Skip to main content
Glama
rafaljanicki

X (Twitter) MCP server

by rafaljanicki

search_twitter

Query X (Twitter) to retrieve specific tweets, filter results by product, count, or cursor for precise and targeted data collection.

Instructions

Search Twitter with a query

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNo
cursorNo
productNoTop
queryYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • Registers the 'search_twitter' tool with FastMCP server using the @server.tool decorator, specifying the name and description.
    @server.tool(name="search_twitter", description="Search Twitter with a query")
  • Defines the input schema via type hints: query (str), product (Optional[str]), count (Optional[int]), cursor (Optional[str]); output as List[Dict]. Includes docstring with parameter descriptions.
    async def search_twitter(query: str, product: Optional[str] = "Top", count: Optional[int] = 100, cursor: Optional[str] = None) -> List[Dict]:
  • Executes the tool: determines sort_order from product, clamps count to 10-100, initializes Twitter client, performs search_recent_tweets, returns list of tweet dictionaries.
    """Searches Twitter for recent tweets.
    
    Args:
        query (str): The search query. Supports operators like #hashtag, from:user, etc.
        product (Optional[str]): Sorting preference. 'Top' for relevancy (default), 'Latest' for recency.
        count (Optional[int]): Number of tweets to retrieve. Default 100. Min 10, Max 100 for search_recent_tweets.
        cursor (Optional[str]): Pagination token (next_token) for fetching the next set of results.
    """
    sort_order = "relevancy" if product == "Top" else "recency"
    
    # Ensure count is within the allowed range (10-100)
    if count is None:
        effective_count = 100 # Default to 100 if not provided
    elif count < 10:
        logger.info(f"Requested count {count} is less than minimum 10. Using 10 instead.")
        effective_count = 10
    elif count > 100:
        logger.info(f"Requested count {count} is greater than maximum 100. Using 100 instead.")
        effective_count = 100
    else:
        effective_count = count
        
    client, _ = initialize_twitter_clients()
    tweets = client.search_recent_tweets(query=query, max_results=effective_count, sort_order=sort_order, next_token=cursor, tweet_fields=["id", "text", "created_at"])
    return [tweet.data for tweet in tweets.data]
Behavior2/5

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

No annotations are provided, so the description carries full burden. It mentions searching but doesn't disclose behavioral traits like rate limits, authentication needs, pagination (implied by 'cursor' parameter but not explained), or what the search returns (e.g., tweets, users). This is inadequate for a tool with multiple parameters and no annotation coverage.

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 a single, efficient sentence with zero waste. It's front-loaded and appropriately sized for a basic tool, though it under-specifies rather than being overly verbose.

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

Completeness2/5

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

Given complexity (4 parameters, 0% schema coverage, no annotations) and an output schema exists (which helps), the description is incomplete. It doesn't cover parameter meanings, usage context, or behavioral aspects, making it insufficient for effective tool selection and invocation.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate but adds no parameter information. It doesn't explain 'query' (e.g., search syntax), 'count' (max results), 'cursor' (pagination), or 'product' (e.g., 'Top' vs 'Latest'). With 4 parameters and no schema descriptions, this is a significant gap.

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

Purpose3/5

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

The description 'Search Twitter with a query' states a clear verb ('Search') and resource ('Twitter'), but it's vague about scope and doesn't distinguish from siblings like 'get_timeline' or 'get_user_mentions' which also retrieve tweets. It specifies the action but lacks detail on what kind of search (e.g., public tweets, users, trends).

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. With many sibling tools for retrieving tweets (e.g., 'get_timeline', 'get_user_mentions'), the description doesn't indicate this is for general keyword-based searches, leaving the agent to infer usage from the name alone.

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

Related 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/rafaljanicki/x-twitter-mcp-server'

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