The X (Twitter) API built for AI

Paste one docs URL into any LLM and ship your X integration in a single prompt. Built for AI coding assistants and for autonomous agents that need live X data.

api.sorsa.io/v3/static/sorsa_api_v3_documentation_en.txt
Works with Claude, GPT, Gemini, Grok, Cursor, and any AI.

AI coding assistants

Ship it from the tools you already code in

Paste the prompt, paste the docs URL, get working code. Here is the exact prompt for each tool.

Claude Code

Full project integration from the terminal.

Build a Python script that pulls every tweet from @naval and saves them to CSV. Use the Sorsa API, docs: https://api.sorsa.io/v3/static/sorsa_api_v3_documentation_en.txt

OpenAI Codex

Generate functions and modules.

Write a function that takes a list of usernames and returns their follower counts with the Sorsa API. Docs: https://api.sorsa.io/v3/static/sorsa_api_v3_documentation_en.txt

Cursor

Add an API client inside your editor.

Add a Sorsa API client to this project that searches tweets by keyword and handles pagination. Docs: https://api.sorsa.io/v3/static/sorsa_api_v3_documentation_en.txt

GitHub Copilot

Inline completions.

# Sorsa API docs: https://api.sorsa.io/v3/static/sorsa_api_v3_documentation_en.txt
# search tweets for "AI agents" with over 100 likes, latest first

Gemini CLI

Quick data pulls from the shell.

Use the Sorsa API to fetch the latest 100 mentions of @openai with over 50 likes. Docs: https://api.sorsa.io/v3/static/sorsa_api_v3_documentation_en.txt

ChatGPT or Claude

One-off scripts, no setup.

Here are the Sorsa API docs: https://api.sorsa.io/v3/static/sorsa_api_v3_documentation_en.txt Write me a script to download all tweets from @sama into a CSV.

Works the same in Grok build, Antigravity, and any other LLM or coding agent. One docs URL is all it needs.


AI agent ready

Plug live X data into your AI agents

Connect any autonomous agent to a live X feed through clean tools, not glue code. The same 20 requests per second on every plan means agents do not get throttled the moment they go autonomous, and read-only access means an agent cannot break anything.

Function-calling native

Every endpoint maps cleanly to a tool an agent can call.

Built for autonomous loops

Flat 20 req/sec on every plan, predictable per-request cost.

Safe by default

Read-only, so an agent can read X data but never post or delete.

Drop Sorsa API in with one skill

Install the open-source Sorsa API skill once and your agent gains read-only X tools: search tweets, read profiles, pull followers and following, fetch user timelines, track mentions, and read trends. It works with skill-based agents like OpenClaw (through ClawHub) and Hermes Agent, or drop the skill folder into any agent that loads one. Bring your Sorsa API key. No X developer account, no posting, no write access.

OpenClaw Hermes Agent OpenAGI Claude tool use OpenAI function calling any custom agent
  • search tweets
  • read profiles
  • followers and following
  • user timelines
  • track mentions
  • read trends

Prefer MCP? Connect the Sorsa API MCP Server

Add Sorsa API as native tools in Claude, Cursor, VS Code, and any MCP client. One line to install, live X data on tap, no glue code on your side.

Set up the MCP server

One pass

From prompt to data in one pass

A real round-trip. You ask, the model reads the docs, it ships this.

"Pull recent tweets about AI agents with 100+ likes and save them to CSV. Use Sorsa API."

Python
import requests, csv

resp = requests.post(
    "https://api.sorsa.io/v3/search-tweets",
    headers={"ApiKey": "YOUR_API_KEY"},
    json={"query": "AI agents min_faves:100", "order": "latest"},
)
tweets = resp.json()["tweets"]

with open("tweets.csv", "w", newline="") as f:
    writer = csv.writer(f)
    writer.writerow(["author", "likes", "text"])
    for t in tweets:
        writer.writerow([t["user"]["username"], t["likes_count"], t["full_text"]])

That is the whole integration. Pass next_cursor to page past the first 20 results. Every tweet already includes the full author profile at no extra cost.


Reliability

Why the model gets it right on the first try

The docs are built so an LLM can read them once and produce correct, working calls without guessing.

01

One self-contained docs file

The model reads every endpoint, parameter, and response shape from a single URL.

02

OpenAPI 3.0, built for function calling

A native fit for Claude tool use and OpenAI function calling.

03

Clean, predictable JSON

Every response has the same shape, so generated code parses it on the first try.

04

Flat pricing, 1 request = 1 call

The cost of the code your assistant writes stays predictable, with no per-resource math.

05

Endpoints close to the official X API

The model's prior knowledge transfers, so it writes correct calls faster.

06

Read-only by design

An assistant or agent cannot post, delete, or take any destructive action.


Comparison

Your AI assistant on X data: without Sorsa API vs with Sorsa API

What an assistant or agent can actually do with X data on its own, and what it can do once you point it at Sorsa API.

CapabilityWithout Sorsa APIWith Sorsa API
Search X platform-wideCannot, only reads a URL you paste inSearches millions by keyword, operator, date, and engagement
Read profiles and the follower graphLimited to one pasted pageFull profile, followers, and following by handle or ID
Real-time dataStale or blockedLive tweets, metrics, and trends
Build a working integrationGuesses an undocumented or OAuth-gated API and stallsReads one docs URL and ships code
Run autonomously at scaleRate-limited and brittle20 req/sec on every plan, flat per-request cost

Use cases

What you can build in one prompt

Point your assistant at the docs and describe the outcome. Each of these is one prompt away.

Sentiment pipeline over any keyword or cashtag.

See how

Export a follower or following list to CSV.

See how

Monitor mentions of your brand in real time.

See how

Track a competitor's timeline and engagement.

See how

Pull trending topics for any location.

See how

Build a clean dataset for model training.

See how

AI-Native

One URL. Every endpoint. Any LLM.

Our documentation is a single self-contained, machine-readable file. Drop the URL into Claude Code, Codex, Cursor, ChatGPT, Gemini, or Grok and the model learns every endpoint, parameter, and response shape on the spot, then writes your integration end to end. No SDK to learn, no wrapper to write.

api.sorsa.io/v3/static/sorsa_api_v3_documentation_en.txt
01

One docs file

The model reads everything from a single URL, no crawling 30 doc pages.

02

OpenAPI 3.0 spec

Structured for machine reading and native function calling.

03

Clean JSON

Every response has the same predictable shape, so generated code just works.


FAQ

Questions, answered.

Can Claude Code, Cursor, or Codex write a Sorsa API integration for me?

Yes. Paste our docs URL into your assistant and it writes the client, the requests, and the response parsing for you. Most integrations are a single prompt.

Do I need to install anything to use Sorsa API with my AI tools?

No. For code generation, just paste the docs URL. For live agent tools you can optionally install the MCP server or the Sorsa API skill, but neither is required to start.

Does Sorsa API work with OpenAI function calling and Claude tool use?

Yes. The OpenAPI 3.0 spec and clean, predictable JSON are built for both.

Which AI agents can use the Sorsa API skill?

Skill-based agents like OpenClaw (through ClawHub) and Hermes Agent, plus any agent that loads a skill folder. You bring your Sorsa API key.

Can my AI agent post tweets or send DMs through Sorsa API?

No. Sorsa API is read-only by design. That keeps autonomous agents safe and the service stable: an agent can read X data but never post, delete, or follow.

How do I keep API costs predictable when an agent runs in a loop?

Flat pricing. 1 request equals 1 call on every endpoint and every plan, with a flat 20 requests per second so the agent is not throttled.

Is there an OpenAPI spec and an MCP server?

Yes to both. The OpenAPI 3.0 documentation lives at one URL, and a dedicated Sorsa API MCP server connects the API as native tools in any MCP client.

What can I actually pull?

Public X data: tweet and user search, profiles, followers and following, timelines, comments, quotes, retweeters, mentions, trends, and action verification.

Paste the docs. Ship in one prompt.

Drop the URL into your assistant, grab a key, and your X integration is done.

Get your API key