Skip to main content
Glama
justinscott12

modrinth-mcp

modrinth_create_project

Creates a new Modrinth project as a draft. Use to set up a project page before publishing versions.

Instructions

Create a NEW Modrinth project (the initial project page). Created as a DRAFT — nothing is public until you submit it for review on the site or set requested_status. This is a write action; only call it when the user explicitly asks to create a new project. After it exists, publish jars with modrinth_create_version.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyNoLong-form markdown description for the project page.
slugYesURL slug, 3-64 chars, e.g. 'no-anvil-limit'. Becomes modrinth.com/project/<slug>.
titleYesProject display name, e.g. 'No Anvil Limit'.
wiki_urlNoWiki/docs URL.
icon_pathNoAbsolute path to an icon image (png/jpg/webp/gif/svg).
categoriesNoFeatured categories, e.g. ['utility','game-mechanics']. Must be valid Modrinth categories for the project_type.
issues_urlNoIssue tracker URL.
license_idNoSPDX license id, e.g. 'MIT', 'GPL-3.0-only', 'ARR'.
source_urlNoSource code repo URL.
client_sideNoWhether the mod is needed on the client. Editable later.
descriptionYesShort one-or-two-sentence summary shown in search.
discord_urlNoDiscord invite URL.
server_sideNoWhether the mod is needed on the server. Editable later.
project_typeNoProject type. Defaults to mod.
requested_statusNoDesired status once processed. Stays a draft until you submit for review on the site.
Behavior4/5

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

Annotations indicate readOnly=false but description adds critical context: the project is created as a DRAFT, nothing public until submission or requested_status set. This is essential behavioral disclosure beyond the schema, though it could detail whether creation is reversible or requires auth.

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

Conciseness5/5

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

Three concise sentences, front-loaded with purpose and key behavior, no fluff. Efficient use of words.

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

Completeness4/5

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

Given the tool's complexity (15 params, 4 enums) and no output schema, the description gives enough context for safe use: draft creation, explicit user request, next steps. Could note more about potential errors, but adequate.

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

Parameters4/5

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

Schema covers all 15 parameters with descriptions, but the tool description adds the key semantic of the 'requested_status' field (stays draft until review) and clarifies the draft workflow. This supplements the schema without redundancy.

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?

Description clearly states it creates a new Modrinth project, explicitly notes it's a draft, and contrasts with sibling tool modrinth_create_version ('After it exists, publish jars with...'). This distinguishes it from related tools effectively.

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?

Provides explicit guidance: 'only call it when the user explicitly asks to create a new project' and explains draft status process. Names the alternative for publishing versions, offering clear when/why.

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/justinscott12/modrinth-mcp'

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