# xcatcher MCP server

High-throughput X/Twitter crawl via tasks; download XLSX; x402 USDC Base/Solana top-ups.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-lvpiggyqq-xcatcher
- Repository: https://github.com/lvpiggyqq/xcatcher-mcp-manifest

## Install
- Endpoint: https://xcatcher.top/mcp/
- Auth: Not captured

## Setup notes
- Remote header: Authorization
- Remote header: Accept
- Remote header: Content-Type
- Remote endpoint: https://xcatcher.top/mcp/
- Header: Authorization
- Header: Accept
- Header: Content-Type

## Tools
- get_service_info (Get Xcatcher service info) - Read Xcatcher's live capabilities, prices, limits, endpoints, and recommended agent workflow. Call this first when planning a crawl or when cached documentation may be stale. No points are consumed. Endpoint: https://xcatcher.top/mcp/
- preflight_crawl (Preflight an Xcatcher crawl for free) - Normalize and deduplicate X handles, validate the mode, and preview the current modeled points/USDC cost. This free read-only check requires no account, creates no quote or task, and moves no funds. Use it before requesting a live x402 payment challenge. Endpoint: https://xcatcher.top/mcp/
- get_sample_result (Inspect a free Xcatcher sample result) - Return a stable synthetic example of Xcatcher's paginated result and coverage metadata. No live X data is fetched, no account is needed, no task or quote is created, and no funds move. Endpoint: https://xcatcher.top/mcp/
- get_account_balance (Get Xcatcher balance) - Return the account attached to the current Bearer API key and its points balance. Use before creating a task to estimate whether an x402 top-up will be needed. Read-only. Endpoint: https://xcatcher.top/mcp/
- list_crawl_tasks (List Xcatcher crawl tasks) - List recent tasks owned by the current Bearer API key, newest first. Use next_before_id for cursor pagination. Read-only and does not consume points. Endpoint: https://xcatcher.top/mcp/
- get_x402_quote (Get an x402 top-up quote) - Create a short-lived USDC quote for a requested number of Xcatcher points. Returns the exact live amount and supported Base/Solana payment requirements; it does not move funds. Ask the user before signing or sending any payment. Endpoint: https://xcatcher.top/mcp/
- get_direct_crawl_payment (Get accountless crawl payment requirements) - Create a request-bound x402 v2 payment requirement for an accountless crawl. Use this only for the accountless x402 path after preflight_crawl; API-key accounts use create_crawl_task instead. Normal requests use progressive batch pricing, so quote the complete deduplicated handle list together. This does not move funds. Return payment_required_b64 unchanged to an x402-compatible wallet/client; the live amount, asset, network, destination, and quoteId are authoritative. Endpoint: https://xcatcher.top/mcp/
- submit_direct_crawl_payment (Pay for and create an accountless crawl) - Submit an x402 v2 PAYMENT-SIGNATURE for the exact users/mode used by get_direct_crawl_payment. This may settle USDC and create a crawl task. Call only after explicit spending approval. On success, securely save task_token: it grants task-scoped result access for seven days. Endpoint: https://xcatcher.top/mcp/
- get_direct_task_status (Get accountless paid task status) - Read an accountless paid crawl using its task_id and task-scoped token. Use this instead of get_task_status for an accountless x402 task. Poll every 5-10 seconds until task.has_result is true or it reaches failed/cancelled. Endpoint: https://xcatcher.top/mcp/
- get_direct_result_preview (Preview accountless paid crawl results) - Return structured JSON rows for a completed accountless paid crawl. Use this instead of get_result_preview for an accountless x402 task; API-key accounts use get_result_preview. Use offset for pagination; the task token is required and should be treated as a secret. Endpoint: https://xcatcher.top/mcp/
- create_crawl_task (Create an X crawl task) - Create a crawl task for one or more X (Twitter) usernames. Side effects: creates a new task AND consumes points.

If points are insufficient, upstream returns HTTP 402 with PAYMENT-REQUIRED (quote). This tool surfaces it as error.code=PAYMENT_REQUIRED with payment_required payload so agents can request spending approval, top up, then retry safely.

Modes:
- normal: Fast latest-post snapshot at scale (fresh-feed monitoring). Optimized for high-throughput batch retrieval.
- deep:   Deeper per-user collection/enrichment (typically slower; higher resource usage). Use when you need more than a quick latest-post snapshot.

Performance note: Normal mode is optimized for a small latest-post snapshot per handle. Actual completeness and latency depend on X availability, upstream limits, and network conditions.
Batching: For very large sets, split users into batches. Suggested upper bound per task: 500 users (configurable via MAX_USERS_PER_TASK).

Reliability:
- Use idempotency_key to make retries safe (avoid duplicate charges).
- After creation, poll get_task_status every 5–10s until has_result=true.
- Then call get_result_download_url (download still requires the same Bearer token).
 Endpoint: https://xcatcher.top/mcp/
- x402_topup (Credit points from an x402 payment) - Top up points for the CURRENT Bearer key using x402 proof.

Inputs:
- quote_id: returned by PAYMENT-REQUIRED (or /api/v1/x402/quote)
- payment_signature_b64: base64(JSON) that will be passed as HTTP header PAYMENT-SIGNATURE

Side effects: credits points to the same Bearer key (no key rotation).
On success returns credited_points and balance_after (shape depends on upstream).
 Endpoint: https://xcatcher.top/mcp/
- get_task_status (Get crawl task status) - Get API-key account task status by task_id (read-only); accountless x402 tasks use get_direct_task_status instead. Recommended polling interval: every 5–10 seconds until has_result=true.

Returns safe structured state, result metadata, and authenticated result URLs; server filesystem paths are never exposed. Endpoint: https://xcatcher.top/mcp/
- wait_for_task (Wait for a crawl task) - Poll a crawl task server-side until it has a result, reaches a terminal failure/cancelled state, or the bounded timeout expires. Read-only and cheaper for agent context than repeated manual polling. Endpoint: https://xcatcher.top/mcp/
- get_result_preview (Preview crawl results) - Return up to 100 result rows from an API-key account task as native structured JSON for direct agent analysis; accountless x402 tasks use get_direct_result_preview instead. Use offset/next_offset for pagination; this does not download or parse XLSX. Use after has_result=true; use get_result_download_url when the complete XLSX is required. Read-only. Endpoint: https://xcatcher.top/mcp/
- get_result_download_url (Get result download URL) - Get an absolute download URL for a task result (read-only). If the task is not finished, returns ok=false with code=RESULT_NOT_READY (HTTP 409). Downloading the URL requires the same Authorization: Bearer token. Endpoint: https://xcatcher.top/mcp/
- cancel_task (Cancel a queued crawl task) - Cancel a queued task by task_id. Side effects: changes task state. Xcatcher refunds cost_points when a queued task is successfully cancelled. Endpoint: https://xcatcher.top/mcp/

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.lvpiggyqq
- Version: 1.0.3
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Dec 24, 2025
- Source: https://registry.modelcontextprotocol.io