图形平台的模型上下文协议(mcp)服务器
概览
什么是 Graphlit MCP 服务器?
Graphlit MCP 服务器是为 Graphlit 平台设计的专用服务器,实施模型上下文协议(MCP)。该服务器促进 Graphlit 生态系统中各个组件之间的无缝通信和数据交换,确保模型能够高效管理和使用。它作为需要强大模型管理和上下文处理的应用程序的支柱,是开发人员和数据科学家在处理机器学习模型时的重要工具。
Graphlit MCP 服务器的特点
- 模型管理:服务器允许用户轻松管理多个机器学习模型,支持快速更新和修改。
- 上下文处理:提供先进的上下文处理能力,确保模型在正确的上下文中运行,以实现最佳性能。
- 可扩展性:Graphlit MCP 服务器设计用于处理不断增长的模型和请求,可以根据应用程序的需求进行扩展。
- 集成:服务器与 Graphlit 平台的其他组件无缝集成,增强整体功能和用户体验。
- 开源:作为一个公共代码库,开发人员可以为其开发做出贡献,确保持续改进和创新。
如何使用 Graphlit MCP 服务器
- 安装:首先从 GitHub 克隆代码库。使用以下命令:
git clone https://github.com/graphlit/graphlit-mcp-server.git
- 配置:根据您的需求配置服务器设置。这可能包括设置模型路径、上下文参数和其他必要的配置。
- 运行服务器:使用提供的脚本或命令启动服务器。确保所有依赖项已正确安装和配置。
- 部署模型:将您的机器学习模型上传到服务器。利用提供的 API 端点管理和与您的模型交互。
- 监控和维护:定期监控服务器的性能和日志,以确保最佳运行。根据需要更新模型和配置。
常见问题解答
Graphlit MCP 服务器的目的是什么?
Graphlit MCP 服务器旨在高效管理机器学习模型及其上下文,促进在 Graphlit 平台内更好的集成和性能。
Graphlit MCP 服务器是开源的吗?
是的,Graphlit MCP 服务器是一个开源项目,允许开发人员贡献和增强其功能。
我如何为 Graphlit MCP 服务器做贡献?
您可以通过分叉代码库、进行更改并提交拉取请求来贡献。确保遵循代码库中提供的贡献指南。
运行 Graphlit MCP 服务器的系统要求是什么?
服务器需要一个兼容的环境,并安装必要的依赖项。请参考代码库中的文档以获取详细的系统要求。
我在哪里可以找到有关 Graphlit 的更多信息?
有关更多信息,请访问官方 Graphlit 网站 www.graphlit.com。
详情
Model Context Protocol (MCP) Server for Graphlit Platform
Overview
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. This document outlines the setup process and provides a basic example of using the client.
Ingest anything from Slack, Discord, websites, Google Drive, email, Jira, Linear or GitHub into a Graphlit project - and then search and retrieve relevant knowledge within an MCP client like Cursor, Windsurf, Goose or Cline.
Your Graphlit project acts as a searchable, and RAG-ready knowledge base across all your developer and product management tools.
Documents (PDF, DOCX, PPTX, etc.) and HTML web pages will be extracted to Markdown upon ingestion. Audio and video files will be transcribed upon ingestion.
Web crawling and web search are built-in as MCP tools, with no need to integrate other tools like Firecrawl, Exa, etc. separately.
You can read more about the MCP Server use cases and features on our blog.
Watch our latest YouTube video on using the Graphlit MCP Server with the Goose MCP client.
For any questions on using the MCP Server, please join our Discord community and post on the #mcp channel.
