modelcontextprotocol/servers-archived
Watch
1
0
Fork
You've already forked servers-archived
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Merge branch 'main' into fix-puppeteer-async-eval

Browse source
This commit is contained in:
Mati Horovitz 2024-12-05 20:12:07 +02:00
commit 695aa90bac
50 changed files with 3368 additions and 1601 deletions
Download patch file Download diff file Expand all files Collapse all files

7
.github/pull_request_template.md vendored
View file

@ -3,8 +3,8 @@
## Description
## Server Details
<!-- If modifying an existing server or adding a new one, provide details -->
- Server: <!-- e.g., filesystem, github, new-server-name -->
<!-- If modifying an existing server, provide details -->
- Server: <!-- e.g., filesystem, github -->
- Changes to: <!-- e.g., tools, resources, prompts -->
## Motivation and Context
@ -18,7 +18,6 @@
## Types of changes
<!-- What types of changes does your code introduce? Put an `x` in all the boxes that apply: -->
- [ ] New MCP Server
- [ ] Bug fix (non-breaking change which fixes an issue)
- [ ] New feature (non-breaking change which adds functionality)
- [ ] Breaking change (fix or feature that would cause existing functionality to change)
@ -27,7 +26,7 @@
## Checklist
<!-- Go over all the following points, and put an `x` in all the boxes that apply. -->
- [ ] I have read the [MCP Protocol Documentation](https://modelcontextprotocol.io)
- [ ] My server follows MCP security best practices
- [ ] My changes follows MCP security best practices
- [ ] I have updated the server's README accordingly
- [ ] I have tested this with an LLM client
- [ ] My code follows the repository's style guidelines

2
.github/workflows/typescript.yml vendored
View file

@ -74,6 +74,6 @@ jobs:
- name: Publish package
working-directory: src/${{ matrix.package }}
run: npm publish # --provenance
run: npm publish --access public
env:
NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}

6
CONTRIBUTING.md
View file

@ -5,12 +5,16 @@ Thank you for your interest in contributing to the Model Context Protocol (MCP)
## Types of Contributions
### 1. New Servers
Adding a new server is a valuable way to contribute. Before creating a new server:
The repository contains reference implementations, as well as a list of community servers.
We generally don't accept new servers into the repository. We do accept pull requests to the [README.md](./README.md)
adding a reference to your servers.
- Check the [modelcontextprotocol.io](https://modelcontextprotocol.io) documentation
- Ensure your server doesn't duplicate existing functionality
- Consider whether your server would be generally useful to others
- Follow [security best practices](https://modelcontextprotocol.io/docs/concepts/transports#security-considerations) from the MCP documentation
- Create a PR adding a link to your server to the [README.md](./README.md).
### 2. Improvements to Existing Servers
Enhancements to existing servers are welcome! This includes:

80
README.md
View file

@ -1,42 +1,90 @@
# MCP servers
# Model Context Protocol servers
A collection of reference implementations and community-contributed servers for the [Model Context Protocol](https://modelcontextprotocol.io/) (MCP). This repository showcases the versatility and extensibility of MCP, demonstrating how it can be used to give Large Language Models (LLMs) secure, controlled access to tools and data sources.
This repository is a collection of *reference implementations* for the [Model Context Protocol](https://modelcontextprotocol.io/) (MCP), as well as references
to community built servers and additional resources.
The servers in this repository showcase the versatility and extensibility of MCP, demonstrating how it can be used to give Large Language Models (LLMs) secure, controlled access to tools and data sources.
Each MCP server is implemented with either the [Typescript MCP SDK](https://github.com/modelcontextprotocol/typescript-sdk) or [Python MCP SDK](https://github.com/modelcontextprotocol/python-sdk).
## 🌟 Featured Servers
## 🌟 Reference Servers
These servers aim to demonstrate MCP features and the Typescript and Python SDK.
