wehub-resource-sync
1338 lines
32 KiB
Plaintext
1338 lines
32 KiB
Plaintext
---
|
|
title: MCP Clients
|
|
description: Installation examples for MCP clients
|
|
---
|
|
|
|
Context7 supports all MCP clients. Below are configuration examples for popular clients. If your client isn't listed, check its documentation for MCP server installation. To configure manually, use the Context7 server URL `https://mcp.context7.com/mcp` with your MCP client and pass your API key via the `CONTEXT7_API_KEY` header.
|
|
|
|
<Tip>
|
|
Looking for the easiest way to get started? Use `npx ctx7 setup` to configure Context7
|
|
automatically, and `npx ctx7 remove` to remove the generated setup later. See the [CLI
|
|
docs](/clients/cli) for more details.
|
|
</Tip>
|
|
|
|
<Note>
|
|
For detailed guides including rules, skills, agents, and best practices, see
|
|
[Cursor](/clients/cursor) for rules and Composer integration tips, and [Claude
|
|
Code](/clients/claude-code) for skills, agents, commands, and plugin installation.
|
|
</Note>
|
|
|
|
## OAuth Authentication
|
|
|
|
Context7 MCP server supports OAuth 2.0 authentication for MCP clients that implement the [MCP OAuth specification](https://modelcontextprotocol.io/specification/2025-03-26/basic/authorization).
|
|
|
|
To use OAuth, change the endpoint from `/mcp` to `/mcp/oauth` in your client configuration:
|
|
|
|
```diff
|
|
- "url": "https://mcp.context7.com/mcp"
|
|
+ "url": "https://mcp.context7.com/mcp/oauth"
|
|
```
|
|
|
|
OAuth is only available for remote HTTP connections. For local MCP connections using stdio transport, use API key authentication instead.
|
|
|
|
<AccordionGroup>
|
|
|
|
<Accordion title="Claude Code">
|
|
|
|
Run this command. See [Claude Code MCP docs](https://code.claude.com/docs/en/mcp) for more info.
|
|
|
|
#### Local Server Connection
|
|
|
|
```sh
|
|
claude mcp add --scope user context7 -- npx -y @upstash/context7-mcp --api-key YOUR_API_KEY
|
|
```
|
|
|
|
#### Remote Server Connection
|
|
|
|
```sh
|
|
claude mcp add --scope user --header "CONTEXT7_API_KEY: YOUR_API_KEY" --transport http context7 https://mcp.context7.com/mcp
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Cursor">
|
|
|
|
Go to: `Cursor Settings` -> `Tools & MCP` -> `New MCP Server`
|
|
|
|
Pasting the following configuration into your Cursor `~/.cursor/mcp.json` file is the recommended approach. You may also install in a specific project by creating `.cursor/mcp.json` in your project folder. See [Cursor MCP docs](https://cursor.com/docs/context/mcp) for more info.
|
|
|
|
Since Cursor 1.0, you can click the install button below for instant one-click installation.
|
|
|
|
#### Remote Server Connection
|
|
|
|
[](https://cursor.com/en/install-mcp?name=context7&config=eyJ1cmwiOiJodHRwczovL21jcC5jb250ZXh0Ny5jb20vbWNwIn0%3D)
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"url": "https://mcp.context7.com/mcp",
|
|
"headers": {
|
|
"CONTEXT7_API_KEY": "YOUR_API_KEY"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
#### Local Server Connection
|
|
|
|
[](https://cursor.com/en/install-mcp?name=context7&config=eyJjb21tYW5kIjoibnB4IC15IEB1cHN0YXNoL2NvbnRleHQ3LW1jcCJ9)
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Opencode">
|
|
|
|
Add this to your Opencode configuration file. See [Opencode MCP docs](https://opencode.ai/docs/mcp-servers) for more info.
|
|
|
|
#### Remote Server Connection
|
|
|
|
```json
|
|
"mcp": {
|
|
"context7": {
|
|
"type": "remote",
|
|
"url": "https://mcp.context7.com/mcp",
|
|
"headers": {
|
|
"CONTEXT7_API_KEY": "YOUR_API_KEY"
|
|
},
|
|
"enabled": true
|
|
}
|
|
}
|
|
```
|
|
|
|
#### Local Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcp": {
|
|
"context7": {
|
|
"type": "local",
|
|
"command": ["npx", "-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"],
|
|
"enabled": true
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="OpenAI Codex">
|
|
|
|
See [OpenAI Codex MCP docs](https://developers.openai.com/codex/mcp) for more info.
