Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOG_LEVELNoLog level: DEBUG, INFO, WARN, or ERROR. Defaults to INFO.INFO
ALLOWED_ROOTNoSemicolon/comma separated allowed directory roots for filesystem tools (e.g. C:/Users/youse;F:/workspace). Defaults to process.cwd().process.cwd()
CONTINUITY_ROOTNoStorage directory for Continuity Memory projects. Defaults to ~/.continuity.~/.continuity

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{}
prompts
{}
resources
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
read_fileA

Read file contents. Supports line range (1-based).

write_fileC

Write content to file. Creates parent dirs.

append_fileA

Append content to file. Creates if missing.

delete_fileC

Delete a file.

copy_fileB

Copy file from source to destination.

list_directoryB

List directory contents with metadata. Supports recursive listing.

create_directoryA

Create directory (and parents).

delete_directoryA

Delete directory. Set recursive=true for non-empty.

renameC

Rename/move a file or directory.

get_file_infoA

Get file/directory metadata: size, type, timestamps, permissions.

file_existsB

Check if path exists and its type.

search_filesA

Search text pattern across files in a directory. Returns matching lines with paths and line numbers.

find_filesB

Find files/dirs by name pattern. Supports wildcards and regex.

execute_commandB

Run a shell command in an allowed directory. PowerShell on Windows, bash on Unix.

list_processesA

List running processes with PID, name, and memory.

kill_processC

Terminate a process by PID.

list_active_portsA

List TCP ports in LISTEN state.

memory_storeC

Store a key-value pair in persistent memory.

memory_retrieveC

Retrieve a value by key from persistent memory.

memory_initB

Init or load project memory. Call first in any session. Returns briefing.

memory_readB

Read project memory. Mode: briefing (default) | section | full.

memory_updateC

Update a memory section (architecture|todo|file-map|decisions) in small increments.

memory_logA

Append single timestamped event to log. Call frequently after meaningful steps.

memory_compactC

Run server-side compaction of log and sections into briefing.md.

memory_listB

List all known project IDs and metadata.

memory_statusB

Get token estimates, last compaction, and client info for a project.

take_screenshotA

Capture screen to PNG file.

mouse_moveA

Move cursor to screen coordinates.

mouse_clickA

Click mouse button at current position.

keyboard_typeA

Simulate keyboard typing on active window.

get_envA

Read environment variable(s). Omit name for all.

set_envB

Set an environment variable for this session.

get_system_infoB

Get system info: OS, CPU, RAM, disk.

read_clipboardA

Read text from system clipboard.

write_clipboardB

Write text to system clipboard.

send_notificationB

Send a native desktop notification.

http_requestA

Make HTTP request (GET/POST/PUT/DELETE/PATCH) with headers and body.

Prompts

Interactive templates invoked by user choice

NameDescription
continuity-memoryContinuity memory workflow instructions for multi-session & cross-AI continuity.

Resources

Contextual data attached and managed by the client

NameDescription
Continuity Memory SkillSkill instructions for Continuity MCP

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/YOUSEFISLAM-dev/qwen-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server