# Xcatcher — Recent X Posts

> Fetch recent public X/Twitter posts by named handle for monitoring, comparison, OSINT, and research.

- name: io.github.lvpiggyqq/xcatcher
- version: 3.1.0
- connection class: unknown (unknown)
- trust: 72/100
- quality: 88/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.lvpiggyqq%2Fxcatcher
- tools: https://api.protogrid.dev/v1/servers/io.github.lvpiggyqq%2Fxcatcher/tools

**Not classified yet.** The remote endpoints have not been probed successfully, or the listing has nothing to connect to.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "xcatcher": {
      "type": "http",
      "url": "https://xcatcher.top/mcp/",
      "headers": {
        "Authorization": "Bearer ${XCATCHER_TOKEN}",
        "Accept": "application/json"
      }
    }
  }
}
```

Placeholders to fill: `${XCATCHER_TOKEN}`.

## Trust

- hygiene: 100
- liveness: 28
- freshness: 85
- provenance: 90
- drivers: +repository +namespace-matches-repo +website -unreachable(1 failures) ~updated-71d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 88/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 93 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 1 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 17 of 17 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 3,418 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 17, about 3,418 tokens to load them all
- tool set hash: 55f498faba220c2bfac8762f199772f9
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.lvpiggyqq/xcatcher.svg)](https://protogrid.dev/servers/io.github.lvpiggyqq/xcatcher)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://xcatcher.top/mcp/ (streamable-http, auth none, reachable false, uptime30d 0.9385965)

## Packages

_none_

## Tools (17)

- `cancel_task`: Cancel a queued task by task_id. Side effects: changes task state. Xcatcher refunds cost_points when a queued task is successfully cancelled.
- `create_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).

- `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.
- `get_direct_crawl_payment`: 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.
- `get_direct_result_preview`: 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.
- `get_direct_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.
- `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.
- `get_result_preview`: 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.
- `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.
- `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.
- `get_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.
- `get_x402_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.
- `list_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.
- `preflight_crawl`: 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.
- `submit_direct_crawl_payment`: 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.
- `wait_for_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.
- `x402_topup`: 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).