lavela

Create a project from a repo

lavela.launch_saas

Create a project from a name and the app's GitHub repo, and decide how it deploys — nothing is deployed or charged. Its deploy field and next_step name the deploy for THIS account (deploy.blockedBy = fix that first) — follow next_step. Not idempotent: a retry creates a second project — check lavela.list_projects first. Details: https://console.lavela.dev/docs/mcp#deploy-from-repo

Input Schema

TableJSON Schema

Name	Required	Description	Default
`name`	Yes
`source`	Yes
`business`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 7, 2026
- addedInput schema / properties / business / properties / name / description
```
Added value: +"Default: name."
```
- removedInput schema / properties / business / required
```
Removed value: -[
-  "name"
-]
```
- changedInput schema / required
```
Previous value: -[
-  "name",
-  "business",
-  "source"
-]New value: +[
+  "name",
+  "source"
+]
```
First observedOct 7, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnly=false and idempotent=false, and the description adds the consequences the annotation can't: a retry creates a second project, and despite creating a project nothing is deployed or charged. The deploy/next_step/blockedBy gating is genuinely new behavioral context absent from the 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?

Purpose is front-loaded in the first clause, followed by behavioral caveats, the non-idempotency warning, and a docs link. Dense but each clause carries information; slightly heavy use of arrows/backticks adds friction without padding the length.

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?

No output schema exists, and the description compensates by naming the response's guidance fields (deploy, next_step, deploy.blockedBy) so the agent knows what to do with the result. The main gap is the unaddressed business sub-object, which an agent cannot infer from the bare schema.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate, and it only covers name and the GitHub repo (source.githubUrl) in prose. The entire business object (name, country, industry, description — including constraints like the 2-char country) is never mentioned, leaving a third of the parameter surface undocumented in both places.

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?

States a concrete verb+resource ("Create a project") plus its two key inputs (name, GitHub repo) and immediately bounds the action: "nothing is deployed or charged." That negation separates it from the provisioning siblings (provision_compute_from_repo, provision_hosting) without the agent needing to open either schema.

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?

Gives real sequencing guidance: check lavela.list_projects before retrying because the call is non-idempotent, and follow the returned next_step, fixing deploy.blockedBy first. It stops short of naming alternate siblings (e.g. when to prefer provision_compute_from_repo instead), so it is clear context rather than full when/when-not routing.

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

All lavela tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?