// MCP TOOL REFERENCE

MEGA TOOLS

20 tools from the Mega MCP Server, categorised by risk level.

View the Mega policy → Token cost: 1,286 tokens →

// ALL 20 MEGA TOOLS

READ 14 tools

Read mega_cat Display contents of a remote file Read mega_cd Change current working directory in MEGA cloud Read mega_cp Copy files/folders within MEGA cloud storage Read mega_df Show MEGA cloud storage space usage Read mega_du Show disk usage of remote path Read mega_find Search for files/folders in MEGA cloud storage Read mega_get Download files from MEGA cloud to local filesystem Read mega_ls List files and folders in MEGA cloud storage Read mega_mv Move or rename files/folders in MEGA cloud storage Read mega_pwd Print current working directory in MEGA cloud Read mega_share Share a folder with another MEGA user Read mega_transfers Show current transfers (uploads/downloads) Read mega_tree Show directory tree structure Read mega_whoami Get current logged-in MEGA account information

WRITE 5 tools

Write mega_export Create a public link for a file/folder Write mega_import Import a public MEGA link to your account Write mega_mkdir Create a directory in MEGA cloud storage Write mega_put Upload files from local filesystem to MEGA cloud Write mega_sync Set up sync between local and remote folders

DESTRUCTIVE 1 tools

Destructive mega_rm Remove files or folders from MEGA cloud storage

// RUNNING THIS SERVER

The managed route: connect Mega through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y mega-mcp-server

// FAQ

How many tools does the Mega MCP server have? +

The Mega MCP server exposes 20 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Mega tools? +

Route the Mega server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Mega tools fall into? +

Mega tools are categorised as Read (14), Write (5), Destructive (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.