$ loading_
Orchestrate local LMs with file tools and Ollama for coding tasks.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mcp-coding" yet — see the docs or source repo.
Use mcp-coding to scan Python files in the current project, find duplicated data-cleaning logic, refactor it into shared functions in utils/cleaning.py, and update all references. List the change plan first, then apply writes.
A refactor plan, a list of changed files, and the applied code updates.
Based on the existing README and src directory, create a CLI agent script for this project that works with Ollama, reads a task instruction file, generates code, and writes results to a specified output directory.
A runnable CLI script, setup or usage notes, and a list of created files.
Read the JavaScript files in the project, check for missing error handling, unused variables, and possible path issues; list problems by file and directly fix low-risk issues while keeping a change log.
A problem list, fix notes, and the updated file contents.
Offload simple coding tasks to local Ollama and reduce Claude API usage.
Securely let AI read, search, and edit local files with local LLMs.
Securely read, write, and list files inside AI-driven workflows.
Give AI coding agents filesystem, Git, database, and compute tools via MCP.
Connect local Ollama to MCP apps for chat, model management, and generation.
Securely access filesystems over HTTP and analyze code with LLMs.