Skip to main content
Glama
hmumixaM

USCardForum MCP Server

by hmumixaM

search_forum

Search USCardForum for credit card discussions using advanced query operators to filter by title, author, category, tags, or date range.

Instructions

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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query string. Supports operators: 'in:title', '@username', 'category:name', '#tag', 'after:date', 'before:date'
pageNoPage number for pagination (starts at 1)
orderNoSort order: 'relevance' (default), 'latest', 'views', 'likes', 'activity', or 'posts'

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
postsNoMatching posts
usersNoMatching users
topicsNoMatching topics
grouped_search_resultNoResult metadata

Implementation Reference

  • The core handler function for the 'search_forum' tool. Decorated with @mcp.tool() for MCP registration. Defines input schema via Annotated Fields and implements the logic by calling get_client().search().
    @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)
  • Pydantic models defining the output structure of the search_forum tool, including SearchResult and its nested models (SearchPost, SearchTopic, SearchUser, GroupedSearchResult). Includes a factory method to parse from API response.
    """Domain models for search results."""
    
    from __future__ import annotations
    
    from datetime import datetime
    from typing import Any
    
    from pydantic import BaseModel, Field
    
    
    class SearchPost(BaseModel):
        """A post in search results."""
    
        id: int = Field(..., description="Post ID")
        topic_id: int = Field(..., description="Parent topic ID")
        post_number: int = Field(..., description="Position in topic")
        username: str | None = Field(None, description="Author username")
        blurb: str | None = Field(None, description="Content excerpt with highlights")
        created_at: datetime | None = Field(None, description="When posted")
        like_count: int = Field(0, description="Number of likes")
    
        class Config:
            extra = "ignore"
    
    
    class SearchTopic(BaseModel):
        """A topic in search results."""
    
        id: int = Field(..., description="Topic ID")
        title: str = Field(..., description="Topic title")
        posts_count: int = Field(0, description="Number of posts")
        views: int = Field(0, description="View count")
        like_count: int = Field(0, description="Total likes")
        category_id: int | None = Field(None, description="Category ID")
        category_name: str | None = Field(None, description="Category name")
        created_at: datetime | None = Field(None, description="Creation time")
    
        class Config:
            extra = "ignore"
    
    
    class SearchUser(BaseModel):
        """A user in search results."""
    
        id: int = Field(..., description="User ID")
        username: str = Field(..., description="Username")
        name: str | None = Field(None, description="Display name")
        avatar_template: str | None = Field(None, description="Avatar URL")
    
        class Config:
            extra = "ignore"
    
    
    class GroupedSearchResult(BaseModel):
        """Metadata about search result counts."""
    
        post_ids: list[int] = Field(default_factory=list, description="Matching post IDs")
        topic_ids: list[int] = Field(default_factory=list, description="Matching topic IDs")
        user_ids: list[int] = Field(default_factory=list, description="Matching user IDs")
        more_posts: bool | None = Field(None, description="More posts available")
        more_topics: bool | None = Field(None, description="More topics available")
    
        class Config:
            extra = "ignore"
    
    
    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,
            )
  • The server entrypoint imports search_forum from server_tools and includes it in __all__, exposing it for the MCP server main() function.
    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,
    )
    
    __all__ = [
        "MCP_HOST",
        "MCP_PORT",
        "MCP_TRANSPORT",
        "NITAN_TOKEN",
        "SERVER_INSTRUCTIONS",
        "get_client",
        "main",
        "mcp",
        "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",
        "resource_categories",
        "resource_hot_topics",
        "resource_new_topics",
        "search_forum",
        "subscribe_topic",
        "research_topic",
    ]
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure and does so effectively. It explains that the tool returns a SearchResult object with detailed components (posts, topics, users, metadata), describes pagination behavior ('If more results exist, increment page parameter'), and outlines the default sort order ('relevance'). It does not cover aspects like rate limits or authentication needs, but provides substantial operational context.

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

Conciseness5/5

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

The description is well-structured and front-loaded, starting with a clear purpose statement, followed by organized sections for arguments, returns, examples, and pagination. Every sentence adds value, such as the detailed query examples and pagination instructions, with no redundant or unnecessary information, making it efficient and easy to parse.

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

Completeness5/5

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

Given the tool's complexity (search functionality with multiple parameters and operators), the description is complete. It fully explains the input parameters with examples, describes the output structure in detail (SearchResult object with nested components), and includes practical usage guidance. The presence of an output schema reduces the need to explain return values, but the description still adds valuable context, making it comprehensive for agent use.

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

Parameters4/5

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

The schema description coverage is 100%, so the baseline is 3, but the description adds significant value beyond the schema. It elaborates on the 'query' parameter with detailed examples of Discourse operators (e.g., 'in:title', '@username'), provides a comprehensive list of 'order' options with explanations, and includes example queries that demonstrate parameter usage in context, enhancing understanding beyond the schema's basic descriptions.

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?

The description clearly states the tool's purpose with a specific verb ('Search') and resource ('USCardForum for topics and posts'), distinguishing it from sibling tools like 'get_topic_info' or 'get_hot_topics' which retrieve specific content rather than performing searches. It explicitly identifies what is being searched (topics and posts) and how (matching a query).

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?

The description provides clear context for when to use this tool (searching with a query) and includes example queries that illustrate practical applications. However, it does not explicitly state when not to use it or name alternatives among sibling tools, such as using 'get_hot_topics' for trending content without a specific query.

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/hmumixaM/uscardforum-mcp4'

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