twitter-x-aio

Search

get_search_searchTerm

With the search endpoint you can search all of twitter. You just need to provide a search term. ⚠ If you have a large cursor the GET-request will limit at some length. For that you can use a POST-request which has no limits. Billing per call: 1 Credits.

Input Schema

TableJSON Schema

Name	Required	Description
`count`	No	The default count is 20. You can specify a custom one here.
`cursor`	No	At the end of the entries array you'll find two objects with the type TimelineTimelineCursor. There is one cursor to go up (Top) and one for going down (bottom) the list.
`filters`	No	Learn more about all filters by reading the docs or contact me on telegram @benagain :)
`category`	No	ENUM Top,Latest,People,Photos,Videos
`searchTerm`	Yes
`includeTimestamp`	No	Decide if you need a unix created_at timestamp. This will slightly increase the speed of the request.

TDQS

A4.3/5.0

Behavior4/5

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

Without annotations, the description carries the full burden. It discloses a behavioral trait (GET cursor limit) and cost per call (1 Credit), which is useful. However, it does not explicitly state that the operation is read-only or provide details about authentication, but 'search' implies a safe read operation.

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 three sentences, front-loaded with the purpose, and includes a warning and billing info. Every sentence adds value with no fluff, and it is visually structured with an emoji for attention.

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

Completeness3/5

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

Given no output schema and no annotations, the description is adequate but incomplete. It covers the main functionality and the GET/POST distinction but does not describe the response format, potential errors, or details about filters/category beyond what the schema already states.

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

Parameters3/5

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

Schema description coverage is 83%, so parameters are well-documented. The description only adds that a search term is needed, which mirrors the required field. No additional meaning is provided beyond the schema, so the baseline of 3 is appropriate.

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 searches all of Twitter with a search term. It distinguishes the GET search from the POST search by mentioning the GET request's cursor limit, which differentiates it from the post_search_searchTerm sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit guidance on when to use POST instead of GET: when there is a large cursor, the GET request will limit, and POST has no limits. This directly addresses the main alternative and provides a clear usage condition.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All twitter-x-aio tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

C2.5/5.0

Disambiguation3/5

Most tools target distinct data types, but there is notable overlap: get_search_searchTerm vs post_search_searchTerm and get_tweet_tweetId vs post_tweet_tweetId are functional duplicates, and the three followings variants (get_user_userId_followings, _basic, _ids) have unclear boundaries. This creates ambiguity for an agent trying to select the right tool.

Naming Consistency2/5

Tool names mix HTTP method prefixes (get_, post_) with resource_parameter structures, and camelCase is embedded in parameters (searchTerm, tweetId, tweetsAndReplies). The pattern is not uniform (e.g., get_user_by_username_username vs get_user_usernames_to_ids), making the naming feel ad hoc and hard to predict.

Tool Count3/5

With 23 tools, the set is on the heavier side. Many tools are redundant (GET/POST duplicates) or overly granular (three followings endpoints), padding the count without adding distinct capabilities. A leaner set of 15-18 tools would be more appropriate for the read-only Twitter data scope.

Completeness4/5

The server covers the core read-only Twitter data surface well: user info, tweets, media, followers/followings, likes, search, trends, and miscellaneous utilities. The only notable gap is the lack of a direct endpoint for listing a user's followers' details (though that could be composed), and no ability to post or interact, which aligns with the apparent purpose.

Resources

Need Help?