|
|
|
|
#### Context7 Plugin
|
|
|
|
You can also install Context7 as a Codex plugin. It connects to the hosted MCP server and includes a documentation lookup skill. After installation, a browser window opens so you can log in via OAuth.
|
|
|
|
```sh
|
|
codex plugin marketplace add upstash/context7
|
|
codex plugin add context7@context7-marketplace
|
|
```
|
|
|
|
Start a new Codex thread after installation so Codex can load the plugin.
|
|
|
|
#### Using CLI
|
|
|
|
```sh
|
|
codex mcp add context7 -- npx -y @upstash/context7-mcp --api-key YOUR_API_KEY
|
|
```
|
|
|
|
#### Local Server Connection
|
|
|
|
Add this to your Codex configuration file (`~/.codex/config.toml` or `.codex/config.toml`).
|
|
|
|
```toml
|
|
[mcp_servers.context7]
|
|
command = "npx"
|
|
args = ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
startup_timeout_ms = 20_000
|
|
```
|
|
|
|
#### Remote Server Connection
|
|
|
|
```toml
|
|
[mcp_servers.context7]
|
|
url = "https://mcp.context7.com/mcp"
|
|
http_headers = { "CONTEXT7_API_KEY" = "YOUR_API_KEY" }
|
|
```
|
|
|
|
<Note>If you see startup timeout errors, try increasing `startup_timeout_ms` to `40_000`.</Note>
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Google Antigravity">
|
|
|
|
Add this to your Antigravity MCP config file. See [Antigravity MCP docs](https://antigravity.google/docs/mcp) for more info.
|
|
|
|
#### Remote Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"serverUrl": "https://mcp.context7.com/mcp",
|
|
"headers": {
|
|
"CONTEXT7_API_KEY": "YOUR_API_KEY"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
#### Local Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="VS Code">
|
|
|
|
The easiest way to install is the [Context7 VS Code extension](https://marketplace.visualstudio.com/items?itemName=Upstash.context7-mcp), which registers the server automatically and supports an API key via the `context7.apiKey` setting. See [VS Code](/clients/vscode) for details. For manual configuration, use the options below.
|
|
|
|
[<img alt="Install in VS Code (npx)" src="https://img.shields.io/badge/VS_Code-VS_Code?style=flat-square&label=Install%20Context7%20MCP&color=0098FF" />](https://insiders.vscode.dev/redirect?url=vscode%3Amcp%2Finstall%3F%7B%22name%22%3A%22context7%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40upstash%2Fcontext7-mcp%40latest%22%5D%7D)
|
|
[<img alt="Install in VS Code Insiders (npx)" src="https://img.shields.io/badge/VS_Code_Insiders-VS_Code_Insiders?style=flat-square&label=Install%20Context7%20MCP&color=24bfa5" />](https://insiders.vscode.dev/redirect?url=vscode-insiders%3Amcp%2Finstall%3F%7B%22name%22%3A%22context7%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40upstash%2Fcontext7-mcp%40latest%22%5D%7D)
|
|
|
|
Add this to your VS Code MCP config file (`.vscode/mcp.json`). See [VS Code MCP docs](https://code.visualstudio.com/docs/copilot/chat/mcp-servers) for more info.
|
|
|
|
#### Remote Server Connection
|
|
|
|
```json
|
|
{
|
|
"servers": {
|
|
"context7": {
|
|
"type": "http",
|
|
"url": "https://mcp.context7.com/mcp",
|
|
"headers": {
|
|
"CONTEXT7_API_KEY": "YOUR_API_KEY"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
#### Local Server Connection
|
|
|
|
```json
|
|
{
|
|
"servers": {
|
|
"context7": {
|
|
"type": "stdio",
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Kiro">
|
|
|
|
See [Kiro Model Context Protocol Documentation](https://kiro.dev/docs/mcp/configuration/) for details.
