经 AI Skill Hub 精选评估,MCP图引擎 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
MCP图引擎 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
MCP图引擎 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/TyKolt/kremis
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"mcp---": {
"command": "npx",
"args": ["-y", "kremis"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 MCP图引擎 执行以下任务... Claude: [自动调用 MCP图引擎 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"mcp___": {
"command": "npx",
"args": ["-y", "kremis"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <img src="docs/logo/icon.svg" alt="Kremis" width="120" height="120"> </p>
<p align="center"> <strong>A deterministic knowledge graph MCP server. Local, single binary, no LLM in the loop.</strong> </p>
<p align="center"> A minimal, graph-based cognitive substrate in Rust.<br> Records, associates, retrieves — but never invents. </p>
<p align="center"> <a href="https://github.com/TyKolt/kremis/actions/workflows/ci.yml"><img src="https://github.com/TyKolt/kremis/actions/workflows/ci.yml/badge.svg" alt="CI"></a> <a href="https://crates.io/crates/kremis-core"><img src="https://img.shields.io/crates/v/kremis-core.svg" alt="crates.io"></a> <a href="https://kremis.mintlify.app"><img src="https://img.shields.io/badge/docs-mintlify-0D9373.svg" alt="Docs"></a> <a href="https://dev.to/tykolt/i-spent-months-trying-to-stop-llm-hallucinations-prompt-engineering-wasnt-enough-so-i-wrote-a-4872"><img src="https://img.shields.io/badge/story-dev.to-0A0A0A.svg" alt="Background & Story"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-blue.svg" alt="License"></a> <a href="https://www.rust-lang.org/"><img src="https://img.shields.io/badge/rust-1.89%2B-orange.svg" alt="Rust"></a> <img src="https://img.shields.io/badge/status-alpha-orange" alt="Status"> </p>
Alpha — Functional and tested. Breaking changes may still occur before v1.0.
<p align="center"> <img src="assets/demo.svg" alt="Kremis Honesty Demo" width="800"> </p>
---
redb backend with crash-safe transactions---
```bash docker build -t kremis .
Requires Rust 1.89+ and Cargo.
git clone https://github.com/TyKolt/kremis.git
cd kremis
cargo build --release
cargo test --workspace
cargo run -p kremis -- init # initialize database
cargo run -p kremis -- ingest -f examples/sample_signals.json -t json # ingest sample data
cargo run -p kremis -- server # start HTTP server
In a second terminal:
curl http://localhost:8080/health
curl -X POST http://localhost:8080/query \
-H "Content-Type: application/json" \
-d '{"type":"lookup","entity_id":1}'
Note: CLI commands and the HTTP server cannot run simultaneously (redb holds an exclusive lock). Stop the server before using CLI commands.
Ingest a few facts, let an LLM generate claims, and Kremis validates each one:
[FACT] Alice is an engineer. ← Kremis: "engineer"
[FACT] Alice works on the Kremis project. ← Kremis: "Kremis"
[FACT] Alice knows Bob. ← Kremis: "Bob"
[NOT IN GRAPH] Alice holds a PhD from MIT. ← Kremis: None
[NOT IN GRAPH] Alice previously worked at DeepMind. ← Kremis: None
[NOT IN GRAPH] Alice manages a team of 8. ← Kremis: None
Confirmed by graph: 3/6
Not in graph: 3/6
Three facts grounded. Three fabricated. No ambiguity.
python examples/demo_honesty.py # mock LLM (no external deps)
python examples/demo_honesty.py --ollama # real LLM via Ollama
---
docker run -d -p 8080:8080 -v kremis-data:/data \ --entrypoint kremis kremis server -H 0.0.0.0 -D /data/kremis.db ```
---
简单易用,适合构建智能代理
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
AI Skill Hub 点评:MCP图引擎 的核心功能完整,质量良好。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | kremis |
| 原始描述 | 开源MCP工具:A minimal graph engine for grounded AI — records, associates, and retrieves, but。⭐12 · Rust |
| Topics | aimcprust |
| GitHub | https://github.com/TyKolt/kremis |
| License | Apache-2.0 |
| 语言 | Rust |
收录时间:2026-05-25 · 更新时间:2026-05-30 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端