While Im still personally skeptical on the ability of these tools to produce a GOOD software engineer, it’s something I should probably consider testing in a limited capacity.
I’ve noticed Deepseek has a few integrations, both official and hobbyist, with text editors like Claude Code. Plus, I’d rather not pay £20/mo for any of this stuff, let alone to any AI company NOT linked to the CPC.
I might consider a locally hosted model but the upfront cost for anything that can run it decently fast/high params are quite prohibitive. My home server isn’t really set up for good cooling!


I’ve never heard anything specific about DeepSeek tho, I assume it’s strong on value and a great way to save on cost until you hit a problem that requires bigger thinkier models. Can it use MCP? I know SWE is very spotty on using MCP, even when you explicitly beg it to.
Deepseek can use MCP over the API if you have an MCP client. Although the use case for MCP isn’t as big as advertised. Deepseek-reasoner does a great job with those “thinkier” problems, especially if you chain the outputs and provide the right context. I don’t think it’s as good as Claude Sonnet-4.5, but it’s around 30 times cheaper.