Provides access to Chris's programming context and knowledge base stored in a GitHub repository, enabling AI agents to search for coding patterns, guidelines, and best practices for JavaScript, TypeScript, React, and various testing frameworks
Optionally integrates with OpenAI's embeddings API to enhance search capabilities within the context provider, upgrading from local embeddings to more sophisticated query processing
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Chris MCPwhat are your best practices for React hooks?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Chris MCP
A context provider on how I program. Basically the AI version of me for AI utilities like cline.
1. Install
The following sections describe several ways to install this MCP.
Make sure you are using Node version 22.
1.1. Option 1: Using NPX
Run the following commands in the same folder your other MCP servers are.
$ mkdir chris-mcp
$ cd chris-mcp
$ npx --y chris-mcp fetch --output ./data
$ npx --y chris-mcp verify --output ./data
$ pwdCopy the response from pwd and edit your MCP server configuration by following one of the options below.
1.1.1 Using NPX With Claude Desktop
Add the following configuration to your claude_desktop_config.json where [pwd] is the response from the pwd command earlier.
{
"name": "github.com/cblanquera/mcp",
"command": "npx",
"args": [
"-y",
"chris-mcp",
"serve",
"--input",
"[pwd]/data"
]
}1.1.2 Using NPX With Cline
Add the following configuration to your cline_mcp_settings.json where [pwd] is the response from the pwd command earlier.
{
"mcpServers": {
"github.com/cblanquera/mcp": {
"command": "npx",
"args": [
"-y",
"chris-mcp",
"serve",
"--input",
"[pwd]/data"
]
}
}
}1.2. Option 2: Direct From the Repository
Run the following commands in the same folder your other MCP servers are.
$ git clone https://github.com/cblanquera/mcp.git chris-mcp
$ cd chris-mcp
$ npm i
$ npm run build
$ npm run fetch --output ./data
$ npm run verify --output ./data
$ pwdCopy the response from pwd and edit your MCP server configuration by following one of the options below.
1.2.1. From the Repository With Claude Desktop
Add the following configuration to your claude_desktop_config.json.
{
"name": "github.com/cblanquera/mcp",
"command": "node",
"args": [
"[pwd]/dist/scripts/serve.js",
"--input",
"[pwd]/data"
]
}1.2.2. From the Repository With Cline
Add the following configuration to your cline_mcp_settings.json.
{
"mcpServers": {
"github.com/cblanquera/mcp": {
"command": "node",
"args": [
"[pwd]/dist/scripts/serve.js",
"--input",
"[pwd]/data"
]
}
}
}1.3. From Prompt
Copy and paste the following prompt.
Set up the MCP server from https://github.com/cblanquera/mcp while adhering to these MCP server installation rules:
- Start by loading the MCP documentation.
- Use "github.com/cblanquera/mcp" as the server name in cline_mcp_settings.json.
- Create the directory for the new MCP server before starting installation.
- Make sure you read the user's existing cline_mcp_settings.json file before editing it with this new mcp, to not overwrite any existing servers.
- Use commands aligned with the user's shell and operating system best practices.
- Once installed, demonstrate the server's capabilities by using one of its tools.
Here is the project's README to help you get started:Then paste in this README.
Related MCP server: Context Continuation MCP Server
2. Usage
You can manually start the server like the following.
$ npm start --input [pwd]/dataOr you can run it manually like the following.
$ node [pwd]/dist/scripts/serve.js --input [pwd]/dataIf you installed via npx, you can start the server like the following.
$ npx chris-mcp serve --input [pwd]/data2.1. Fetching Updated Context
You can manually fetch and verify the context like the following.
$ npm run fetch --output [pwd]/data
$ npm run verify --output [pwd]/dataOr you can run it manually like the following.
$ node [pwd]/dist/scripts/fetch.js --output [pwd]/data
$ node [pwd]/dist/scripts/verify.js --output [pwd]/dataIf you installed via npx, you can start the server like the following.
$ npx chris-mcp fetch --output [pwd]/data
$ npx chris-mcp verify --output [pwd]/data2.2. Upgrading Search Model
The MCP uses Xenova/all-MiniLM-L6-v2 locally to determine the best search query term for the MCP. Think about it like random prompt → correct query → ask MCP. You can upgrade this to use your OpenAI key by adding OPENAI_HOST, OPENAI_KEY and EMBEDDING_MODEL environment variables in your MCP settings like the following.
{
"name": "chris-context",
"command": "node",
"command": "npx",
"args": [
"-y",
"chris-mcp",
"serve",
"--input",
"[pwd]/data"
],
"env": {
"OPENAI_HOST": "https://api.openai.com/v1",
"OPENAI_KEY": "sk-xxx",
"EMBEDDING_MODEL": "text-embedding-3-small"
}
}WARNING: OpenRouter doesn't support the
/embeddingsAPI endpoint. This is called when providing an OpenAI compatible host.
3. Maximizing Your Knowledge Base
Create a rule (markdown file) called Chris-MCP-Rule.md in your knowledge folder (ex. .clinerules) with the following context.
# Rule: Using the Chris MCP
- If the user mentions "chris" and asks about code formatting, coding styles, coding standards, documentation styles, testing styles, use the MCP tool `chris-context.search_context`.
- If the user asks for a compact summary of rules for code formatting, writing documentation, writing tests, use the MCP tool `chris-context.build_brief`.
- Always prefer these MCP tools over answering from memory.This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.