<a href="https://glama.ai/mcp/servers/fscrivteod"> <img width="380" height="200" src="https://glama.ai/mcp/servers/fscrivteod/badge" alt="graphlit-mcp-server MCP server" /> </a>Tools
Retrieval
- Query Contents
- Query Collections
- Query Feeds
- Query Conversations
- Retrieve Relevant Sources
- Retrieve Similar Images
- Visually Describe Image
RAG
- Prompt LLM Conversation
Extraction
- Extract Structured JSON from Text
Publishing
- Publish as Audio (ElevenLabs Audio)
- Publish as Image (OpenAI Image Generation)
Ingestion
- Files
- Web Pages
- Messages
- Posts
- Emails
- Issues
- Text
- Memory (Short-Term)
Data Connectors
- Microsoft Outlook email
- Google Mail
- Notion
- Linear
- Jira
- GitHub Issues
- Google Drive
- OneDrive
- SharePoint
- Dropbox
- Box
- GitHub
- Slack
- Microsoft Teams
- Discord
- Twitter/X
- Podcasts (RSS)
Web
- Web Crawling
- Web Search (including Podcast Search)
- Web Mapping
- Screenshot Page
Notifications
- Slack
- Webhook
- Twitter/X
Operations
- Configure Project
- Create Collection
- Add Contents to Collection
- Remove Contents from Collection
- Delete Collection(s)
- Delete Feed(s)
- Delete Content(s)
- Delete Conversation(s)
- Is Feed Done?
- Is Content Done?
Enumerations
- List Slack Channels
- List Microsoft Teams Teams
- List Microsoft Teams Channels
- List SharePoint Libraries
- List SharePoint Folders
- List Linear Projects
- List Notion Databases
Resources
- Project
- Contents
- Feeds
- Collections (of Content)
- Workflows
- Conversations
- Specifications
Prerequisites
Before you begin, ensure you have the following:
- Node.js installed on your system (recommended version 18.x or higher).
- An active account on the Graphlit Platform with access to the API settings dashboard.
Configuration
The Graphlit MCP Server supports environment variables to be set for authentication and configuration:
GRAPHLIT_ENVIRONMENT_ID
: Your environment ID.GRAPHLIT_ORGANIZATION_ID
: Your organization ID.GRAPHLIT_JWT_SECRET
: Your JWT secret for signing the JWT token.
You can find these values in the API settings dashboard on the Graphlit Platform.
Installation
Installing via VS Code
For quick installation, use one of the one-click install buttons below:
For manual installation, add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing Ctrl + Shift + P
and typing Preferences: Open User Settings (JSON)
.
Optionally, you can add it to a file called .vscode/mcp.json
in your workspace. This will allow you to share the configuration with others.
Note that the
mcp
key is not needed in the.vscode/mcp.json
file.
{
"mcp": {
"inputs": [
{
"type": "promptString",
"id": "organization_id",
"description": "Graphlit Organization ID",
"password": true
},
{
"type": "promptString",
"id": "environment_id",
"description": "Graphlit Environment ID",
"password": true
},
{
"type": "promptString",
"id": "jwt_secret",
"description": "Graphlit JWT Secret",
"password": true
}
],
"servers": {
"graphlit": {
"command": "npx",
"args": ["-y", "graphlit-mcp-server"],
"env": {
"GRAPHLIT_ORGANIZATION_ID": "${input:organization_id}",
"GRAPHLIT_ENVIRONMENT_ID": "${input:environment_id}",
"GRAPHLIT_JWT_SECRET": "${input:jwt_secret}"
}
}
}
}
}
Installing via Windsurf
To install graphlit-mcp-server in Windsurf IDE application, Cline should use NPX:
npx -y graphlit-mcp-server
Your mcp_config.json file should be configured similar to:
