Veezee: LinkedIn people & company data for agents

Get an account's tweets

x_get_tweets

Read-only

Fetch one page of an X account's timeline. identifier is a screen name, profile URL, or numeric id (auto-detected). mode picks the view: posts (default) is the account's own tweets, posts_and_replies includes their replies, highlights is the account's pinned highlights tab. include_retweets (default true) filters retweets out when false. Costs 4 credits per page; a cursor page is a NEW call priced the same way. Returns tweet summaries with engagement counts and a cursor for older tweets. Use this for 'what has X been posting', voice checks before outreach, or drafting replies in an account's register. For keyword search across all of X use x_search; for one specific tweet you already have, x_get_tweet.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`mode`	No	Which timeline view to read.	posts
`cursor`	No	Cursor from a previous page for older tweets.
`freshness`	No	recent (default) serves cached data from the last few hours when available; realtime forces a live fetch for +2 credits (refunded if we fall back to cached data). Trial keys are cached-only and reject realtime with TRIAL_CAP_EXCEEDED; paying upgrades this same key to unlock it.	recent
`identifier`	Yes	Screen name without the @, profile URL, or numeric account id.
`max_credits`	No	Spend ceiling for this one call. The call is rejected (nothing charged) if its quote exceeds this. Only the quote is ever reserved, never this ceiling.
`include_retweets`	No	Set false to drop retweets from the page.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`usage`	Yes
`common`	Yes
`entity`	Yes
`platform`	Yes
`freshness`	Yes
`data_as_of`	Yes
`canonical_url`	Yes
`schema_version`	Yes
`platform_fields`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedSep 10, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already indicate readOnly and openWorld hints. The description adds value beyond annotations: cost details (4 credits per page, fresh cursor costs anew), pagination (cursor for older tweets), caching/real-time freshness behavior, and trial key limitations. No contradictions with annotations.

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

Conciseness4/5

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

The description is concise but presented as a dense paragraph. While not overly verbose, it could benefit from structuring (e.g., bullet points for modes) to improve readability.

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 (6 parameters, enums, output schema), the description covers all essentials: functionality, parameter details, costs, pagination, return structure (summaries with engagements and cursor), and alternatives. Output schema exists so return value details are unnecessary.

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

Parameters5/5

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

Schema coverage is 100%, and the description adds meaningful context: identifier auto-detection, mode explanations, freshness modes with credit differences, max_credits as spend ceiling. This enriches the bare schema 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 fetches a page of an X account's timeline. It distinguishes from siblings by explicitly mentioning alternatives like x_search for keyword search and x_get_tweet for a specific tweet.

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 provides explicit usage scenarios ('what has X been posting', voice checks, drafting replies) and directs to alternatives for other needs (x_search, x_get_tweet).

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

All Veezee: LinkedIn people & company data for agents tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?