Skip to main content
Glama

install_project

Clones a GitHub or GitLab repository into a Docker sandbox, builds it, and generates one MCP tool per discovered executable command so the project's CLI becomes callable.

Instructions

Clone a GitHub/GitLab repository into a fresh Docker sandbox, build it, discover its executables and generate one MCP tool per command and subcommand (named "__"). Building runs the project's own install scripts inside the sandbox with network access; afterwards the sandbox is offline unless network is true. Can take minutes; if it outlives wait_seconds, poll project_info.

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": {
      "repo": "<repo>"
    },
    "name": "install_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNoBranch, tag or commit to install (default: default branch).
repoYesRepository: "owner/name" (GitHub), "github:owner/name", "gitlab:group/name", or an https URL.
imageNoOverride the Docker image used for the sandbox.
networkNoKeep outbound network enabled after install (default false).
ecosystemNoOverride the detected build system.
reinstallNoDiscard an existing sandbox for this repository and rebuild.
submodulesNoAlso clone git submodules (default false).
wait_secondsNoHow long this call waits for the build (default 600).
timeout_secondsNoBuild time limit (default 900).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare openWorldHint=true, so the description carries most of the burden and does a lot: it discloses that the project's own install scripts run with network access, that the sandbox goes offline afterwards unless network is true, and that calls can take minutes. It stops short of describing failure behavior, auth requirements for private repos, or what the immediate response contains.

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 core action is front-loaded in the first sentence, followed by the side effects and long-running caveat. It is dense but nearly every clause carries information; the parenthetical tool-naming detail is slightly awkward mid-sentence but still earns its place.

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?

For a complex, long-running, side-effectful tool with no output schema, the description covers the essential model: sandbox creation, build with network, post-build network state, and async polling. The main gap is that it never says what install_project itself returns (status, generated tool list), which matters given there is no output schema.

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

Parameters3/5

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

Schema description coverage is 100%, so all nine parameters are already documented, establishing a baseline of 3. The description adds behavioral meaning for wait_seconds (poll project_info if exceeded) and network (offline after install unless true), but the remaining parameters such as ref, image, ecosystem, and reinstall add nothing 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?

States a chain of specific verbs and resources: clone a repo into a Docker sandbox, build it, discover executables, and generate one MCP tool per command/subcommand. It even names the generated tool naming pattern, so an agent can distinguish this from siblings like sandbox_exec or project_info at a glance.

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 clear context for use and explicitly routes the agent to project_info for polling when the build outlives wait_seconds. It does not state when NOT to use it (e.g., an existing sandbox for the repo needs reinstall=true rather than a fresh install), so it falls short of full exclusion guidance.

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