|
|
|
|
[](https://kiro.dev/launch/mcp/add?name=context7&config=%7B%22url%22%3A%22https%3A%2F%2Fmcp.context7.com%2Fmcp%22%2C%22disabled%22%3Afalse%2C%22autoApprove%22%3A%5B%5D%7D)
|
|
|
|
1. Navigate `Kiro` > `MCP Servers`
|
|
2. Add a new MCP server by clicking the `+ Add` button.
|
|
3. Paste the configuration:
|
|
|
|
#### Remote Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"url": "https://mcp.context7.com/mcp"
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
To use an API key in Kiro, add:
|
|
|
|
```json
|
|
"headers": {
|
|
"CONTEXT7_API_KEY": "YOUR_API_KEY"
|
|
}
|
|
```
|
|
|
|
See the [API keys guide](/howto/api-keys) for how to create one.
|
|
|
|
#### Local Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
4. Click `Save` to apply.
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Kilo Code">
|
|
|
|
You can configure the Context7 MCP server in **Kilo Code** using either the UI or by editing your config file. See [Kilo Code MCP docs](https://kilo.ai/docs/automate/mcp/using-in-kilo-code) for more info.
|
|
|
|
Kilo Code stores MCP servers in a `kilo.jsonc` file:
|
|
|
|
- **Global** — `~/.config/kilo/kilo.jsonc`
|
|
- **Project** — `kilo.jsonc` in your project root or `.kilo/kilo.jsonc` (takes precedence)
|
|
|
|
### Configure via Kilo Code UI
|
|
|
|
1. Click the **Settings** icon in the sidebar toolbar.
|
|
2. Navigate to the **Agent Behaviour** tab.
|
|
3. Select the **MCP Servers** sub-tab.
|
|
4. Click **Add Server** and choose **Remote (HTTP)** or **Local (stdio)**.
|
|
5. Fill in the details and save.
|
|
|
|
### Manual Configuration
|
|
|
|
Add Context7 under the `mcp` key in your `kilo.jsonc`.
|
|
|
|
#### Remote Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcp": {
|
|
"context7": {
|
|
"type": "remote",
|
|
"url": "https://mcp.context7.com/mcp",
|
|
"headers": {
|
|
"CONTEXT7_API_KEY": "YOUR_API_KEY"
|
|
},
|
|
"enabled": true
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
#### Local Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcp": {
|
|
"context7": {
|
|
"type": "local",
|
|
"command": ["npx", "-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"],
|
|
"enabled": true
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Roo Code">
|
|
|
|
Add this to your Roo Code MCP configuration file. See [Roo Code MCP docs](https://docs.roocode.com/features/mcp/using-mcp-in-roo) for more info.
|
|
|
|
#### Remote Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"type": "streamable-http",
|
|
"url": "https://mcp.context7.com/mcp",
|
|
"headers": {
|
|
"CONTEXT7_API_KEY": "YOUR_API_KEY"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
#### Local Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Devin Desktop">
|
|
|
|
Add this to your Devin Desktop MCP config file. See [Devin Desktop MCP docs](https://docs.devin.ai/desktop/cascade/mcp) for more info.
|
|
|
|
#### Remote Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"serverUrl": "https://mcp.context7.com/mcp",
|
|
"headers": {
|
|
"CONTEXT7_API_KEY": "YOUR_API_KEY"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
#### Local Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Claude Desktop">
|
|
|
|
#### Remote Server Connection
|
|
|
|
Open Claude Desktop and navigate to Settings > Connectors > Add Custom Connector. Enter the name as `Context7` and the remote MCP server URL as `https://mcp.context7.com/mcp`.
|
|
|
|
#### Local Server Connection
|
|
|
|
Open Claude Desktop developer settings and edit your `claude_desktop_config.json` file. See [Claude Desktop MCP docs](https://modelcontextprotocol.io/quickstart/user) for more info.
