Xcatcher — Recent X Posts
Fetch recent public X/Twitter posts by named handle for monitoring, comparison, OSINT, and research.
Should I use this
Quality & Safety
Findings (1)
- LOWTool 'get_result_download_url' suggests web access but openWorldHint=falsein get_result_download_url
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"xcatcher": {
"url": "https://xcatcher.top/mcp"
}
}
}Remote endpoints
https://xcatcher.top/mcpstreamable-httphttps://xcatcher.top/mcp/streamable-httpWhat it can do
Tool inventory
Tools (17)
🟢get_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.
Input Schema
{
"type": "object",
"properties": {},
"title": "get_service_infoArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_service_infoOutput"
}🟢preflight_crawl(users, mode)
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.
Input Schema
{
"type": "object",
"properties": {
"users": {
"description": "X handles, @handles, or x.com/twitter.com profile URLs.",
"items": {
"type": "string"
},
"maxItems": 500,
"minItems": 1,
"title": "Users",
"type": "array"
},
"mode": {
"default": "normal",
"description": "API-key accounts use 1 point per normal handle and 10 per deep handle; direct x402 normal requests receive progressive batch pricing shown by preflight.",
"enum": [
"normal",
"deep"
],
"title": "Mode",
"type": "string"
}
},
"required": [
"users"
],
"title": "preflight_crawlArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "preflight_crawlOutput"
}🟢get_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.
Input Schema
{
"type": "object",
"properties": {},
"title": "get_sample_resultArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_sample_resultOutput"
}🟢get_account_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.
Input Schema
{
"type": "object",
"properties": {},
"title": "get_account_balanceArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_account_balanceOutput"
}🟢list_crawl_tasks(limit, before_id)
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.
Input Schema
{
"type": "object",
"properties": {
"limit": {
"default": 20,
"description": "Tasks to return (1-100).",
"maximum": 100,
"minimum": 1,
"title": "Limit",
"type": "integer"
},
"before_id": {
"anyOf": [
{
"minimum": 1,
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"description": "Cursor from next_before_id; omit for the newest tasks.",
"title": "Before Id"
}
},
"title": "list_crawl_tasksArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "list_crawl_tasksOutput"
}🟡get_x402_quote(points)
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.
Input Schema
{
"type": "object",
"properties": {
"points": {
"description": "Number of points to buy (1-200000). Live quote amount is authoritative.",
"maximum": 200000,
"minimum": 1,
"title": "Points",
"type": "integer"
}
},
"required": [
"points"
],
"title": "get_x402_quoteArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_x402_quoteOutput"
}🟡get_direct_crawl_payment(users, mode)
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.
Input Schema
{
"type": "object",
"properties": {
"users": {
"description": "X handles, @handles, or x.com/twitter.com profile URLs.",
"items": {
"type": "string"
},
"maxItems": 500,
"minItems": 1,
"title": "Users",
"type": "array"
},
"mode": {
"default": "normal",
"description": "Direct x402 normal requests use progressive batch pricing; deep is $0.10 per normalized requested handle. Always preflight the complete list.",
"enum": [
"normal",
"deep"
],
"title": "Mode",
"type": "string"
}
},
"required": [
"users"
],
"title": "get_direct_crawl_paymentArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_direct_crawl_paymentOutput"
}🔴submit_direct_crawl_payment(users, payment_signature_b64, mode)
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.
Input Schema
{
"type": "object",
"properties": {
"users": {
"description": "The exact handles/profile URLs used for the payment requirement.",
"items": {
"type": "string"
},
"maxItems": 500,
"minItems": 1,
"title": "Users",
"type": "array"
},
"payment_signature_b64": {
"description": "The base64(JSON) PAYMENT-SIGNATURE produced for the accepted x402 v2 requirement.",
"title": "Payment Signature B64",
"type": "string"
},
"mode": {
"default": "normal",
"description": "Must exactly match the quoted mode.",
"enum": [
"normal",
"deep"
],
"title": "Mode",
"type": "string"
}
},
"required": [
"users",
"payment_signature_b64"
],
"title": "submit_direct_crawl_paymentArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "submit_direct_crawl_paymentOutput"
}🟢get_direct_task_status(task_id, task_token)
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.
Input Schema
{
"type": "object",
"properties": {
"task_id": {
"description": "Task ID returned after x402 settlement.",
"minimum": 1,
"title": "Task Id",
"type": "integer"
},
"task_token": {
"description": "Task-scoped xtask_ token returned after settlement or idempotent recovery.",
"title": "Task Token",
"type": "string"
}
},
"required": [
"task_id",
"task_token"
],
"title": "get_direct_task_statusArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_direct_task_statusOutput"
}🟢get_direct_result_preview(task_id, task_token, limit, offset)
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.
Input Schema
{
"type": "object",
"properties": {
"task_id": {
"description": "Completed paid task ID.",
"minimum": 1,
"title": "Task Id",
"type": "integer"
},
"task_token": {
"description": "Task-scoped xtask_ token.",
"title": "Task Token",
"type": "string"
},
"limit": {
"default": 20,
"description": "Rows to return (1-100).",
"maximum": 100,
"minimum": 1,
"title": "Limit",
"type": "integer"
},
"offset": {
"default": 0,
"description": "Zero-based row offset.",
"minimum": 0,
"title": "Offset",
"type": "integer"
}
},
"required": [
"task_id",
"task_token"
],
"title": "get_direct_result_previewArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_direct_result_previewOutput"
}🔴create_crawl_task(users, mode, idempotency_key)
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).
Input Schema
{
"type": "object",
"properties": {
"users": {
"description": "Array of X usernames (handles). You may include a leading '@'.",
"items": {
"type": "string"
},
"maxItems": 500,
"minItems": 1,
"title": "Users",
"type": "array"
},
"mode": {
"default": "normal",
"description": "normal = fast latest-post snapshot at scale; deep = deeper per-user collection (slower).",
"enum": [
"normal",
"deep"
],
"title": "Mode",
"type": "string"
},
"idempotency_key": {
"anyOf": [
{
"maxLength": 128,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional idempotency key for safe retries (recommended for agents).",
"title": "Idempotency Key"
}
},
"required": [
"users"
],
"title": "create_crawl_taskArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "create_crawl_taskOutput"
}🔴x402_topup(quote_id, payment_signature_b64)
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).
Input Schema
{
"type": "object",
"properties": {
"quote_id": {
"description": "Quote ID returned by PAYMENT-REQUIRED (or /x402/quote).",
"title": "Quote Id",
"type": "string"
},
"payment_signature_b64": {
"description": "Base64(JSON) for header PAYMENT-SIGNATURE.",
"title": "Payment Signature B64",
"type": "string"
}
},
"required": [
"quote_id",
"payment_signature_b64"
],
"title": "x402_topupArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "x402_topupOutput"
}🟢get_task_status(task_id)
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.
Input Schema
{
"type": "object",
"properties": {
"task_id": {
"description": "Task ID returned by create_crawl_task.",
"minimum": 1,
"title": "Task Id",
"type": "integer"
}
},
"required": [
"task_id"
],
"title": "get_task_statusArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_task_statusOutput"
}🟢wait_for_task(task_id, timeout_seconds, poll_interval_seconds)
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.
Input Schema
{
"type": "object",
"properties": {
"task_id": {
"description": "Task ID returned by create_crawl_task.",
"minimum": 1,
"title": "Task Id",
"type": "integer"
},
"timeout_seconds": {
"default": 60,
"description": "Maximum wait in seconds (5-120).",
"maximum": 120,
"minimum": 5,
"title": "Timeout Seconds",
"type": "integer"
},
"poll_interval_seconds": {
"default": 5,
"description": "Seconds between status checks (2-15).",
"maximum": 15,
"minimum": 2,
"title": "Poll Interval Seconds",
"type": "integer"
}
},
"required": [
"task_id"
],
"title": "wait_for_taskArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "wait_for_taskOutput"
}🟢get_result_preview(task_id, limit, offset)
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.
Input Schema
{
"type": "object",
"properties": {
"task_id": {
"description": "Completed task ID owned by the current API key.",
"minimum": 1,
"title": "Task Id",
"type": "integer"
},
"limit": {
"default": 20,
"description": "Maximum result rows to return (1-100).",
"maximum": 100,
"minimum": 1,
"title": "Limit",
"type": "integer"
},
"offset": {
"default": 0,
"description": "Zero-based row offset for pagination.",
"minimum": 0,
"title": "Offset",
"type": "integer"
}
},
"required": [
"task_id"
],
"title": "get_result_previewArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_result_previewOutput"
}🟢get_result_download_url(task_id)
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.
Input Schema
{
"type": "object",
"properties": {
"task_id": {
"description": "Task ID. Must be completed (has_result=true).",
"minimum": 1,
"title": "Task Id",
"type": "integer"
}
},
"required": [
"task_id"
],
"title": "get_result_download_urlArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_result_download_urlOutput"
}🔴cancel_task(task_id)
Cancel a queued task by task_id. Side effects: changes task state. Xcatcher refunds cost_points when a queued task is successfully cancelled.
Input Schema
{
"type": "object",
"properties": {
"task_id": {
"description": "Task ID to cancel.",
"minimum": 1,
"title": "Task Id",
"type": "integer"
}
},
"required": [
"task_id"
],
"title": "cancel_taskArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "cancel_taskOutput"
}Community
Evidence