Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

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
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
phygital_brain_startA

Start a Phygital Brain job: returns that job's step-by-step instructions (a skill) as text, for you to follow. It changes nothing by itself: you then build or change the person's brain with your own file tools, in the folder they chose. Call it first when the person says 'set up my second brain', 'upgrade my second brain', 'set up my team', 'set up my brain keeper', 'translate Phygital Brain into my language', 'switch my brain to another language', or the same in another language. Calling it again returns the same instructions. To open a file the instructions name, use phygital_brain_read_file; to see which files exist, use phygital_brain_list_files. An unknown job returns an error naming the valid ones.

phygital_brain_read_fileA

Read one of Phygital Brain's own files and return its full text: a form, a template, a language file, a skill, or the suggested skills and apps people can add (start with 'suggested-skills/README.md' and 'suggested-apps/README.md'). Use it when the instructions from phygital_brain_start name a file, or when the person asks what they can add to their brain; if you don't know the exact name, list the folder with phygital_brain_list_files first. A missing file, a folder, or a path outside the skills folder returns an error that says so. It reads only Phygital Brain's files, never the person's brain, and changes nothing.

phygital_brain_list_filesA

List what's in one of Phygital Brain's folders: one name per line, sorted, with folders ending in '/'. It doesn't look inside subfolders: list a subfolder to see its files. Use it to find a file's exact name, then open the file with phygital_brain_read_file. A folder that doesn't exist returns an error. It reads only Phygital Brain's files, never the person's brain, and changes nothing.

Prompts

Interactive templates invoked by user choice

NameDescription
set-up-my-second-brainBuild a Phygital Brain in the folder you chose.
brain-keeperSet up, update or move the Brain Keeper.
add-languageMake Phygital Brain in a new language, or switch a brain's language.

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.6/5.0

Scored across 3 tools

Disambiguation5/5

The three tools have clearly distinct purposes: listing folder contents, reading a specific file, and starting a job to retrieve instructions. Their descriptions explicitly explain when to use each and how they relate, so an agent should not confuse them.

Naming Consistency5/5

All tools use the same snake_case pattern with a consistent phygital_brain_ prefix followed by an action: list_files, read_file, and start. The naming is predictable and readable throughout.

Tool Count5/5

Three tools is a well-scoped minimum for this server's purpose: browse files, read files, and retrieve job instructions. Each tool earns its place, and there are no redundant or unnecessary operations.

Completeness4/5

The tool surface covers the core lifecycle: discovering files, reading them, and starting jobs that provide instructions for building or changing the brain. A direct search or find operation is absent, but listing and reading are sufficient for the intended read-only file-access role.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues