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 8d 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.

mcp/kip-mcp-server/server.json · 13 lines

What it actually says

{
  "KIP": {
    "command": "npx",
    "args": [
      "-y",
      "@ldclabs/kip-mcp-server"
    ],
    "env": {
      "KIP_BACKEND_URL": "",
      "KIP_API_KEY": ""
    }
  }
}
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. 8d ago First seen · 13 lines scan A 49d3dd999e52

Subscribe to this mod's changes

KIP is an MCP server published in the GitHub repository ldclabs/KIP (81 stars, last pushed yesterday), 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.

Building agentsMemory and contextai-agentcontext-engineeringknowledge-graphpersistent memory
Related

Other mcp servers, from other repositories

rawthink-mcp

Persistent memory MCP server for AI development workflows — hybrid search, knowledge graph, session lifecycle. Runs locally from the rawthink-mcp Python package. Needs 9 environment variables to run.

ygtalp/rawthink-mcp · not measured

ori-memory

Persistent memory infrastructure for AI agents. Identity, knowledge graph, and search. Runs locally from the ori-memory npm package.

aayoawoyemi/Ori-Mnemos · not measured

chatcrystal

Local-first AI PKM memory for coding conversations. Runs locally from the chatcrystal npm package. Needs 2 environment variables to run.

ZengLiangYi/ChatCrystal · not measured

halomem

MCP server "halomem", hosted remotely, as configured in halofyai/halofy.

halofyai/halofy · not measured

local-memory-mcp

Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys. Runs locally from the @studiomeyer/local-memory-mcp npm package. Needs 4 environment variables to run.

studiomeyer-io/local-memory-mcp · not measured

synapse-layer

Persistent memory infrastructure for AI agents — AES-256-GCM encrypted at rest, semantic search, MCP-native. Runs locally from the synapse-layer Python package. Needs 3 environment variables to run.

SynapseLayer/synapse-layer · not measured