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="ChatGPT (Web)">
|
|
|
|
ChatGPT supports MCP servers through remote connectors via [Developer Mode](https://developers.openai.com/api/docs/guides/developer-mode) (beta). Available for Pro, Plus, Team, Enterprise, and Edu plans.
|
|
|
|
#### 1. Enable Developer Mode
|
|
|
|
Go to: `Settings` → `Apps` → `Advanced settings` → Enable `Developer Mode`
|
|
|
|
#### 2. Create an App
|
|
|
|
Go to: `Settings` → `Apps` → `Create App`
|
|
|
|
Fill in the following:
|
|
|
|
| Field | Value |
|
|
| ------------------ | ------------------------------------------------------------------------------------------- |
|
|
| **Name** | `Context7` |
|
|
| **Description** | `Fetch up-to-date documentation and code examples for any library directly from the source` |
|
|
| **MCP Server URL** | `https://mcp.context7.com/mcp/oauth` |
|
|
|
|
> Accept the security notice and complete the one-time OAuth authorization.
|
|
|
|
#### 3. Use in a Conversation
|
|
|
|
Start a new chat → Click the plus icon → Hover over `More` → Select the `Context7` app.
|
|
|
|
Alternatively, you can say `use context7` in your prompt and ChatGPT will automatically use the `Context7` app.
|
|
|
|
See [OpenAI MCP docs](https://developers.openai.com/api/docs/mcp) for more info.
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="ChatGPT (Desktop)">
|
|
|
|
The ChatGPT desktop app shares apps configured on the web. Set up the app on [chatgpt.com](https://chatgpt.com) first.
|
|
|
|
#### 1. Enable Developer Mode (on the Web)
|
|
|
|
Go to: `Settings` → `Apps` → `Advanced settings` → Enable `Developer Mode`
|
|
|
|
#### 2. Create an App (on the Web)
|
|
|
|
Go to: `Settings` → `Apps` → `Create App`
|
|
|
|
Fill in the following:
|
|
|
|
| Field | Value |
|
|
| ------------------ | ------------------------------------------------------------------------------------------- |
|
|
| **Name** | `Context7` |
|
|
| **Description** | `Fetch up-to-date documentation and code examples for any library directly from the source` |
|
|
| **MCP Server URL** | `https://mcp.context7.com/mcp/oauth` |
|
|
|
|
> Accept the security notice and complete the one-time OAuth authorization.
|
|
|
|
#### 3. Use in the Desktop App
|
|
|
|
Open the ChatGPT desktop app → Start a new chat → ChatGPT will automatically use the `Context7` app when you ask it to.
|
|
|
|
Apps configured on the web are automatically available in the desktop app.
|
|
|
|
See [OpenAI MCP docs](https://developers.openai.com/api/docs/mcp) for more info.
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Trae">
|
|
|
|
Use the Add manually feature and fill in the JSON configuration. See [Trae documentation](https://docs.trae.ai/ide/model-context-protocol?_lang=en) for more details.
|
|
|
|
#### Remote Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"url": "https://mcp.context7.com/mcp",
|
|
"headers": {
|
|
"CONTEXT7_API_KEY": "YOUR_API_KEY"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
#### Local Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Cline">
|
|
|
|
You can easily install Context7 through the [Cline MCP Server Marketplace](https://cline.bot/mcp-marketplace) by following these instructions:
|
|
|
|
1. Open **Cline**.
|
|
2. Click the hamburger menu icon to enter the **MCP Servers** section.
|
|
3. Use the search bar within the **Marketplace** tab to find _Context7_.
|
|
4. Click the **Install** button.
|
|
|
|
Or you can directly edit MCP servers configuration:
|
|
|
|
1. Open **Cline**.
|
|
2. Click the hamburger menu icon to enter the **MCP Servers** section.
|
|
3. Choose **Remote Servers** tab.
|
|
4. Click the **Edit Configuration** button.
|
|
5. Add context7 to `mcpServers`:
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"url": "https://mcp.context7.com/mcp",
|
|
"headers": {
|
|
"Authorization": "Bearer YOUR_API_KEY"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Augment Code">
|
|
|
|
To configure Context7 MCP in Augment Code, you can use either the graphical interface or manual configuration. See [Augment Code MCP docs](https://docs.augmentcode.com/setup-augment/mcp) for more info.
|
|
|
|
### Using the Augment Code UI
|
|
|
|
1. Open the options menu in the upper right of the Augment panel.
|
|
2. Select **Settings**.
|
|
3. Navigate to the **MCP** section.
|
|
4. Click the **+** button to add a new server.
|
|
5. Enter the name **Context7** and the command:
|
|
|
|
```
|
|
npx -y @upstash/context7-mcp@latest
|
|
```
|
|
|
|
### Manual Configuration
|
|
|
|
In the **MCP** section, use **Import from JSON** and paste the following (a top-level `mcpServers` object keyed by server name):
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Gemini CLI">
|
|
|
|
See [Gemini CLI Configuration](https://google-gemini.github.io/gemini-cli/docs/tools/mcp-server.html) for details.
