Skip to main content
Glama
openl-tablets

OpenL MCP Server

Official

Create or Clone Project

openl_create_project

Creates a new OpenL project in a design repository, either as a blank project or by cloning an existing project's full structure including rules, tests, and settings.

Instructions

Create a new OpenL project in a design repository and commit it. Two modes, selected by the template argument: • CREATE (omit template): create a BLANK project from the default empty skeleton. Committed atomically on the repository's default branch; returns the commit revision. • CLONE (pass template = an existing project name): copy the source project's FULL structure (rules, tests, settings, request/response examples) into the new project and rename it — the project name in rules.xml is updated to projectName, matching OpenL Studio's Copy Project. The clone is committed atomically through the create-from-zip endpoint, so it is indexed and appears in openl_list_projects immediately. Call openl_list_repositories() / openl_list_projects() first. Returns the new project name and commit revision (hash). A name collision is rejected with 409; a missing clone source returns 404; missing permission returns 403. Note: branch is honored for clones but that path writes directly to Git via the files API (one commit per file, not atomic), so a BRANCH clone may not appear in openl_list_projects until OpenL re-indexes the repository — omit branch for the default, immediately-visible clone. Local repositories are not supported.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
branchNoTarget branch (the ticket's `defaultBranch`). Honored when CLONING (the source is read from and the clone written to this branch). For a BLANK project, omit this — blank projects are created on the repository's default branch (the create endpoint cannot target a branch); passing branch without template is rejected.
commentNoCommit comment for audit. Applied when creating a BLANK project; clone commit messages are system-generated. Defaults to 'Project <name> is created.' when omitted.
templateNoHow to create the project (the ticket's `template`). OMIT to create a BLANK project from the default empty skeleton. To CLONE an existing project, pass its name (from openl_list_projects()): its full structure is copied (rules, tests, settings, request/response examples) and the project is renamed to projectName. The clone source must be in the same repository.
repositoryYesRepository identifier. Pass either the 'id' or the 'name' field from openl_list_repositories() — the tool accepts both (and is case-insensitive). DO NOT invent values like 'Design Repository' or 'design-repo'; the actual names are typically short tokens (e.g. 'Design'). Always call openl_list_repositories() first if you don't already have the value in context.
projectNameYesName for the new project (the ticket's `project`). Becomes the project folder name and — when cloning — the renamed project name written into rules.xml. Must be unique in the repository; a collision is rejected with 409. Allowed characters: letters, digits, space, '_' and '-'.
response_formatNoResponse format: 'json' for structured data, 'markdown' for human-readable (default), 'markdown_concise' for brief summary (1-2 paragraphs), 'markdown_detailed' for full details with contextmarkdown
Behavior5/5

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

The description fully explains behavioral details beyond annotations: the two creation modes, atomic commits, indexing after clone, and that branch clones may not appear immediately in listing. It also notes that blank projects are created on the default branch. No contradictions with annotations.

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?

The description is well-structured with sections for each mode and bullet points, making it scannable. Though relatively long, every sentence adds value. Slight improvement could be more concise phrasing, but it effectively communicates complex behavior.

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?

The description covers return values (new project name and commit revision), error codes (409, 404, 403), prerequisites (calling list functions), and behavioral nuances (branch indexing delay). For a tool with no output schema, it provides complete context for an AI agent to use correctly.

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?

With 100% schema coverage, baseline is 3, but the description adds extensive meaning: it clarifies the template parameter's dual role (omit for blank, pass name for clone), warns against inventing repository values, explains when branch is honored, and details the commit comment default and when it applies. This goes well beyond the schema.

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 the tool creates or clones an OpenL project, distinguishing two modes (CREATE and CLONE) with specific behaviors. It identifies the resource (design repository project) and the action (committed creation), making it distinct from siblings like openl_close_project or openl_deploy_project.

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

Usage Guidelines4/5

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

The description advises calling openl_list_repositories() or openl_list_projects() first and explains when to omit or include the template argument. It warns about errors (409, 404, 403) and branch behavior for clones. However, it does not explicitly compare with alternative tools for similar tasks, missing some guidance on when not to use this tool.

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/openl-tablets/openl-mcp'

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