- **[AWS KB Retrieval](src/aws-kb-retrieval)** - Retrieval from AWS Knowledge Base using Bedrock Agent Runtime
- **[Brave Search](src/brave-search)** - Web and local search using Brave's Search API
- **[EverArt](src/everart)** - AI image generation using various models
- **[Fetch](src/fetch)** - Web content fetching and conversion for efficient LLM usage
- **[Filesystem](src/filesystem)** - Secure file operations with configurable access controls
- **[Git](src/git)** - Tools to read, search, and manipulate Git repositories
- **[GitHub](src/github)** - Repository management, file operations, and GitHub API integration
- **[GitLab](src/gitlab)** - GitLab API, enabling project management
- **[Git](src/git)** - Tools to read, search, and manipulate Git repositories
- **[Google Drive](src/gdrive)** - File access and search capabilities for Google Drive
- **[PostgreSQL](src/postgres)** - Read-only database access with schema inspection
- **[Sqlite](src/sqlite)** - Database interaction and business intelligence capabilities
- **[Slack](src/slack)** - Channel management and messaging capabilities
- **[Sentry](src/sentry)** - Retrieving and analyzing issues from Sentry.io
- **[Memory](src/memory)** - Knowledge graph-based persistent memory system
- **[Puppeteer](src/puppeteer)** - Browser automation and web scraping
- **[Brave Search](src/brave-search)** - Web and local search using Brave's Search API
- **[Google Maps](src/google-maps)** - Location services, directions, and place details
- **[Fetch](src/fetch)** - Web content fetching and conversion for efficient LLM usage
- **[Memory](src/memory)** - Knowledge graph-based persistent memory system
- **[PostgreSQL](src/postgres)** - Read-only database access with schema inspection
- **[Puppeteer](src/puppeteer)** - Browser automation and web scraping
- **[Sentry](src/sentry)** - Retrieving and analyzing issues from Sentry.io
- **[Sequential Thinking](src/sequentialthinking)** - Dynamic and reflective problem-solving through thought sequences
- **[Slack](src/slack)** - Channel management and messaging capabilities
- **[Sqlite](src/sqlite)** - Database interaction and business intelligence capabilities
## 🌎 Community Servers
## 🤝 Third-Party Servers
- **[Cloudflare](https://github.com/cloudflare/mcp-server-cloudflare)** - Deploy, configure & interrogate your resources on the Cloudflare developer platform (e.g. Workers/KV/R2/D1)
### 🎖️ Official Integrations
Official integrations are maintained by companies building production ready MCP servers for their platforms.
- <img height="12" width="12" src="https://cdn.simpleicons.org/cloudflare" /> **[Cloudflare](https://github.com/cloudflare/mcp-server-cloudflare)** - Deploy, configure & interrogate your resources on the Cloudflare developer platform (e.g. Workers/KV/R2/D1)
- **[Raygun](https://github.com/MindscapeHQ/mcp-server-raygun)** - Interact with your crash reporting and real using monitoring data on your Raygun account
- <img height="12" width="12" src="https://e2b.dev/favicon.ico" alt="E2B Logo" /> **[E2B](https://github.com/e2b-dev/mcp-server)** - Run code in secure sandboxes hosted by [E2B](https://e2b.dev)
- **[Neon](https://github.com/neondatabase/mcp-server-neon)** - Interact with the Neon serverless Postgres platform
- <img height="12" width="12" src="https://www.tinybird.co/favicon.ico" alt="Tinybird Logo" /> **[Tinybird](https://github.com/tinybirdco/mcp-tinybird)** - Interact with Tinybird serverless ClickHouse platform
- <img height="12" width="12" src="https://pics.fatwang2.com/56912e614b35093426c515860f9f2234.svg" /> [Search1API](https://github.com/fatwang2/search1api-mcp) - One API for Search, Crawling, and Sitemaps
- <img height="12" width="12" src="https://qdrant.tech/img/brand-resources-logos/logomark.svg" /> **[Qdrant](https://github.com/qdrant/mcp-server-qdrant/)** - Implement semantic memory layer on top of the Qdrant vector search engine
### 🌎 Community Servers
A growing set of community-developed and maintained servers demonstrates various applications of MCP across different domains.
> **Note:** Community servers are **untested** and should be used at **your own risk**. They are not affiliated with or endorsed by Anthropic.
- **[MCP Installer](https://github.com/anaisbetts/mcp-installer)** - This server is a server that installs other MCP servers for you.
- **[Spotify MCP](https://github.com/varunneal/spotify-mcp)** - This MCP allows an LLM to play and use Spotify.
- **[Inoyu](https://github.com/sergehuber/inoyu-mcp-unomi-server)** - Interact with an Apache Unomi CDP customer data platform to retrieve and update customer profiles
- **[MySQL](https://github.com/designcomputer/mysql_mcp_server)** - MySQL database integration with configurable access controls and schema inspection
- **[BigQuery](https://github.com/LucasHild/mcp-server-bigquery)** (by LucasHild) - This server enables LLMs to inspect database schemas and execute queries on BigQuery.
- **[BigQuery](https://github.com/ergut/mcp-bigquery-server)** (by ergut) - Server implementation for Google BigQuery integration that enables direct BigQuery database access and querying capabilities
- **[Todoist](https://github.com/abhiz123/todoist-mcp-server)** - Interact with Todoist to manage your tasks.
- **[Tavily search](https://github.com/RamXX/mcp-tavily")** - An MCP server for Tavily's search & news API, with explicit site inclusions/exclusions
- **[Linear](https://github.com/jerhadf/linear-mcp-server)** - Allows LLM to interact with Linear's API for project management, including searching, creating, and updating issues.
- **[Playwright MCP](https://github.com/executeautomation/mcp-playwright)** - This MCP Server will help you run browser automation and webscraping using Playwright
- **[AWS](https://github.com/rishikavikondala/mcp-server-aws)** - Perform operations on your AWS resources using an LLM
- **[LlamaCloud](https://github.com/run-llama/mcp-server-llamacloud)** (by marcusschiesser) - Integrate the data stored in a managed index on [LlamaCloud](https://cloud.llamaindex.ai/)
- **[Any Chat Completions](https://github.com/pyroprompts/any-chat-completions-mcp)** - Interact with any OpenAI SDK Compatible Chat Completions API like OpenAI, Perplexity, Groq, xAI and many more.
- **[Windows CLI](https://github.com/SimonB97/win-cli-mcp-server)** - MCP server for secure command-line interactions on Windows systems, enabling controlled access to PowerShell, CMD, and Git Bash shells.
- **[OpenRPC](https://github.com/shanejonas/openrpc-mpc-server)** - Interact with and discover JSON-RPC APIs via [OpenRPC](https://open-rpc.org).
## 📚 Resources
Additional resources on MCP.
- **[Awesome MCP Servers by punkpeye](https://github.com/punkpeye/awesome-mcp-servers)** - A curated list of MCP servers by **[Frank Fiegel](https://github.com/punkpeye)**
- **[Awesome MCP Servers by wong2](https://github.com/wong2/awesome-mcp-servers)** - A curated list of MCP servers by **[wong2](https://github.com/wong2)**
- **[Awesome MCP Servers by appcypher](https://github.com/appcypher/awesome-mcp-servers)** - A curated list of MCP servers by **[Stephen Akinyemi](https://github.com/appcypher)**
- **[mcp-get](https://mcp-get.com)** - Command line tool for installing and managing MCP servers by **[Michael Latman](https://github.com/michaellatman)**
- **[mcp-cli](https://github.com/wong2/mcp-cli)** - A CLI inspector for the Model Context Protocol by **[wong2](https://github.com/wong2)**
## 🚀 Getting Started
### Using MCP Servers in this Repository
Typescript-based servers in this repository can be used directly with `npx`.
Typescript-based servers in this repository can be used directly with `npx`.
For example, this will start the [Memory](src/memory) server:
```sh
npx -y @modelcontextprotocol/server-memory
```
Python-based servers in this repository can be used directly with [`uvx`](https://docs.astral.sh/uv/concepts/tools/) or [`pip`](https://pypi.org/project/pip/). `uvx` is recommended for ease of use and setup.
Python-based servers in this repository can be used directly with [`uvx`](https://docs.astral.sh/uv/concepts/tools/) or [`pip`](https://pypi.org/project/pip/). `uvx` is recommended for ease of use and setup.
