Skip to main content
Glama
revelri

lutris-source-mcp

by revelri

stop_seeding

Provide a torrent infohash to stop seeding, optionally confirm, and keep the downloaded files intact.

Instructions

Stop seeding without deleting on-disk files. mutates: true

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
infohashYes
confirmNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The 'stop_seeding' MCP tool handler. Loads config, creates a Qbittorrent client, calls qb.delete(infohash, delete_files=False) to stop seeding without removing on-disk files, and returns a confirmation dict.
    @mcp.tool(description="Stop seeding without deleting on-disk files. mutates: true")
    @confirm_required("stop_seeding")
    def stop_seeding(infohash: str, confirm: bool = False) -> dict[str, Any]:
        cfg = _cfg.load()
        qb = Qbittorrent(cfg.qbittorrent)
        qb.delete(infohash, delete_files=False)
        return {"ok": True, "infohash": infohash, "kept_files": True}
  • The schema is implicitly defined by the function signature of stop_seeding: accepts 'infohash' (str) and 'confirm' (bool, default False). The return type is dict[str, Any]. The @mcp.tool decorator registers this via FastMCP.
    @mcp.tool(description="Stop seeding without deleting on-disk files. mutates: true")
    @confirm_required("stop_seeding")
    def stop_seeding(infohash: str, confirm: bool = False) -> dict[str, Any]:
        cfg = _cfg.load()
        qb = Qbittorrent(cfg.qbittorrent)
        qb.delete(infohash, delete_files=False)
        return {"ok": True, "infohash": infohash, "kept_files": True}
  • The FastMCP server instance 'mcp' is created here. The tool registers itself via the @mcp.tool decorator when the module is imported through _register() → from lutris_source_mcp.tools import install_pipeline.
    mcp = FastMCP(
        name="lutris-source-mcp",
        instructions=(
            "Source pipeline for lutris-mcp. prepare_install_source(query) "
            "searches Prowlarr, hands off to qBittorrent, polls every 5s with "
            "a stdout heartbeat, abandons after stall_timeout_seconds of zero "
            "progress, classifies the resulting tree, and returns a path "
            "lutris-mcp consumes via install_from_yaml or install_from_directory."
        ),
    )
    
    
    def _register() -> None:
        # Side-effect imports register tools.
        from lutris_source_mcp.tools import diagnostics, install_pipeline  # noqa: F401
    
    
    _register()
  • The confirm_required decorator wraps destructive tools. For stop_seeding, if confirm=False (default), it returns a Preview object instead of executing. When confirm=True, the actual handler runs.
    def confirm_required(action: str) -> Callable[[F], F]:
        def decorator(fn: F) -> F:
            @wraps(fn)
            def wrapper(*args: Any, **kwargs: Any) -> Any:
                if not kwargs.get("confirm", False):
                    target = (
                        kwargs.get("query")
                        or kwargs.get("infohash")
                        or kwargs.get("target")
                        or "<unknown>"
                    )
                    return Preview(action=action, target=str(target),
                                   would_do=f"{action} on {target}")
                return fn(*args, **kwargs)
            return wrapper  # type: ignore[return-value]
        return decorator
Behavior3/5

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

Description includes 'mutates: true' and clarifies that files are not deleted, which adds some behavioral insight beyond the action name. However, it lacks details on side effects, state changes, or permissions required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise (one sentence plus a note), but the brevity sacrifices necessary information, especially given the lack of schema descriptions.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, 0% schema coverage, and no explanation of the output schema or parameters, the description is severely incomplete for a tool requiring input parameters and producing output.

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

Parameters1/5

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

Schema description coverage is 0%, and the description fails to explain the two parameters (infohash and confirm). No additional meaning is provided beyond the schema structure.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action 'Stop seeding' and distinguishes it from deletion by noting 'without deleting on-disk files'. The resource (seeding) is implied, and the sibling tools are unrelated, making the purpose stand out.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, nor any prerequisites or context. The sibling list doesn't include similar tools, so no comparison can be drawn.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/revelri/lutris-source-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server