Keelen

import_project

Destructive

Connect an EXISTING GitHub repo as a Keelen project.

This is the counterpart of create_project: use THIS tool when the user
already has a repo, and create_project only to scaffold a brand-new one.

`repo_full_name` is "owner/repo" — it MUST be visible to the workspace's
GitHub connection (list_github_repos() to browse; a non-visible repo 404s).
`engine` is OPTIONAL — one of claude_code | codex | glm | kimi | grok
(defaults to claude_code); codex/glm/kimi/grok require a matching connected
credential.
`build_description` is OPTIONAL but STRONGLY recommended — a plain-language
"what should Keelen build first?" submitted as the project's first Request so
the loop has work; an imported project with no Request sits idle until you
call submit_request(project_id, ...).

`project_kind` is OPTIONAL — one of library | node_library | python_library |
service | cli | web_app | godot_game | roblox_game | unknown. Omit it and the
kind is auto-detected. PASS IT when the repo is a MONOREPO (apps in
subdirectories), a stack with no standard root manifest (Java, Ruby, PHP,
.NET, Elixir), or when you want a classification detection cannot infer —
in those cases detection yields "unknown", which BLOCKS the dev lane until
someone overrides it. A value you pass is authoritative and is never
overwritten by later auto-detection. `stack` is the OPTIONAL language axis
(python | node | rust | go | cpp) for a language-agnostic kind.
`preview_command` is REQUIRED when project_kind is "web_app" (the command
that serves the app locally, e.g. "npm run dev") and optional otherwise,
where it overrides the detected one.

Re-importing the same live repo is replay-guarded (returns the existing
project with already_exists=True), and re-importing a SOFT-DELETED repo
RESTORES that deleted row in place — it does not create a fresh project.
Restored queued work can include refinement that deletes tasks, and the call
is not idempotent end to end. On a plan with no scheduled-project allowance
the project is still created but with the loop OFF — next_step then steers to
get_billing(). Otherwise follow next_step and poll
get_provisioning_status(project_id).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`stack`	No
`engine`	No
`project_kind`	No
`repo_full_name`	Yes
`preview_command`	No
`build_description`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedAug 19, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations provide only the basic safety hints (destructive=true, not idempotent, open world), and the description substantially extends them: replay-guard returning already_exists=True, soft-deleted repos being RESTORED in place rather than recreated, restored queued work that 'can include refinement that deletes tasks,' and the no-scheduled-project-allowance branch that creates the project with the loop OFF. It also surfaces the 404 error condition for non-visible repos and the credential requirement for non-default engines. No contradiction — destructiveHint=true is consistent with the disclosed task-deletion behavior.

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 sentence and every sentence earns its place — parameter semantics, the create_project contrast, and the non-idempotency warning are all load-bearing for correct invocation. However, the content is a dense prose block without labeled sections or bullets; given the 6 parameters and several conditional branches, scannability would be improved by formatting, so it falls just short of a 5.

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?

For a complex, destructive-capable import tool with 6 parameters, no schema descriptions, and a rich interaction surface, the description is essentially complete: full parameter semantics, error behavior (404), replay-guard and soft-delete restore edge cases, billing-plan branch, and the next_step/get_provisioning_status follow-up protocol. Nothing an agent needs to invoke it correctly or handle its outcomes is missing.

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 description coverage is 0% — the schema exposes bare titles and defaults only — so the description carries the entire burden and fully compensates. Every one of the 6 parameters gets meaning: repo_full_name's 'owner/repo' format plus visibility requirement, engine's full enum with default and credential constraint, project_kind's full enum with the auto-detection fallback caveat, build_description's role as the first Request, stack's language-axis semantics, and preview_command's conditional requirement for web_app. The enum values are enumerated inline even though the schema has no enums declared.

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?

Opens with a specific verb+resource — 'Connect an EXISTING GitHub repo as a Keelen project' — and immediately distinguishes itself from the sibling create_project: 'use THIS tool when the user already has a repo, and create_project only to scaffold a brand-new one.' The scope (existing repo, not scaffolding) is unambiguous and no other sibling could be confused with it.

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?

Explicitly names create_project as the alternative and states which condition selects each tool. It also gives conditional usage rules: when to pass project_kind (monorepos, non-standard root manifests) versus omit it (auto-detection), when preview_command is mandatory (web_app), and when build_description is strongly recommended. Follow-up routing to submit_request, get_billing, and get_provisioning_status is spelled out.

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

All Keelen 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.