For example, this will start the [Git](src/git) server:
```sh

1977
package-lock.json generated
View file

File diff suppressed because it is too large Load diff

8
package.json
View file

@ -1,7 +1,7 @@
{
"name": "@modelcontextprotocol/servers",
"private": true,
"version": "0.5.1",
"version": "0.6.2",
"description": "Model Context Protocol servers",
"license": "MIT",
"author": "Anthropic, PBC (https://anthropic.com)",
@ -26,6 +26,8 @@
"@modelcontextprotocol/server-slack": "*",
"@modelcontextprotocol/server-brave-search": "*",
"@modelcontextprotocol/server-memory": "*",
"@modelcontextprotocol/server-filesystem": "*"
"@modelcontextprotocol/server-filesystem": "*",
"@modelcontextprotocol/server-everart": "*",
"@modelcontextprotocol/server-sequential-thinking": "*"
}
}
}

53
src/aws-kb-retrieval-server/README.md Normal file
View file

@ -0,0 +1,53 @@
# AWS Knowledge Base Retrieval MCP Server
An MCP server implementation for retrieving information from the AWS Knowledge Base using the Bedrock Agent Runtime.
## Features
- **RAG (Retrieval-Augmented Generation)**: Retrieve context from the AWS Knowledge Base based on a query and a Knowledge Base ID.
- **Supports multiple results retrieval**: Option to retrieve a customizable number of results.
## Tools
- **retrieve_from_aws_kb**
- Perform retrieval operations using the AWS Knowledge Base.
- Inputs:
- `query` (string): The search query for retrieval.
- `knowledgeBaseId` (string): The ID of the AWS Knowledge Base.
- `n` (number, optional): Number of results to retrieve (default: 3).
## Configuration
### Setting up AWS Credentials
1. Obtain AWS access key ID, secret access key, and region from the AWS Management Console.
2. Ensure these credentials have appropriate permissions for Bedrock Agent Runtime operations.
### Usage with Claude Desktop
Add this to your `claude_desktop_config.json`:
```json
{
"mcpServers": {
"aws-kb-retrieval": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-aws-kb-retrieval"
],
"env": {
"AWS_ACCESS_KEY_ID": "YOUR_ACCESS_KEY_HERE",
"AWS_SECRET_ACCESS_KEY": "YOUR_SECRET_ACCESS_KEY_HERE",
"AWS_REGION": "YOUR_AWS_REGION_HERE"
}
}
}
}
```
## License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
This README assumes that your server package is named `@modelcontextprotocol/server-aws-kb-retrieval`. Adjust the package name and installation details if they differ in your setup. Also, ensure that your server script is correctly built and that all dependencies are properly managed in your `package.json`.

166
src/aws-kb-retrieval-server/index.ts Normal file
View file

@ -0,0 +1,166 @@
#!/usr/bin/env node
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import {
CallToolRequestSchema,
ListToolsRequestSchema,
Tool,
} from "@modelcontextprotocol/sdk/types.js";
import {
BedrockAgentRuntimeClient,
RetrieveCommand,
RetrieveCommandInput,
} from "@aws-sdk/client-bedrock-agent-runtime";
// AWS client initialization
const bedrockClient = new BedrockAgentRuntimeClient({
region: process.env.AWS_REGION,
credentials: {
accessKeyId: process.env.AWS_ACCESS_KEY_ID!,
secretAccessKey: process.env.AWS_SECRET_ACCESS_KEY!,
},
});
interface RAGSource {
id: string;
fileName: string;
snippet: string;
score: number;
}
async function retrieveContext(
query: string,
knowledgeBaseId: string,
n: number = 3
): Promise<{
context: string;
isRagWorking: boolean;
ragSources: RAGSource[];
}> {
try {
if (!knowledgeBaseId) {
console.error("knowledgeBaseId is not provided");
return {
context: "",
isRagWorking: false,
ragSources: [],
};
}
const input: RetrieveCommandInput = {
knowledgeBaseId: knowledgeBaseId,
retrievalQuery: { text: query },
retrievalConfiguration: {
vectorSearchConfiguration: { numberOfResults: n },
},
};
const command = new RetrieveCommand(input);
const response = await bedrockClient.send(command);
const rawResults = response?.retrievalResults || [];
const ragSources: RAGSource[] = rawResults
.filter((res) => res?.content?.text)
.map((result, index) => {
const uri = result?.location?.s3Location?.uri || "";
const fileName = uri.split("/").pop() || `Source-${index}.txt`;
return {
id: (result.metadata?.["x-amz-bedrock-kb-chunk-id"] as string) || `chunk-${index}`,
