mcp.tools.server_selector¶

Intelligent MCP server selection and filtering tools for AI agents.

This module provides sophisticated tools for filtering, selecting, and recommending MCP servers based on various criteria including prefixes, capabilities, task analysis, and performance metrics. Designed to help AI agents make intelligent decisions about which servers to use for specific tasks.

The server selector provides:

  • Namespace/prefix-based filtering for organized server groups

  • Capability-based server recommendations

  • Task analysis for automatic server selection

  • Performance-aware server ranking

  • Interactive selection interfaces

  • Smart server combinations and workflows

Classes:

MCPServerSelector: Main class for intelligent server selection ServerFilter: Flexible filtering system for servers TaskAnalyzer: Analyzes tasks to recommend appropriate servers ServerRecommender: Provides smart server recommendations

Example

Basic server selection:

from haive.mcp.tools import MCPServerSelector
from haive.mcp.documentation import MCPDocumentationLoader

# Create selector with all available servers
loader = MCPDocumentationLoader()
all_servers = loader.load_all_mcp_documents()

selector = MCPServerSelector(all_servers)

# Filter by prefix (organization/namespace)
anthropic_servers = selector.filter_by_prefix("anthropic/")
openai_servers = selector.filter_by_prefix("openai/")

# Get recommendations for a task
task = "I need to analyze a GitHub repository for security issues"
recommendations = selector.recommend_for_task(task)

# Interactive selection
chosen_servers = await selector.interactive_select(
    "Choose servers for code analysis",
    categories=["development", "security"]
)

Note

This system is designed to make server selection intelligent and context-aware, reducing the need for manual server configuration.

Attributes¶

logger

Classes¶

MCPServerSelector

Intelligent MCP server selection and recommendation system.

ServerFilter

Flexible filtering system for MCP servers.

ServerScore

Score and metadata for a server recommendation.

TaskAnalyzer

Analyzes task descriptions to determine server requirements.

TaskRequirements

Analyzed requirements from a task description.

Module Contents¶

class mcp.tools.server_selector.MCPServerSelector(servers: list[dict[str, Any]] | None = None)¶

Intelligent MCP server selection and recommendation system.

create_config_for_selection(selected_servers: list[str], lazy_init: bool = True) → haive.mcp.config.MCPConfig¶

Create MCPConfig for selected servers.

Parameters:

  • selected_servers – List of server names to include

  • lazy_init – Whether to use lazy initialization

Returns:

MCPConfig with selected servers

filter_by_prefix(prefix: str) → list[dict[str, Any]]¶

Filter servers by prefix/namespace.

Parameters:

prefix – Prefix to filter by (e.g., “modelcontextprotocol/”)

Returns:

List of servers with matching prefix

get_available_categories() → list[str]¶

Get all available server categories.

Returns:

List of unique categories

get_available_prefixes() → list[str]¶

Get all available server prefixes/namespaces.

Returns:

List of unique prefixes found in server names

get_selection_summary(selected_servers: list[str]) → dict[str, Any]¶

Get summary of selected servers.

Parameters:

selected_servers – List of selected server names

Returns:

Summary dictionary with statistics and details

async interactive_select(prompt: str = 'Select MCP servers to use:', categories: list[str] | None = None, prefixes: list[str] | None = None, max_selections: int | None = None) → list[str]¶

Interactive server selection interface.

Parameters:

  • prompt – Prompt to display to user

  • categories – Filter by categories

  • prefixes – Filter by prefixes

  • max_selections – Maximum number of selections allowed

Returns:

List of selected server names

recommend_for_task(task_description: str, max_servers: int = 5, include_experimental: bool = False) → list[ServerScore]¶

Recommend servers for a specific task.

Parameters:

  • task_description – Natural language description of the task

  • max_servers – Maximum number of servers to recommend

  • include_experimental – Whether to include experimental servers

Returns:

List of ServerScore objects ranked by relevance

analyzer¶
filter¶
server_map¶
servers = None¶
class mcp.tools.server_selector.ServerFilter(servers: list[dict[str, Any]])¶

Flexible filtering system for MCP servers.

filter_by_capability_keyword(keyword: str) → list[dict[str, Any]]¶

Filter servers by capability keyword in description.

Parameters:

keyword – Keyword to search for

Returns:

List of servers mentioning the keyword

filter_by_category(category: str) → list[dict[str, Any]]¶

Filter servers by category.

Parameters:

category – Category to filter by

Returns:

List of servers in the category

filter_by_multiple_criteria(prefixes: list[str] | None = None, categories: list[str] | None = None, keywords: list[str] | None = None, exclude_prefixes: list[str] | None = None) → list[dict[str, Any]]¶

Filter servers by multiple criteria.

Parameters:

  • prefixes – List of prefixes to include

  • categories – List of categories to include

  • keywords – List of capability keywords

  • exclude_prefixes – List of prefixes to exclude

Returns:

List of servers matching all criteria

filter_by_prefix(prefix: str) → list[dict[str, Any]]¶

Filter servers by name prefix (namespace).

Parameters:

prefix – Prefix to filter by (e.g., “anthropic/”, “openai/”)

Returns:

List of servers matching the prefix

servers¶
class mcp.tools.server_selector.ServerScore¶

Score and metadata for a server recommendation.

capabilities_match: list[str]¶
category_match: bool¶
prefix_match: bool¶
reasons: list[str]¶
score: float¶
server_name: str¶
class mcp.tools.server_selector.TaskAnalyzer¶

Analyzes task descriptions to determine server requirements.

analyze_task(task_description: str) → TaskRequirements¶

Analyze a task description to determine requirements.

Parameters:

task_description – Natural language task description

Returns:

TaskRequirements with analyzed needs

capability_patterns¶
server_patterns¶
class mcp.tools.server_selector.TaskRequirements¶

Analyzed requirements from a task description.

complexity_score: float¶
keywords: list[str]¶
preferred_categories: list[str]¶
required_capabilities: list[str]¶
suggested_servers: list[str]¶
mcp.tools.server_selector.logger¶