|
|
|
|
1. Open the Gemini CLI settings file at `~/.gemini/settings.json`
|
|
2. Add the following to the `mcpServers` object:
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"httpUrl": "https://mcp.context7.com/mcp",
|
|
"headers": {
|
|
"CONTEXT7_API_KEY": "YOUR_API_KEY",
|
|
"Accept": "application/json, text/event-stream"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
Or, for a local server:
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Hermes">
|
|
|
|
Use the Hermes CLI or edit `~/.hermes/config.yaml` directly. See the [Hermes CLI docs](https://github.com/nousresearch/hermes-agent/blob/main/website/docs/reference/cli-commands.md) for more info.
|
|
|
|
#### Remote Server Connection (API Key)
|
|
|
|
Add this to your Hermes config file (`~/.hermes/config.yaml`).
|
|
|
|
```yaml
|
|
mcp_servers:
|
|
context7:
|
|
url: "https://mcp.context7.com/mcp"
|
|
headers:
|
|
CONTEXT7_API_KEY: "YOUR_API_KEY"
|
|
```
|
|
|
|
#### Remote Server Connection (OAuth)
|
|
|
|
```yaml
|
|
mcp_servers:
|
|
context7:
|
|
url: "https://mcp.context7.com/mcp/oauth"
|
|
auth: oauth
|
|
```
|
|
|
|
#### Using CLI (OAuth)
|
|
|
|
```sh
|
|
hermes mcp add context7 --url https://mcp.context7.com/mcp/oauth --auth oauth
|
|
```
|
|
|
|
#### Local Server Connection
|
|
|
|
```yaml
|
|
mcp_servers:
|
|
context7:
|
|
command: "npx"
|
|
args: ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
```
|
|
|
|
<Note>
|
|
Start with the API key method if you want the most direct setup. Hermes also supports OAuth for remote MCP servers via `auth: oauth`. On headless setups, Hermes may print an authorization URL to stdout or logs for you to open manually. If `hermes mcp add ... --auth oauth` drops into the interactive agent without saving the server entry, add the `mcp_servers.context7` config manually, then run `hermes mcp test context7` to trigger the auth flow and verify the connection.
|
|
</Note>
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Using Bun or Deno">
|
|
|
|
Use these alternatives to run the local Context7 MCP server with other runtimes.
|
|
|
|
#### Bun
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "bunx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
#### Deno
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "deno",
|
|
"args": [
|
|
"run",
|
|
"--allow-env=NO_DEPRECATION,TRACE_DEPRECATION",
|
|
"--allow-net",
|
|
"npm:@upstash/context7-mcp"
|
|
]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Copilot Coding Agent">
|
|
|
|
Add the following configuration to `Repository` -> `Settings` -> `Code & automation` -> `Copilot` -> `MCP servers`. Only secrets named with the `COPILOT_MCP_` prefix are exposed to the MCP config, so store your key as a `COPILOT_MCP_CONTEXT7_API_KEY` Actions secret and reference it:
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"type": "http",
|
|
"url": "https://mcp.context7.com/mcp",
|
|
"headers": {
|
|
"CONTEXT7_API_KEY": "$COPILOT_MCP_CONTEXT7_API_KEY"
|
|
},
|
|
"tools": ["query-docs", "resolve-library-id"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
See the [official GitHub documentation](https://docs.github.com/en/copilot/how-tos/agents/copilot-coding-agent/extending-copilot-coding-agent-with-mcp) for more info.
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Copilot CLI">
|
|
|
|
The easiest way is the Context7 plugin, which bundles the MCP server with a skill, an agent, and a command — see [GitHub Copilot CLI](/clients/copilot-cli). For manual configuration, open `~/.copilot/mcp-config.json` and add:
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"type": "http",
|
|
"url": "https://mcp.context7.com/mcp",
|
|
"headers": {
|
|
"CONTEXT7_API_KEY": "YOUR_API_KEY"
|
|
},
|
|
"tools": ["query-docs", "resolve-library-id"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
Or, for a local server:
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"type": "local",
|
|
"command": "npx",
|
|
"tools": ["query-docs", "resolve-library-id"],
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Amazon Q Developer CLI">
|
|
|
|
Add this to your Amazon Q Developer CLI configuration file. See [Amazon Q Developer CLI docs](https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/command-line-mcp-configuration.html) for more details.