fileName: fileName.replace(/_/g, " ").replace(".txt", ""),
snippet: result.content?.text || "",
score: (result.score as number) || 0,
};
})
.slice(0, 3);
const context = rawResults
.filter((res): res is { content: { text: string } } => res?.content?.text !== undefined)
.map(res => res.content.text)
.join("\n\n");
return {
context,
isRagWorking: true,
ragSources,
};
} catch (error) {
console.error("RAG Error:", error);
return { context: "", isRagWorking: false, ragSources: [] };
}
}
// Define the retrieval tool
const RETRIEVAL_TOOL: Tool = {
name: "retrieve_from_aws_kb",
description: "Performs retrieval from the AWS Knowledge Base using the provided query and Knowledge Base ID.",
inputSchema: {
type: "object",
properties: {
query: { type: "string", description: "The query to perform retrieval on" },
knowledgeBaseId: { type: "string", description: "The ID of the AWS Knowledge Base" },
n: { type: "number", default: 3, description: "Number of results to retrieve" },
},
required: ["query", "knowledgeBaseId"],
},
};
// Server setup
const server = new Server(
{
name: "aws-kb-retrieval-server",
version: "0.2.0",
},
{
capabilities: {
tools: {},
},
},
);
// Request handlers
server.setRequestHandler(ListToolsRequestSchema, async () => ({
tools: [RETRIEVAL_TOOL],
}));
server.setRequestHandler(CallToolRequestSchema, async (request) => {
const { name, arguments: args } = request.params;
if (name === "retrieve_from_aws_kb") {
const { query, knowledgeBaseId, n = 3 } = args as Record<string, any>;
try {
const result = await retrieveContext(query, knowledgeBaseId, n);
if (result.isRagWorking) {
return {
content: [
{ type: "text", text: `Context: ${result.context}` },
{ type: "text", text: `RAG Sources: ${JSON.stringify(result.ragSources)}` },
],
};
} else {
return {
content: [{ type: "text", text: "Retrieval failed or returned no results." }],
};
}
} catch (error) {
return {
content: [{ type: "text", text: `Error occurred: ${error}` }],
};
}
} else {
return {
content: [{ type: "text", text: `Unknown tool: ${name}` }],
isError: true,
};
}
});
// Server startup
async function runServer() {
const transport = new StdioServerTransport();
await server.connect(transport);
console.error("AWS KB Retrieval Server running on stdio");
}
runServer().catch((error) => {
console.error("Fatal error running server:", error);
process.exit(1);
});

30
src/aws-kb-retrieval-server/package.json Normal file
View file

@ -0,0 +1,30 @@
{
"name": "@modelcontextprotocol/server-aws-kb-retrieval",
"version": "0.6.2",
"description": "MCP server for AWS Knowledge Base retrieval using Bedrock Agent Runtime",
"license": "MIT",
"author": "Anthropic, PBC (https://anthropic.com)",
"homepage": "https://modelcontextprotocol.io",
"bugs": "https://github.com/modelcontextprotocol/servers/issues",
"type": "module",
"bin": {
"mcp-server-aws-kb-retrieval": "dist/index.js"
},
"files": [
"dist"
],
"scripts": {
"build": "tsc && shx chmod +x dist/*.js",
"prepare": "npm run build",
"watch": "tsc --watch"
},
"dependencies": {
"@modelcontextprotocol/sdk": "0.5.0",
"@aws-sdk/client-bedrock-agent-runtime": "^3.0.0"
},
"devDependencies": {
"@types/node": "^20.10.0",
"shx": "^0.3.4",
"typescript": "^5.6.2"
}
}

17
src/aws-kb-retrieval-server/tsconfig.json Normal file
View file

@ -0,0 +1,17 @@
{
"extends": "../../tsconfig.json",
"compilerOptions": {
"outDir": "./dist",
"rootDir": ".",
"composite": true,
"incremental": true,
"tsBuildInfoFile": "./dist/.tsbuildinfo"
},
"include": [
"./**/*.ts"
],
"exclude": [
"node_modules",
"dist"
]
}

6
src/brave-search/package.json
View file

@ -1,6 +1,6 @@
{
"name": "@modelcontextprotocol/server-brave-search",
"version": "0.5.2",
"version": "0.6.2",
"description": "MCP server for Brave Search API integration",
"license": "MIT",
"author": "Anthropic, PBC (https://anthropic.com)",
@ -19,11 +19,11 @@
"watch": "tsc --watch"
},
"dependencies": {
"@modelcontextprotocol/sdk": "0.5.0"
"@modelcontextprotocol/sdk": "1.0.1"
},
"devDependencies": {
"@types/node": "^20.10.0",
"shx": "^0.3.4",
"typescript": "^5.6.2"
}
}
}

73
src/everart/README.md Normal file
View file

@ -0,0 +1,73 @@
# EverArt MCP Server
Image generation server for Claude Desktop using EverArt's API.
