Context Coder: MCP server providing secure file system operations with relative path handling for AI context management
Context Coder: MCP server providing secure file system operations with relative path handling for AI context management. That is what the safe file mcp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
Context Coder (aka. Coco) provides AI models with an MCP tools to load your entire codebase into the LLM context. This gives AI assistants everything they need to write code that fits your existing patterns and architecture.
The server publishes 11 tools. What each one is for:
get_codebase_top_largest_files — Get top X largest files in codebase - helpful for identifying files to add to .cocoignore/.cocominifyread_file — Read file contents (only use when specifically asked to re-read or for debugging)write_file — Create or overwrite filesedit_file — Make line-based partial edits to files (available when --edit-file-mode is enabled)create_directory — Create directorieslist_directory — List directory contents (only use when specifically asked or for debugging)directory_tree — Get directory structure as JSON (only use when specifically asked or for debugging)move_file — Move or rename filessearch_files — Search by patternexecute_command — Run shell commandsCombining — You can have both a .cocoignore and a .cocominify file in the same repoInstallation goes through your MCP client rather than a global install: point it at context-coder on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Plenty of file and storage access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Safe File MCP's toolset — get_codebase_top_largest_files, read_file, write_file and 8 more — is a fair guide to whether it matches your workflow. It is maintained by khromov; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| get_codebase_top_largest_files | Get top X largest files in codebase - helpful for identifying files to add to .cocoignore/.cocominify |
| read_file | Read file contents (only use when specifically asked to re-read or for debugging) |
| write_file | Create or overwrite files |
| edit_file | Make line-based partial edits to files (available when --edit-file-mode is enabled) |
| create_directory | Create directories |
| list_directory | List directory contents (only use when specifically asked or for debugging) |
| directory_tree | Get directory structure as JSON (only use when specifically asked or for debugging) |
| move_file | Move or rename files |
| search_files | Search by pattern |
| execute_command | Run shell commands |
| Combining | You can have both a .cocoignore and a .cocominify file in the same repo. |
{
"mcpServers": {
"context-coder": {
"command": "npx",
"args": ["-y", "supergateway", "--streamableHttp", "http://localhost:3001/mcp"]
}
}
}Configuration as documented by the project. Restart the client after saving.
Scoped local file access — read, write, search and reorganise files in directories you explicitly allow.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Connects AI models to an Obsidian knowledge base for direct access and manipulation of notes and folders.