Category: AI

Recently I installed claude code – without an Anthropic account. I am using DeepSeek api because it’s good, and cheap.

For website updates, it is helpful to have the AI automate some things, to check that the updates work irl. Recently Google launched their official Crome Devtools MCP. I heard it works great with claude cli. Turns out it works great with claude cli hacked to use DeepSeek api also!

Installation

(After installing and setting up claude-code-router and claude cli)

Just run: claude mcp add chrome-devtools -- npx chrome-devtools-mcp@latest

Now you can run the claude-code-router in your coding project directory:

ccr code

and then type /mcp to check – the devtools should be listed.

Running

You can do this in several ways, but I like to run the browser and get the mcp to connect to already running session. On my Arch linux laptop I do this:

google-chrome-stable --remote-debugging-port=9222 --user-data-dir=/home/tom/Downloads/temp_chrome/

You need to specify the default debug port and a directory for your session (if you don’t add a temp directory, the AI might have access to your Chrome session, logins etc. Maybe you want that?). Chrome will think you are starting it for the first time – at least the first time you do this – so click through the prompts.

After Chrome is running, you can ask claude cli (with DeepSeek api back-end) to do stuff in your browser. Just ask it to use chrome-devtools-mcp and it will.

I am hoping to use this a lot, make changes and then get the AI to test everything works, iterate..

Don’t do this

ccr code --dangerously-skip-permissions

– gives the ai full control of your computer and no need to ask permission from you to do whatever it wants. Including finishing your project while you watch anime! (Or deleting everything on your hard drive…).

OK I didn’t do it all by myself – I just ran the reverse engineered proxy called claude-code-router which is already set up.

On Arch linux it’s as easy as doing:

yay claude-code 
yay claude-code-router
# and then finally:
ccr code

“ccr” runs claude cli behind a proxy – and routes all requests to your LLM service of choice (even local LLM if you have a powerful enough computer). When it runs for the first time you get to add your api details (in my case DeepSeek api).

You can also install it in other ways – like with npm/npx.

Many people were telling me about how good Claude Code CLI is. Now I can try out Claude Code CLI without paying $$$ – and it works! Even paying Claude Code users are doing this, because they run out of credits (Claude is expensive) and DeepSeek is just as good?

I don’t even have an Anthropic account!

I am still going to be using Aider for my main coding assistant, because I still prefer the control it offers. But for some things having options like MCP integration and proper vibe coding flow is important (like my new take on “Space Invaders” done with Pygame, coming soon!)

Check out the claude-code-router project and see what you think!

PS: Claude Code and Aider share many similarities when it comes to syntax. commands start with “/”, files are addressed with “@”, you can “/clear” to remove chat history from context… I wonder which one came first?

For the money of course! The brief is to “Use AI to do the challenge” so it’s definitely up my alley. Also, they will be having some industry experts to learn from, so I hope to learn something also.

https://aipiraterecruitmentagent.devsoft.co.za

Link to code is on the site.

• Built with Flask
• DeepSeek R1 for AI
  
  – did this instead of updating my CV (I have done that too now..)

MCP is the new AI buzzword. Being a bit involved in the AI-enhanced programming of my own projects, it escaped my attention until about a week ago. It’s time to have a look.

What I am using

Since I don’t want to pay any money (MCP can drain your tokens pretty quick!) I tried setting this up using local models first – but they are very slow on my laptop and I went with Deepseek Chat which is cheap for this test.

Essential Programs

1. Ollama – run LLM’s on your own computer
2. MCP Client for Ollama – allows your local models to connect to MCP’s and for you to configure and control everything from the command line OR:
3. ChatMCP – cross platform GUI program for chatting to MCP enhanced LLM’s. Configure any LLM from api (Deepseek, Claude, OpenAI) to Ollama.
4. MCP’s – there are literally thousands of these already! Some lists I found:
   – https://github.com/modelcontextprotocol/servers
   – https://glama.ai/mcp/servers
5. DeepSeek – get your api key (or sign up for OpenRouter and use the free rate limited one!)
   
   
   

Example using ChatMCP

I will be using this simple calculator MCP as an example:
– https://github.com/githejie/mcp-server-calculator
I just happened to have qwen2.5-coder:1.5b already installed in Ollama so that’s the one I am using (it supports tools) actually I used Deepseek Chat – Ollama is a bit slow on my laptop (it does work though).

In ChatMCP we add the tool like so:

After configuring my Deepseek API key in the settings (bottom right) I choose it from the menu.

DeepSeek Chat works fine (and it’s cheaper). I also got qwen2.5-coder to call tools, it’s a bit slow on my laptop, however (requires Ollama to be running in the background and I don’t have a GPU).

You need to enable the tool:

Then just make the request:

As you can see the AI used the calculator tool (spanner icon) to answer the request! There are so many tools available, from web scraping to controlling your android phone! I even made my own MCP tool to turn on an LED.

I just took a photo with my Android phone by telling the AI to do it for me (using phone-mcp)! What will your MCP enabled AI assistant be able to do?

