haive.mcp.downloader.config¶

Configuration models for MCP Downloader.

This module defines the configuration models used throughout the MCP downloader system, including templates, server configurations, and installation methods.

Example

Creating a server template:

template = ServerTemplate(
name=”npm_official”, installation_method=InstallationMethod.NPM, command_pattern=”@modelcontextprotocol/server-{service}”, capabilities=[“tools”], category=”official”

)

Creating a server configuration:

config = ServerConfig(
name="filesystem",
template="npm_official",
source="npm",
variables={"service": "filesystem"},
tags={"official", "file-operations"}

)

Classes:: InstallationMethod: Enum of supported installation methods ServerTemplate: Template for server installation patterns ServerConfig: Configuration for a specific server DownloaderConfig: Overall downloader configuration

Classes¶

`DiscoveryConfig`	Configuration for server discovery.
`DownloaderConfig`	Overall configuration for the MCP downloader.
`InstallationMethod`	Supported installation methods for MCP servers.
`ServerConfig`	Configuration for a specific MCP server.
`ServerTemplate`	Template for MCP server installation patterns.

Functions¶

`load_config`(config_file)	Load configuration from YAML file.
`save_config`(config, config_file)	Save configuration to YAML file.

Module Contents¶

class haive.mcp.downloader.config.DiscoveryConfig(/, **data)[source]¶

Bases: pydantic.BaseModel

Configuration for server discovery.

Parameters:: data (Any)

sources¶: List of discovery source URLs

patterns¶: Package naming patterns by registry

auto_discover¶: Enable automatic discovery

discovery_interval¶: Hours between discovery runs

max_servers¶: Maximum servers to discover per source

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

class haive.mcp.downloader.config.DownloaderConfig(/, **data)[source]¶

Bases: pydantic.BaseModel

Overall configuration for the MCP downloader.

Parameters:: data (Any)

install_dir¶: Directory for server installations

config_dir¶: Directory for configuration files

log_dir¶: Directory for log files

max_concurrent¶: Maximum concurrent downloads

retry_attempts¶: Number of retry attempts

retry_delay¶: Delay between retries in seconds

health_check_enabled¶: Enable health checks after install

health_check_timeout¶: Health check timeout in seconds

backup_enabled¶: Enable configuration backups

backup_dir¶: Directory for backups

templates¶: List of server templates

servers¶: List of server configurations

discovery¶: Discovery configuration

Example

Full configuration:

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

class haive.mcp.downloader.config.InstallationMethod[source]¶

Bases: str, enum.Enum

Supported installation methods for MCP servers.

NPM¶: Node Package Manager installation

PIP¶: Python Package Index installation

GIT¶: Git repository cloning

DOCKER¶: Docker image pull

BINARY¶: Binary executable download

CURL¶: Direct HTTP download

MANUAL¶: Manual installation process

SCRIPT¶: Custom script execution

Initialize self. See help(type(self)) for accurate signature.

class haive.mcp.downloader.config.ServerConfig(/, **data)[source]¶

Bases: pydantic.BaseModel

Configuration for a specific MCP server.

Server configurations define individual servers to be installed, referencing a template and providing server-specific variables.

Parameters:: data (Any)

name¶: Server name identifier

template¶: Template name to use

source¶: Source location (npm, git URL, etc.)

variables¶: Variables to substitute in template patterns

enabled¶: Whether the server is enabled for installation

priority¶: Installation priority (lower = higher priority)

tags¶: Set of tags for categorization

env_vars¶: Additional environment variables

version¶: Specific version to install

Example

Filesystem server config:

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

model_config¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class haive.mcp.downloader.config.ServerTemplate(/, **data)[source]¶

Bases: pydantic.BaseModel

Template for MCP server installation patterns.

Templates define reusable installation patterns that can be applied to multiple servers with similar installation requirements.

Parameters:: data (Any)

name¶: Unique template identifier

installation_method¶: Method to use for installation

command_pattern¶: Pattern for the command to run the server

args_pattern¶: Default arguments for the command

env_vars¶: Environment variables to set

capabilities¶: List of server capabilities

category¶: Server category for organization

health_check¶: Command to verify server health

prerequisites¶: Required system dependencies

post_install¶: Commands to run after installation

timeout¶: Installation timeout in seconds

Example

NPM template:

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

model_config¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

haive.mcp.downloader.config.load_config(config_file)[source]¶

Load configuration from YAML file.

Parameters:

config_file (pathlib.Path) – Path to YAML configuration file

Returns:

Loaded configuration

Return type:

DownloaderConfig

Raises:

FileNotFoundError – If config file doesn’t exist
ValueError – If config file is invalid

Example

Loading config:

haive.mcp.downloader.config.save_config(config, config_file)[source]¶

Save configuration to YAML file.

Parameters:

config (DownloaderConfig) – Configuration to save
config_file (pathlib.Path) – Path to save file

Return type:

None

Example

Saving config: