Container-MCP provides a secure, sandboxed environment for executing code, running commands, accessing files, and performing web operations on behalf of large language models. Built by 54rt1n, it implements multiple layers of security including container isolation, AppArmor profiles, Firejail sandboxing, and strict resource limits to ensure safe execution of potentially risky operations. The architecture uses domain-specific managers for different operation types (Bash, Python, file operations, web browsing) and runs inside an Ubuntu container with carefully controlled permissions and access restrictions. This implementation is particularly valuable for AI workflows requiring secure tool execution without exposing the host system to potential risks.
暂无评论. 成为第一个评论的人！
登录以参与讨论
Executes bash commands in a secure sandbox environment. Parameters: command (string, required), working_dir (string, optional)
Executes Python code in a secure sandbox environment. Parameters: code (string, required), working_dir (string, optional)
Gets environment variable values. Parameters: var_name (string, optional)
Reads file contents safely. Parameters: path (string, required), encoding (string, optional)
Writes content to a file safely. Parameters: path (string, required), content (string, required), encoding (string, optional)
Lists contents of a directory safely. Parameters: path (string, optional), pattern (string, optional)
Deletes a file safely. Parameters: path (string, required)
Moves or renames a file safely. Parameters: source (string, required), destination (string, required)
Uses a search engine to find information on the web. Parameters: query (string, required)
Scrapes a specific URL and returns the content. Parameters: url (string, required), selector (string, optional)
Interactively browses a website using Playwright. Parameters: url (string, required)
Creates a new document in the knowledge base with metadata but no content. Parameters: path (string, required), metadata (object, optional)
Writes content to an existing document in the knowledge base. Parameters: path (string, required), content (string, required), force (boolean, optional)
Reads document data from the knowledge base. Parameters: path (string, required), include_content (boolean, optional), include_index (boolean, optional)
Updates metadata for a document in the knowledge base. Parameters: path (string, required), metadata (object, required)
Manages RDF triples (preferences and references) for documents. Parameters: action (string, required), triple_type (string, required), path (string, required), predicate (string, required), object (string, optional), ref_path (string, optional)
Searches the knowledge base using text queries and/or graph expansion. Parameters: query (string, optional), graph_seed_urns (array, optional), graph_expand_hops (integer, optional), filter_urns (array, optional), relation_predicates (array, optional), top_k (integer, optional), include_content (boolean, optional), include_index (boolean, optional), use_reranker (boolean, optional)
Lists documents in the knowledge base. Parameters: path (string, optional), recursive (boolean, optional)
Manages knowledge base operations like moving documents and rebuilding search indices. Parameters: action (string, required), additional parameters depend on the action
