Skip to main content
Glama

Import public repository

ingestPublicRepository
Destructive

Import a public GitHub repository into Tofu as an app’s code, from this chat and with no GitHub connection: what the dashboard’s Import public repository does under Import from GitHub. Tofu reads one commit from github.com with no credential and keeps exactly that commit: a later push changes nothing here. It deploys nothing. Every call is one upload against the day’s allowance and, without projectId, makes another app, named name or after the repository. projectId replaces all the code of an app this account owns with that commit’s — its address, settings and earlier versions stay, but a file not in the commit is not in the new version, and an app whose automatic updates follow a repository pauses them at its next push. A private or missing repository and a #branch that does not exist all get one refusal, which says nothing about which private repositories exist. unpackedArchive, when present, names the app folder’s only file: a ZIP whose files Tofu stored instead.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "ingestPublicRepository"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe repository: `owner/repo` or its github.com address, with an optional `#branch` (a branch, a tag or a commit).
nameNo
projectIdNo
rootDirectoryNoThe app’s own folder inside the repository, such as `apps/web`; left out, the whole repository is the app.

Output Schema

NameRequiredDescriptionDefault
refYes
commitShaYes
projectIdYes
repositoryYes
rootDirectoryYes
unpackedArchiveNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations: pins the immutability guarantee ('Tofu reads one commit ... a later push changes nothing here'), discloses a daily upload allowance tied to each call, and explains that failures are deliberately undifferentiated. It also details the destructive consequence of `projectId` (address/settings/version history kept, files absent from the commit removed, automatic update tracking paused), which is exactly the context destructiveHint=true alone cannot convey.

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 and nearly every sentence carries distinct information (immutability, allowance, error opacity, projectId side effects). Density works against it in places — long em-dash-chained sentences and a closing sentence about `unpackedArchive` that is difficult to parse and refers to a field not in the input schema.

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?

With an output schema present, return values need not be explained, and the description covers the remaining decision-relevant ground: no auth needed, one-commit snapshot, no deployment, quota consumption, and projectId side effects. Minor gaps remain — the actual size of the 'day's allowance' is unquantified, and the `unpackedArchive` sentence is ambiguous enough to confuse rather than inform.

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 coverage is only 50% — `name` and `projectId` have no schema description — and the prose compensates fully: `name` defaults to the repository name, and `projectId` switches the call from creating a new app to replacing an existing app's code wholesale. The `#branch` syntax for `url` and the create-vs-replace branch on `projectId` are the two decisions an agent must get right, and both are spelled out.

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?

Names a specific verb and resource ('Import a public GitHub repository into Tofu as an app's code') and disambiguates from the dashboard path and from connected-repo imports ('with no GitHub connection'). It even states a negative scope ('It deploys nothing'), so an agent knows precisely what operation it is invoking.

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?

Clearly scopes usage to public repositories obtainable without a GitHub connection, and implicitly routes connected/private-repo flows elsewhere ('a private or missing repository ... all get one refusal'). It does not name an alternative tool (e.g. a connected-repo or file-ingest sibling) for those excluded cases, so the exclusion is stated without an explicit destination.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources