Skip to main content
Glama

setup_project

Initialize a new project by creating a directory and optionally cloning a git knowledge repo to start capturing structured knowledge.

Instructions

Register and initialise a new project in Flaiwheel.

    Side effects: creates a project directory under MCP_DOCS_PATH, optionally
    clones the git knowledge repo, runs an initial index, and binds this
    session to the new project. Idempotent — safe to call again if the
    project already exists (just rebinds the session).

    Call once per project. Use set_project() to switch between already
    registered projects. Use list_projects() to see what exists.

    Args:
        name: Short project identifier, no spaces (e.g. "my-app")
        git_repo_url: HTTPS URL of the knowledge git repo (optional,
                      can be added later via the Web UI)
        git_branch: Branch to track for git sync (default: "main")
        display_name: Human-readable label shown in the Web UI (optional)
        git_auto_push: Auto-commit and push write_*() docs to git (default: True)
        git_sync_interval: Background git pull interval in seconds (default: 300)

    Returns:
        Project name, chunk count, active-project confirmation, and next steps.
    

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYes
git_branchNomain
display_nameNo
git_repo_urlNo
git_auto_pushNo
git_sync_intervalNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It lists side effects: creates directory, optionally clones git, runs index, binds session. Notes idempotent. Missing details like synchronous vs async index, but sufficient for transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured: summary, side-effects, usage guidance, Args, Returns. Front-loaded with key info. Returns section slightly vague ('Project name, chunk count...') but overall concise and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given complexity (6 params, mutation with side effects, output schema exists), the description covers all essential aspects: behavior, all parameters, returns, and distinguishes from siblings. No gaps identified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 0% description coverage, so description must compensate. It provides full Args section explaining each parameter: name (short identifier, no spaces), git_repo_url (HTTPS, optional), git_branch (default main), display_name (optional label), git_auto_push (default true), git_sync_interval (default 300s). Adds significant meaning beyond schema titles.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Register and initialise a new project in Flaiwheel.' It specifies the verb (register/initialize), resource (project), and scope (new project). It distinguishes from siblings like set_project (switch) and list_projects (list).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit guidance: 'Call once per project. Use set_project() to switch between already registered projects. Use list_projects() to see what exists.' Also notes idempotency, so safe to call again if exists.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

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/dl4rce/flaiwheel'

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