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Warp">
|
|
|
|
See [Warp Model Context Protocol Documentation](https://docs.warp.dev/knowledge-and-collaboration/mcp#adding-an-mcp-server) for details.
|
|
|
|
1. Navigate `Settings` > `Agents` > `MCP servers`.
|
|
2. Add a new MCP server by clicking the `+ Add` button.
|
|
3. Paste the configuration:
|
|
|
|
```json
|
|
{
|
|
"Context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"],
|
|
"env": {},
|
|
"working_directory": null,
|
|
"start_on_launch": true
|
|
}
|
|
}
|
|
```
|
|
|
|
4. Click `Save`.
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Amp">
|
|
|
|
Run this command in your terminal. See [Amp MCP docs](https://ampcode.com/manual#mcp) for more info.
|
|
|
|
#### Without API Key (Basic Usage)
|
|
|
|
```sh
|
|
amp mcp add context7 https://mcp.context7.com/mcp
|
|
```
|
|
|
|
#### With API Key (Higher Rate Limits & Private Repos)
|
|
|
|
```sh
|
|
amp mcp add context7 --header "CONTEXT7_API_KEY=YOUR_API_KEY" https://mcp.context7.com/mcp
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Zed">
|
|
|
|
It can be installed via [Zed Extensions](https://zed.dev/extensions?query=Context7) or you can add this to your Zed `settings.json`. See [Zed MCP docs](https://zed.dev/docs/ai/mcp) for more info.
|
|
|
|
```json
|
|
{
|
|
"context_servers": {
|
|
"Context7": {
|
|
"source": "custom",
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Smithery">
|
|
|
|
To install Context7 MCP Server for any client automatically via [Smithery](https://smithery.ai/servers/@upstash/context7-mcp):
|
|
|
|
```bash
|
|
npx -y @smithery/cli@latest install @upstash/context7-mcp --client <CLIENT_NAME>
|
|
```
|
|
|
|
See the [Context7 server page on Smithery](https://smithery.ai/servers/@upstash/context7-mcp) for more details.
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="JetBrains AI Assistant">
|
|
|
|
See [JetBrains AI Assistant Documentation](https://www.jetbrains.com/help/ai-assistant/configure-an-mcp-server.html) for more details.
|
|
|
|
1. In JetBrains IDEs, go to `Settings` -> `Tools` -> `AI Assistant` -> `Model Context Protocol (MCP)`
|
|
2. Click `+ Add`.
|
|
3. Select the **HTTP** or **STDIO** tab and paste the JSON configuration.
|
|
4. Click `Apply` to save changes.
|
|
|
|
#### Remote Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"url": "https://mcp.context7.com/mcp"
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
#### Local Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Qwen Code">
|
|
|
|
See [Qwen Code MCP Configuration](https://qwenlm.github.io/qwen-code-docs/en/users/features/mcp/) for details.
|
|
|
|
### Using CLI Command
|
|
|
|
By default, configurations are saved to the project scope (`.qwen/settings.json`). Use the `--scope user` flag to save to the user scope (`~/.qwen/settings.json`) instead.
|
|
|
|
#### Remote Server Connection
|
|
|
|
```sh
|
|
qwen mcp add --transport http context7 https://mcp.context7.com/mcp \
|
|
--header "CONTEXT7_API_KEY: YOUR_API_KEY" \
|
|
--header "Accept: application/json, text/event-stream"
|
|
```
|
|
|
|
#### Local Server Connection
|
|
|
|
```sh
|
|
qwen mcp add context7 -- npx -y @upstash/context7-mcp --api-key YOUR_API_KEY
|
|
```
|
|
|
|
### Manual Configuration
|
|
|
|
1. Open the Qwen Code settings file at `~/.qwen/settings.json` (user scope) or `.qwen/settings.json` (project scope)
|
|
2. Add the following to the `mcpServers` object:
|
|
|
|
#### Remote Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"httpUrl": "https://mcp.context7.com/mcp",
|
|
"headers": {
|
|
"CONTEXT7_API_KEY": "YOUR_API_KEY",
|
|
"Accept": "application/json, text/event-stream"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
#### Local Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Using Docker">
|
|
|
|
1. Create a `Dockerfile`:
|
|
|
|
```Dockerfile
|
|
FROM node:22-alpine
|
|
WORKDIR /app
|
|
RUN npm install -g @upstash/context7-mcp
|
|
CMD ["context7-mcp", "--transport", "stdio"]
|
|
```
|
|
|
|
2. Build the image:
|
|
|
|
```bash
|
|
docker build -t context7-mcp .
|
|
```
|
|
|
|
3. Configure your MCP client:
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "docker",
|
|
"args": ["run", "-i", "--rm", "context7-mcp"],
|
|
"transportType": "stdio"
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Docker MCP Toolkit">
|
|
|
|
Context7 is available in the [Docker MCP Catalog](https://hub.docker.com/mcp/server/context7/overview) as a **remote** server, so you don't need to build, pull, or run a local image. The MCP Toolkit connects to the hosted endpoint for you.
|
|
|
|
1. In Docker Desktop, open **MCP Toolkit → Catalog**, search for **Context7**, and enable it.
|
|
2. (Optional) In the server's **Config** tab, set your Context7 API key (`CONTEXT7_API_KEY`) for higher rate limits. The server also works without one.
|
|
3. Connect your MCP client to Docker's MCP gateway. Either run `docker mcp client connect <client>` (for example `vscode`, `cursor`, or `claude-desktop`), or add the gateway to your client config manually:
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"MCP_DOCKER": {
|
|
"command": "docker",
|
|
"args": ["mcp", "gateway", "run"],
|
|
"type": "stdio"
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
The gateway exposes every server you've enabled in the MCP Toolkit, including Context7. Tools appear under the `MCP_DOCKER` server in your client.
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Windows">
|
|
|
|
The configuration on Windows is slightly different. Use `cmd` to run npx:
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "cmd",
|
|
"args": ["/c", "npx", "-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"],
|
|
"disabled": false,
|
|
"autoApprove": []
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="LM Studio">
|
|
|
|
See [LM Studio MCP docs](https://lmstudio.ai/docs/app/plugins/mcp) for more information.
|
|
|
|
#### One-click install:
|
|
|
|
[](https://lmstudio.ai/install-mcp?name=context7&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkB1cHN0YXNoL2NvbnRleHQ3LW1jcCJdfQ%3D%3D)
|
|
|
|
#### Manual set-up:
|
|
|
|
1. Navigate to `Program` (right side) > `Install` > `Edit mcp.json`.
|
|
2. Paste the configuration:
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"Context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
3. Click `Save`.
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Visual Studio 2022">
|
|
|
|
See [Visual Studio MCP Servers documentation](https://learn.microsoft.com/visualstudio/ide/mcp-servers?view=vs-2022) for details.
|
|
|
|
```json
|
|
{
|
|
"inputs": [],
|
|
"servers": {
|
|
"context7": {
|
|
"type": "http",
|
|
"url": "https://mcp.context7.com/mcp",
|
|
"headers": {
|
|
"CONTEXT7_API_KEY": "YOUR_API_KEY"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
Or, for a local server:
|
|
|
|
```json
|
|
{
|
|
"servers": {
|
|
"context7": {
|
|
"type": "stdio",
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Crush">
|
|
|
|
Add this to your Crush configuration file. See [Crush MCP docs](https://github.com/charmbracelet/crush#mcps) for more info.
|
|
|
|
#### Remote Server Connection
|
|
|
|
```json
|
|
{
|
|
"$schema": "https://charm.land/crush.json",
|
|
"mcp": {
|
|
"context7": {
|
|
"type": "http",
|
|
"url": "https://mcp.context7.com/mcp",
|
|
"headers": {
|
|
"CONTEXT7_API_KEY": "YOUR_API_KEY"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
#### Local Server Connection
|
|
|
|
```json
|
|
{
|
|
"$schema": "https://charm.land/crush.json",
|
|
"mcp": {
|
|
"context7": {
|
|
"type": "stdio",
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="BoltAI">
|
|
|
|
Open the "Settings" page, navigate to "Plugins," and enter:
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
See [BoltAI's Documentation](https://docs.boltai.com/docs/plugins/mcp-servers) for more info.
