Keelen

Import Repository

import_project

Destructive

Connect an EXISTING GitHub repo as a Keelen project.

This is the counterpart of create_project: it is for a repo that already
exists, while create_project scaffolds 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
submit_request(project_id, ...) adds one.

`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. It is required for a MONOREPO (apps in
subdirectories), a stack with no standard root manifest (Java, Ruby, PHP,
.NET, Elixir), or a classification detection cannot infer — detection yields
"unknown" there, which BLOCKS the dev lane until
someone overrides it. A supplied value 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 names
get_billing(). Otherwise next_step names the poll of
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 already flag destructiveHint=true, idempotentHint=false and openWorldHint=true, but the description goes well beyond them: replay-guarded re-imports returning already_exists=True, in-place restoration of a soft-deleted row, restored queued work that can delete tasks, non-idempotency end to end, and loop being OFF with next_step naming get_billing(). This is unusually rich operational context for a write tool.

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 intent sentence and the create_project contrast are front-loaded, then parameters are handled in labeled blocks, so it scans well despite its length. It is dense and occasionally repetitive (visibility and detection caveats restated), which keeps it short of a 5, but each paragraph carries real decision-relevant content.

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?

With an output schema present, return values need no explaining, and the description still covers the two outcome branches that matter (already_exists on replay, loop OFF with get_billing() routing, else get_provisioning_status). For a destructive, non-idempotent, open-world import with 6 params, nothing an agent needs to call it correctly 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%, so the description carries the full burden and does: repo_full_name format 'owner/repo' plus visibility rule, engine's enum values and default, project_kind's enum values with auto-detect/override semantics and the cases that block the dev lane, stack's language axis, and the conditional requirement on preview_command. Nothing material about the six parameters is left undocumented.

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 and resource ('Connect an EXISTING GitHub repo as a Keelen project') and immediately disambiguates against the sibling create_project, stating this is for pre-existing repos while create_project scaffolds new ones. An agent can select it correctly without touching the schema.

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?

Gives explicit when-to-use vs create_project, tells the agent to call list_github_repos() to verify visibility (and that non-visible repos 404), and names submit_request as the follow-up when no build_description is supplied. It also states the conditions that make project_kind and preview_command mandatory, which is exactly the routing guidance an agent needs.

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.