{
"mcpServers": {
"graphlit-mcp-server": {
"command": "npx",
"args": [
"-y",
"graphlit-mcp-server"
],
"env": {
"GRAPHLIT_ORGANIZATION_ID": "your-organization-id",
"GRAPHLIT_ENVIRONMENT_ID": "your-environment-id",
"GRAPHLIT_JWT_SECRET": "your-jwt-secret",
}
}
}
}
Installing via Cline
To install graphlit-mcp-server in Cline IDE application, Cline should use NPX:
npx -y graphlit-mcp-server
Your cline_mcp_settings.json file should be configured similar to:
{
"mcpServers": {
"graphlit-mcp-server": {
"command": "npx",
"args": [
"-y",
"graphlit-mcp-server"
],
"env": {
"GRAPHLIT_ORGANIZATION_ID": "your-organization-id",
"GRAPHLIT_ENVIRONMENT_ID": "your-environment-id",
"GRAPHLIT_JWT_SECRET": "your-jwt-secret",
}
}
}
}
Installing via Cursor
To install graphlit-mcp-server in Cursor IDE application, Cursor should use NPX:
npx -y graphlit-mcp-server
Your mcp.json file should be configured similar to:
{
"mcpServers": {
"graphlit-mcp-server": {
"command": "npx",
"args": [
"-y",
"graphlit-mcp-server"
],
"env": {
"GRAPHLIT_ORGANIZATION_ID": "your-organization-id",
"GRAPHLIT_ENVIRONMENT_ID": "your-environment-id",
"GRAPHLIT_JWT_SECRET": "your-jwt-secret",
}
}
}
}
Installing via Smithery
To install graphlit-mcp-server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @graphlit/graphlit-mcp-server --client claude
Installing manually
To use the Graphlit MCP Server in any MCP client application, use:
{
"mcpServers": {
"graphlit-mcp-server": {
"command": "npx",
"args": [
"-y",
"graphlit-mcp-server"
],
"env": {
"GRAPHLIT_ORGANIZATION_ID": "your-organization-id",
"GRAPHLIT_ENVIRONMENT_ID": "your-environment-id",
"GRAPHLIT_JWT_SECRET": "your-jwt-secret",
}
}
}
}
Optionally, you can configure the credentials for data connectors, such as Slack, Google Email and Notion. Only GRAPHLIT_ORGANIZATION_ID, GRAPHLIT_ENVIRONMENT_ID and GRAPHLIT_JWT_SECRET are required.
{
"mcpServers": {
"graphlit-mcp-server": {
"command": "npx",
"args": [
"-y",
"graphlit-mcp-server"
],
"env": {
"GRAPHLIT_ORGANIZATION_ID": "your-organization-id",
"GRAPHLIT_ENVIRONMENT_ID": "your-environment-id",
"GRAPHLIT_JWT_SECRET": "your-jwt-secret",
"SLACK_BOT_TOKEN": "your-slack-bot-token",
"DISCORD_BOT_TOKEN": "your-discord-bot-token",
"TWITTER_TOKEN": "your-twitter-token",
"GOOGLE_EMAIL_REFRESH_TOKEN": "your-google-refresh-token",
"GOOGLE_EMAIL_CLIENT_ID": "your-google-client-id",
"GOOGLE_EMAIL_CLIENT_SECRET": "your-google-client-secret",
"LINEAR_API_KEY": "your-linear-api-key",
"GITHUB_PERSONAL_ACCESS_TOKEN": "your-github-pat",
"JIRA_EMAIL": "your-jira-email",
"JIRA_TOKEN": "your-jira-token",
"NOTION_API_KEY": "your-notion-api-key"
}
}
}
}
NOTE: when running 'npx' on Windows, you may need to explicitly call npx via the command prompt.
"command": "C:\\Windows\\System32\\cmd.exe /c npx"
Support
Please refer to the Graphlit API Documentation.
For support with the Graphlit MCP Server, please submit a GitHub Issue.
For further support with the Graphlit Platform, please join our Discord community.
Server配置
{
"mcpServers": {
"graphlit-mcp-server": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/metorial/mcp-container--graphlit--graphlit-mcp-server--graphlit-mcp-server",
"npm run start"
],
"env": {
"GRAPHLIT_ORGANIZATION_ID": "graphlit-organization-id",
"GRAPHLIT_ENVIRONMENT_ID": "graphlit-environment-id",
"GRAPHLIT_JWT_SECRET": "graphlit-jwt-secret"
}
}
}
}