NOTES

You can add MCP tools to your coding assistant now (eg. Cursor). I am using Cline which has a plugin for VSCode and allows for Deepseek API use (I already pay for this). The configuration looks like this (same format for “MCP Client for Ollama”):

{
  "mcpServers": {
    "hello-world-server": {
      "disabled": false,
      "timeout": 60,
      "command": "/run/media/tom/9109f38b-6b5f-4e3d-a26f-dd920ac0edb6/Manjaro-Home-Backup/3717d0b5-ba54-4c0a-8e8d-407af5c801bd/@home/tom/Documents/PROGRAMMING/Python/mcp_servers/hello_world/.venv/bin/python",
      "args": [
        "-u",
        "/run/media/tom/9109f38b-6b5f-4e3d-a26f-dd920ac0edb6/Manjaro-Home-Backup/3717d0b5-ba54-4c0a-8e8d-407af5c801bd/@home/tom/Documents/PROGRAMMING/Python/mcp_servers/hello_world/server_mcp.py"
      ],
      "env": {
        "PYTHONUNBUFFERED": "1"
      },
      "transportType": "stdio"
    },
    "blink-led-server": {
      "disabled": false,
      "timeout": 60,
      "command": "/run/media/tom/9109f38b-6b5f-4e3d-a26f-dd920ac0edb6/Manjaro-Home-Backup/3717d0b5-ba54-4c0a-8e8d-407af5c801bd/@home/tom/Documents/PROGRAMMING/Python/mcp_servers/mcp_duino/.venv/bin/python",
      "args": [
        "/run/media/tom/9109f38b-6b5f-4e3d-a26f-dd920ac0edb6/Manjaro-Home-Backup/3717d0b5-ba54-4c0a-8e8d-407af5c801bd/@home/tom/Documents/PROGRAMMING/Python/mcp_servers/mcp_duino/server_mcp.py"
      ],
      "env": {},
      "transportType": "stdio"
    },
    "github.com/modelcontextprotocol/servers/tree/main/src/puppeteer": {
      "disabled": false,
      "timeout": 60,
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "--init",
        "-e", "DOCKER_CONTAINER=true",
        "-e", "DISPLAY=$DISPLAY",
        "-v", "/tmp/.X11-unix:/tmp/.X11-unix:rw",
        "--security-opt", "seccomp=unconfined",
        "mcp/puppeteer",
        "--disable-web-security",
        "--no-sandbox",
        "--disable-dev-shm-usage"
      ],
      "env": {},
      "transportType": "stdio"
    },
    "phone-mcp": {
      "command": "uvx",
      "args": [
        "phone-mcp"
      ]
    },
    "calculator": {
      "command": "uvx",
      "args": [
        "mcp-server-calculator"
      ]
    }
  }
}

As you can see, uvx solves a lot of configuration long story here – otherwise you have to specify the path of your virtual environment.

The most common MCP servers are Node based, or Python. I am using Python as it’s my preferred language. Node is pretty similar, just use npx instead of uv.

Next Steps

Next up: converting all of my code to work with MCP. Seriously – if you aren’t MCP compatible, then you need to work on it, I think in the future this will be very important. Check out FastMCP for python implementation.

I use the open source and very capable Aider for AI code generation. Anyone who has tried AI code generation has heard of “context” – the information you send over to the LLM so that it can know what the code looks like that you want to modify.

Anyone using these tools eventually comes up against the dreaded token limit at some point – some sooner rather than later! The LLM can only keep so much context in memory at one time. This is annoying if you are trying to update a legacy codebase with multiple files and countless lines of code – who wants to try to pare this down to only the relevant parts, copy and paste into the window?

In Aider adding files to context is as simple as /add file.txt
To remove files just do /drop file.txt
If file.txt is 100 000 lines long you have to copy and paste the parts you want (up to 60 000 tokens), check how many you have left by running /tokens
But that is takes too long! It defeats the purpose of getting AI to do the reading and modifying for you (remember to review the diffs after!)

Meet LLMAP

llmap is “context extraction at scale”. The tool can search and sumarise vast amounts of code and ouput only the relevant parts which you can then add to your AI coding tool context – leaving out all irrelevant parts (usually most of it!)
Example from my own use case: I had an issue with a looping api request on ESP32 in my Magic Poi project – I had been concentrating on the battery monitor feature and the new feature broke some other functionality. So I did a diff with the last known working branch:
git diff origin/Battery_Monitor_Main_Merge > context_git_diff.txt

This diff is from way back though so it was too large for the context window (if you include all of the code I wanted to update) so I had to run it through llmap with a query:
echo context_git_diff.txt | llmap "list the changes made that affect the control flow of the application." > llmap_diff_context.txt

Now my new file llmap_diff_context.txt with only the relevant information could be added to the context – using /read-only since it’s not included in git nor do I want to edit it. I used /architect mode* to see what changes happened to cause the loop. Turns out it was a simple misplaced line of code and everything worked again!
*for me architect mode is configured to use DeepSeek R1 for thinking and V3 for editing – cheap and effective

LLMAP is easy to use – just install via pip. By the way, if you don’t have a DeepSeek api key, the update I recently submitted to add OpenRouter support has been merged but not yet published. You will have to download and install llmap manually to use OpenRouter – but it works.

Full credit to Johnathan Ellis for creating and sharing this great tool. You gotta love Open Source!