Loading...
MCP server enabling Claude to interact with and modify project files using tools like read, write, edit, and run_command with permission handling.
Boost this tool
Subscribe to listing upgrades or segmented pushes.
MCP server enabling Claude to interact with and modify project files using tools like read, write, edit, and run_command with permission handling.
This server provides powerful file manipulation capabilities, but its safety depends heavily on proper configuration and user awareness. It is safe when used with strict directory restrictions and careful permission management. It is risky when given broad access or when executing untrusted commands.
Performance depends on the complexity of the operations and the size of the files being processed. grep leverages ripgrep for optimized search performance.
Cost is primarily related to computational resources used for command execution and file processing. Consider the size and complexity of operations when estimating costs.
readReads the content of a file, with options for line numbers, offset, and limit.
Read-only operation, no side effects.
writeCreates a new file or overwrites an existing file with provided content.
Can overwrite existing files, potentially leading to data loss.
editMakes line-based edits to a text file.
Modifies existing files, potentially introducing errors or unintended changes.
multi_editMakes multiple precise text replacements in a single file operation with atomic transactions.
Complex edits can introduce errors; atomic transactions mitigate but don't eliminate risk.
directory_treeRetrieves a recursive tree view of directories.
Read-only operation, no side effects.
grepSearches for patterns within files using ripgrep for performance.
Read-only operation, no side effects.
content_replaceReplaces patterns within the content of a file.
Modifies file content, potentially leading to data loss or corruption.
grep_astSearches code with AST context, showing matches within functions, classes, etc.
Read-only operation, no side effects.
run_commandExecutes shell commands on the server.
Allows arbitrary code execution, posing a significant security risk.
notebook_readExtracts and reads source code from all cells in a Jupyter notebook, including outputs.
Read-only operation, no side effects.
notebook_editEdits, inserts, or deletes cells in a Jupyter notebook.
Modifies notebook structure and content, potentially breaking functionality.
thinkProvides a structured space for complex reasoning and analysis without making changes.
No file system modifications or external calls.
dispatch_agentLaunches one or more agents that can perform tasks using read-only tools concurrently.
Agents are restricted to read-only tools.
batchExecutes multiple tool invocations in parallel or serially in a single request.
Aggregates the risks of the individual tools being batched.
todo_writeCreates and manages a structured task list.
Creates or modifies a task list file.
todo_readReads a structured task list.
Read-only operation, no side effects.
None
cloud
This server provides powerful file manipulation capabilities, but its safety depends heavily on proper configuration and user awareness. It is safe when used with strict directory restrictions and careful permission management. It is risky when given broad access or when executing untrusted commands.
Autonomy is highly dependent on the configured permissions and the specific tools used. Exercise caution when granting broad access.
Production Tip
Implement robust input validation and output sanitization to prevent security vulnerabilities.
Configure the server with the appropriate directory restrictions in the configuration file.
Carefully validate and sanitize all inputs to `run_command` to prevent command injection. Consider limiting the commands that can be executed.
Currently, this server does not implement authentication. It is recommended to implement network-level security measures.
This server operates on the local filesystem. To edit remote files, you would need to mount the remote filesystem locally.
Implement logging for executed commands and file modifications. Monitor system resources for performance issues.
The server will return an error message indicating the failure. The behavior of other commands in the batch depends on whether they are executed in parallel or serially.
Currently, there is no built-in dry-run mode. You can simulate a dry-run by reading the file and manually applying the changes.