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Rovo Dev CLI">
|
|
|
|
Edit your Rovo Dev CLI MCP config:
|
|
|
|
```bash
|
|
acli rovodev mcp
|
|
```
|
|
|
|
#### Remote Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"url": "https://mcp.context7.com/mcp"
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
#### Local Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Zencoder">
|
|
|
|
1. Go to the Zencoder menu (...)
|
|
2. Select Agent tools
|
|
3. Click on Add custom MCP
|
|
4. Add the name and configuration:
|
|
|
|
```json
|
|
{
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
```
|
|
|
|
5. Click Install.
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Qodo Gen">
|
|
|
|
See [Qodo Gen docs](https://docs.qodo.ai/qodo-documentation/qodo-gen/qodo-gen-chat/agentic-mode/agentic-tools-mcps) for more details.
|
|
|
|
1. Open Qodo Gen chat panel in VSCode or IntelliJ.
|
|
2. Click Connect more tools.
|
|
3. Click + Add new MCP.
|
|
4. Add the configuration:
|
|
|
|
#### Local Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
#### Remote Server Connection
|
|
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"url": "https://mcp.context7.com/mcp"
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Perplexity Desktop">
|
|
|
|
See [Local and Remote MCPs for Perplexity](https://www.perplexity.ai/help-center/en/articles/11502712-local-and-remote-mcps-for-perplexity) for more information.
|
|
|
|
1. Navigate `Perplexity` > `Settings`
|
|
2. Select `Connectors`.
|
|
3. Click `Add Connector`.
|
|
4. Select `Advanced`.
|
|
5. Enter Server Name: `Context7`
|
|
6. Paste:
|
|
|
|
```json
|
|
{
|
|
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"],
|
|
"command": "npx",
|
|
"env": {}
|
|
}
|
|
```
|
|
|
|
7. Click `Save`.
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Factory">
|
|
|
|
Factory's droid supports MCP servers through its CLI. See [Factory MCP docs](https://docs.factory.ai/cli/configuration/mcp) for more info.
|
|
|
|
#### Remote Server Connection
|
|
|
|
```sh
|
|
droid mcp add context7 https://mcp.context7.com/mcp --type http --header "CONTEXT7_API_KEY: YOUR_API_KEY"
|
|
```
|
|
|
|
#### Local Server Connection
|
|
|
|
```sh
|
|
droid mcp add context7 "npx -y @upstash/context7-mcp" --env CONTEXT7_API_KEY=YOUR_API_KEY
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Emdash">
|
|
|
|
[Emdash](https://github.com/generalaction/emdash) is an orchestration layer for running multiple coding agents in parallel.
|
|
|
|
Context7 is available as a built-in entry in Emdash's MCP catalog. Enable it from the MCP view and provide your `CONTEXT7_API_KEY` (optional, for higher rate limits). Emdash adapts and writes the MCP config into your selected coding agent's config (Codex, Claude Code, Cursor, etc.) for you.
|
|
|
|
See the [Emdash repository](https://github.com/generalaction/emdash) for more information.
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="Desktop Extension">
|
|
|
|
Install the [context7.mcpb](https://github.com/upstash/context7/tree/master/packages/mcp/mcpb/context7.mcpb) file and add it to your client. See [MCP bundles docs](https://github.com/modelcontextprotocol/mcpb#mcp-bundles-mcpb) for more info.
|
|
|
|
</Accordion>
|
|
|
|
<Accordion title="AnythingLLM">
|
|
|
|
AnythingLLM supports MCP Servers through GUI.
|
|
|
|
1. Navigate `AnythingLLM` > `Agents Skills`
|
|
2. Select `MCP Servers`.
|
|
3. Click `Edit MCP config`.
|
|
4. Paste.
|
|
5. Click to "Refresh" button.
|
|
|
|
#### Remote Connection
|
|
```json
|
|
{
|
|
"mcpServers": {
|
|
"context7": {
|
|
"type": "streamable",
|
|
"url": "https://mcp.context7.com/mcp",
|
|
"headers": {
|
|
"CONTEXT7_API_KEY": "YOUR_API_KEY"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
```
|
|
|
|
</Accordion>
|
|
|
|
</AccordionGroup>
|