Composio Migration

Move X/Twitter agent workflows from Composio-style tools to Twexapi MCP.

Use this guide when an agent already calls packaged X/Twitter tools and you want to migrate the workflow to Twexapi MCP.

Prerequisites

A Twexapi API key
A list of existing X/Twitter actions used by your agent
An MCP-capable runtime connected to https://api.twexapi.io/mcp
A test prompt and expected output from the old workflow

Use x-api-key: YOUR_API_KEY for MCP clients and Authorization: Bearer YOUR_API_KEY for REST fallbacks.

Migration map

Existing behavior	Twexapi MCP pattern
Search tweets	`explore(query="advanced search")`, then `twexapi_request`
Read a profile	`explore(category="users")` or `explore(category="accounts")`
Get followers	`explore(category="followers")`
Read replies or quotes	`explore(category="engagement")`
Post or reply	Use a `read_only: false` catalog entry and require confirmation

Agent instruction

Replace packaged X/Twitter tools with Twexapi MCP.
First call explore to find the closest Twexapi endpoint.
Then call twexapi_request with the exact method and relative path returned by explore.
Preserve tweet_id, user_id, route_used, has_more, and next_cursor.
Ask for confirmation before read_only: false actions.

Handoff contract

Make every migrated tool return a stable handoff object before downstream steps consume it.

{
  "route_used": "/twitter/advanced_search/page",
  "method": "POST",
  "source_tool": "legacy_twitter_search",
  "has_more": true,
  "next_cursor": "cursor_123",
  "rows": [
    {
      "tweet_id": "1803006263529541838",
      "author_username": "openai",
      "text": "Example tweet text",
      "created_at": "2026-07-02T10:00:00Z",
      "public_url": "https://x.com/i/web/status/1803006263529541838"
    }
  ]
}

Example migration

Old task:

Search Twitter for AI agent launch announcements and summarize the top posts.

Twexapi MCP task:

Use Twexapi MCP to search recent X posts about "AI agent launch".
Call explore first and choose the search endpoint.
Return JSON with route_used, tweets[{tweet_id,text,author_username,created_at,public_url}], has_more, next_cursor, and a short summary.

Validation checklist

Compare row counts before and after migration.
Verify all downstream steps use tweet_id instead of URL parsing.
Confirm cursors are stored outside the agent conversation.
Add human approval for any migrated write action.

Tool call rewrite

Use this mechanical rewrite when adapting old agent instructions.

Old instruction	New instruction
“Call the Twitter search tool”	“Call `explore(query=\"advanced search\")`, then `twexapi_request`.”
“Fetch this profile”	“Call `explore(category=\"users\")` and preserve `user_id`.”
“Continue pagination”	“Use the returned `next_cursor`; do not parse it.”
“Post this tweet”	“Prepare a write plan and ask for approval before `read_only: false`.”

Regression prompt

Run this before and after migration:

Find recent posts about "AI agents" from the last 24 hours.
Return exactly 10 rows with tweet_id, author_username, text, created_at, public_url, route_used, has_more, and next_cursor.
Do not call write endpoints.

Production rollout

Run old and new workflows side by side on read-only tasks.
Compare row counts, required fields, and representative URLs.
Switch scheduled jobs to the Twexapi MCP/REST route.
Re-enable write actions only after approval prompts are tested.