USCardForum MCP Server

Instructions

Implementation Reference

• src/uscardforum/server_tools/search.py:12-71 (handler)

  The primary handler for the 'search_forum' tool. Uses @mcp.tool() decorator for registration. Input schema defined inline with Pydantic Field descriptions. Logic delegates search to the DiscourseClient instance.
  @mcp.tool() def search_forum( query: Annotated[ str, Field( description="Search query string. Supports operators: 'in:title', '@username', 'category:name', '#tag', 'after:date', 'before:date'" ), ], page: Annotated[ int | None, Field(default=None, description="Page number for pagination (starts at 1)"), ] = None, order: Annotated[ str | None, Field( default=None, description="Sort order: 'relevance' (default), 'latest', 'views', 'likes', 'activity', or 'posts'", ), ] = None, ) -> SearchResult: """ Search USCardForum for topics and posts matching a query. Args: query: Search query string. Supports Discourse operators: - Basic: "chase sapphire bonus" - In title only: "chase sapphire in:title" - By author: "@username chase" - In category: "category:credit-cards chase" - With tag: "#amex bonus" - Exact phrase: '"sign up bonus"' - Exclude: "chase -sapphire" - Time: "after:2024-01-01" or "before:2024-06-01" page: Page number for pagination (starts at 1) order: Sort order for results. Options: - "relevance": Best match (default) - "latest": Most recent first - "views": Most viewed - "likes": Most liked - "activity": Recent activity - "posts": Most replies Returns a SearchResult object with: - posts: List of matching SearchPost objects with excerpts - topics: List of matching SearchTopic objects - users: List of matching SearchUser objects - grouped_search_result: Metadata about result counts Example queries: - "Chase Sapphire Reserve order:latest" - Recent CSR discussions - "AMEX popup in:title" - Topics about AMEX popup in title - "data point category:credit-cards" - Data points in CC category - "@expert_user order:likes" - Most liked posts by a user Pagination: If more results exist, increment page parameter. """ return get_client().search(query, page=page, order=order)
• src/uscardforum/models/search.py:67-100 (schema)

  Pydantic model defining the structured output schema for search results, including nested models for posts, topics, users, and grouped results. Provides from_api_response factory for parsing raw API data.
  class SearchResult(BaseModel): """Complete search results.""" posts: list[SearchPost] = Field(default_factory=list, description="Matching posts") topics: list[SearchTopic] = Field( default_factory=list, description="Matching topics" ) users: list[SearchUser] = Field(default_factory=list, description="Matching users") grouped_search_result: GroupedSearchResult | None = Field( None, description="Result metadata" ) class Config: extra = "ignore" @classmethod def from_api_response(cls, data: dict[str, Any]) -> "SearchResult": """Parse from raw API response.""" posts = [SearchPost(**p) for p in data.get("posts", [])] topics = [SearchTopic(**t) for t in data.get("topics", [])] users = [SearchUser(**u) for u in data.get("users", [])] grouped = None if "grouped_search_result" in data: grouped = GroupedSearchResult(**data["grouped_search_result"]) return cls( posts=posts, topics=topics, users=users, grouped_search_result=grouped, )
• src/uscardforum/server.py:15-45 (registration)

  Imports all MCP tools including 'search_forum' from server_tools package. Importing triggers the automatic registration via decorators when the server module is loaded.
  from uscardforum.server_tools import ( analyze_user, bookmark_post, compare_cards, find_data_points, get_all_topic_posts, get_categories, get_current_session, get_hot_topics, get_new_topics, get_notifications, get_top_topics, get_topic_info, get_topic_posts, get_user_actions, get_user_badges, get_user_followers, get_user_following, get_user_reactions, get_user_replies, get_user_summary, get_user_topics, list_users_with_badge, login, research_topic, resource_categories, resource_hot_topics, resource_new_topics, search_forum, subscribe_topic, )