## Install
```bash
npm install
export EVERART_API_KEY=your_key_here
```
## Config
Add to Claude Desktop config:
```json
{
"mcpServers": {
"everart": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-everart"],
"env": {
"EVERART_API_KEY": "your_key_here"
}
}
}
}
```
## Tools
### generate_image
Generates images with multiple model options. Opens result in browser and returns URL.
Parameters:
```typescript
{
prompt: string, // Image description
model?: string, // Model ID (default: "207910310772879360")
image_count?: number // Number of images (default: 1)
}
```
Models:
- 5000: FLUX1.1 (standard)
- 9000: FLUX1.1-ultra
- 6000: SD3.5
- 7000: Recraft-Real
- 8000: Recraft-Vector
All images generated at 1024x1024.
Sample usage:
```javascript
const result = await client.callTool({
name: "generate_image",
arguments: {
prompt: "A cat sitting elegantly",
model: "7000",
image_count: 1
}
});
```
Response format:
```
Image generated successfully!
The image has been opened in your default browser.
Generation details:
- Model: 7000
- Prompt: "A cat sitting elegantly"
- Image URL: https://storage.googleapis.com/...
You can also click the URL above to view the image again.
```

160
src/everart/index.ts Normal file
View file

@ -0,0 +1,160 @@
#!/usr/bin/env node
import EverArt from "everart";
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import {
CallToolRequestSchema,
ListToolsRequestSchema,
ListResourcesRequestSchema,
ReadResourceRequestSchema,
} from "@modelcontextprotocol/sdk/types.js";
import fetch from "node-fetch";
import open from "open";
const server = new Server(
{
name: "example-servers/everart",
version: "0.2.0",
},
{
capabilities: {
tools: {},
resources: {}, // Required for image resources
},
},
);
if (!process.env.EVERART_API_KEY) {
console.error("EVERART_API_KEY environment variable is not set");
process.exit(1);
}
const client = new EverArt.default(process.env.EVERART_API_KEY);
server.setRequestHandler(ListToolsRequestSchema, async () => ({
tools: [
{
name: "generate_image",
description:
"Generate images using EverArt Models and returns a clickable link to view the generated image. " +
"The tool will return a URL that can be clicked to view the image in a browser. " +
"Available models:\n" +
"- 5000:FLUX1.1: Standard quality\n" +
"- 9000:FLUX1.1-ultra: Ultra high quality\n" +
"- 6000:SD3.5: Stable Diffusion 3.5\n" +
"- 7000:Recraft-Real: Photorealistic style\n" +
"- 8000:Recraft-Vector: Vector art style\n" +
"\nThe response will contain a direct link to view the generated image.",
inputSchema: {
type: "object",
properties: {
prompt: {
type: "string",
description: "Text description of desired image",
},
model: {
type: "string",
description:
"Model ID (5000:FLUX1.1, 9000:FLUX1.1-ultra, 6000:SD3.5, 7000:Recraft-Real, 8000:Recraft-Vector)",
default: "5000",
},
image_count: {
type: "number",
description: "Number of images to generate",
default: 1,
},
},
required: ["prompt"],
},
},
],
}));
server.setRequestHandler(ListResourcesRequestSchema, async () => {
return {
resources: [
{
uri: "everart://images",
mimeType: "image/png",
name: "Generated Images",
},
],
};
});
server.setRequestHandler(ReadResourceRequestSchema, async (request) => {
if (request.params.uri === "everart://images") {
return {
contents: [
{
uri: "everart://images",
mimeType: "image/png",
blob: "", // Empty since this is just for listing
},
],
};
}
throw new Error("Resource not found");
});
server.setRequestHandler(CallToolRequestSchema, async (request) => {
if (request.params.name === "generate_image") {
try {
const {
prompt,
model = "207910310772879360",
image_count = 1,
} = request.params.arguments as any;
// Use correct EverArt API method
const generation = await client.v1.generations.create(
model,
prompt,
"txt2img",
{
imageCount: image_count,
height: 1024,
width: 1024,
},
);
// Wait for generation to complete
const completedGen = await client.v1.generations.fetchWithPolling(
generation[0].id,
);
const imgUrl = completedGen.image_url;
if (!imgUrl) throw new Error("No image URL");
// Automatically open the image URL in the default browser
await open(imgUrl);
// Return a formatted message with the clickable link
return {
content: [
{
type: "text",
text: `Image generated successfully!\nThe image has been opened in your default browser.\n\nGeneration details:\n- Model: ${model}\n- Prompt: "${prompt}"\n- Image URL: ${imgUrl}\n\nYou can also click the URL above to view the image again.`,
},
],
};
} catch (error: unknown) {
console.error("Detailed error:", error);
const errorMessage =
error instanceof Error ? error.message : "Unknown error";
return {
content: [{ type: "text", text: `Error: ${errorMessage}` }],
isError: true,
};
}
}
throw new Error(`Unknown tool: ${request.params.name}`);
});
async function runServer() {
const transport = new StdioServerTransport();
await server.connect(transport);
console.error("EverArt MCP Server running on stdio");
}
runServer().catch(console.error);

32
src/everart/package.json Normal file
View file

@ -0,0 +1,32 @@
{
"name": "@modelcontextprotocol/server-everart",
"version": "0.6.2",
"description": "MCP server for EverArt API integration",
"license": "MIT",
"author": "Anthropic, PBC (https://anthropic.com)",
"homepage": "https://modelcontextprotocol.io",
"bugs": "https://github.com/modelcontextprotocol/servers/issues",
"type": "module",
"bin": {
"mcp-server-everart": "dist/index.js"
},
"files": [
"dist"
],
"scripts": {
"build": "tsc && shx chmod +x dist/*.js",
"prepare": "npm run build",
"watch": "tsc --watch"
},
"dependencies": {
"@modelcontextprotocol/sdk": "0.5.0",
"everart": "^1.0.0",
"node-fetch": "^3.3.2",
"open": "^9.1.0"
},
"devDependencies": {
"@types/node": "^20.11.0",
"shx": "^0.3.4",
"typescript": "^5.3.3"
}
}

10
src/everart/tsconfig.json Normal file
View file

@ -0,0 +1,10 @@
{
"extends": "../../tsconfig.json",
"compilerOptions": {
"outDir": "./dist",
"rootDir": "."
},
"include": [
"./**/*.ts"
]
}

6
src/everything/package.json
View file

@ -1,6 +1,6 @@
{
"name": "@modelcontextprotocol/server-everything",
"version": "0.5.1",
"version": "0.6.2",
"description": "MCP server that exercises all the features of the MCP protocol",
"license": "MIT",
"author": "Anthropic, PBC (https://anthropic.com)",
@ -19,7 +19,7 @@
"watch": "tsc --watch"
},
"dependencies": {
"@modelcontextprotocol/sdk": "0.5.0",
"@modelcontextprotocol/sdk": "1.0.1",
"express": "^4.21.1",
"zod": "^3.23.8",
"zod-to-json-schema": "^3.23.5"
@ -29,4 +29,4 @@
"shx": "^0.3.4",
"typescript": "^5.6.2"
}
}
}

2
src/fetch/pyproject.toml
View file

@ -1,6 +1,6 @@
[project]
name = "mcp-server-fetch"
version = "0.6.1"
version = "0.6.2"
description = "A Model Context Protocol server providing tools to fetch and convert web content for usage by LLMs"
readme = "README.md"
requires-python = ">=3.10"

18
src/fetch/src/mcp_server_fetch/server.py
View file

@ -44,7 +44,7 @@ def extract_content_from_html(html: str) -> str:
return content
def get_robots_txt_url(url: AnyUrl | str) -> str:
def get_robots_txt_url(url: str) -> str:
"""Get the robots.txt URL for a given website URL.
Args:
@ -54,7 +54,7 @@ def get_robots_txt_url(url: AnyUrl | str) -> str:
URL of the robots.txt file
"""
# Parse the URL into components
parsed = urlparse(str(url))
parsed = urlparse(url)
# Reconstruct the base URL with just scheme, netloc, and /robots.txt path
robots_url = urlunparse((parsed.scheme, parsed.netloc, "/robots.txt", "", "", ""))
@ -62,7 +62,7 @@ def get_robots_txt_url(url: AnyUrl | str) -> str:
return robots_url
async def check_may_autonomously_fetch_url(url: AnyUrl | str, user_agent: str) -> None:
async def check_may_autonomously_fetch_url(url: str, user_agent: str) -> None:
"""
Check if the URL can be fetched by the user agent according to the robots.txt file.
Raises a McpError if not.
@ -74,7 +74,9 @@ async def check_may_autonomously_fetch_url(url: AnyUrl | str, user_agent: str) -
async with AsyncClient() as client:
try:
response = await client.get(
robot_txt_url, headers={"User-Agent": user_agent}
robot_txt_url,
follow_redirects=True,
headers={"User-Agent": user_agent},
)
except HTTPError:
raise McpError(
@ -93,7 +95,7 @@ async def check_may_autonomously_fetch_url(url: AnyUrl | str, user_agent: str) -
line for line in robot_txt.splitlines() if not line.strip().startswith("#")
)
robot_parser = Protego.parse(processed_robot_txt)
if not robot_parser.can_fetch(url, user_agent):
if not robot_parser.can_fetch(str(url), user_agent):
raise McpError(
INTERNAL_ERROR,
f"The sites robots.txt ({robot_txt_url}), specifies that autonomous fetching of this page is not allowed, "
@ -106,7 +108,7 @@ async def check_may_autonomously_fetch_url(url: AnyUrl | str, user_agent: str) -
async def fetch_url(
url: AnyUrl | str, user_agent: str, force_raw: bool = False
url: str, user_agent: str, force_raw: bool = False
) -> Tuple[str, str]:
"""
Fetch the URL and return the content in a form ready for the LLM, as well as a prefix string with status information.
@ -116,7 +118,7 @@ async def fetch_url(
async with AsyncClient() as client:
try:
response = await client.get(
str(url),
url,
follow_redirects=True,
headers={"User-Agent": user_agent},
timeout=30,
@ -221,7 +223,7 @@ Although originally you did not have internet access, and were advised to refuse
except ValueError as e:
raise McpError(INVALID_PARAMS, str(e))
url = args.url
url = str(args.url)
if not url:
raise McpError(INVALID_PARAMS, "URL is required")

2
src/fetch/uv.lock generated
View file

@ -327,7 +327,7 @@ wheels = [
[[package]]
name = "mcp-server-fetch"
version = "0.1.3"
version = "0.6.2"
source = { editable = "." }
dependencies = [
{ name = "markdownify" },

6
src/filesystem/package.json
View file

@ -1,6 +1,6 @@
{
"name": "@modelcontextprotocol/server-filesystem",
"version": "0.5.1",
"version": "0.6.2",
"description": "MCP server for filesystem access",
"license": "MIT",
"author": "Anthropic, PBC (https://anthropic.com)",
@ -19,7 +19,7 @@
"watch": "tsc --watch"
},
"dependencies": {
"@modelcontextprotocol/sdk": "0.5.0",
"@modelcontextprotocol/sdk": "1.0.1",
"glob": "^10.3.10",
"zod-to-json-schema": "^3.23.5"
},
@ -28,4 +28,4 @@
"shx": "^0.3.4",
"typescript": "^5.3.3"
}
}
}

Some files were not shown because too many files have changed in this diff Show more