mcp.xpoz.ai

Item: mcp.xpoz.ai
Rating: 86
Author: wmcp.sh

https://mcp.xpoz.ai/mcp

86/100 · MCP Trust Grade · checked 5h ago · MCP 2025-06-18

⚠ Rug-pull watch: this server's tool surface has changed 2× since baseline — last 6h ago. Continuously watched by wmcp.sh for drift & rug-pulls.

What it offers — 48 tools · Developer Tools

getTwitterUsers

Get one or more Twitter user profiles by IDs or usernames (1-100 per request). Use identifierType="id" for numeric user IDs, identifierType="username"

getTwitterUser

Get Twitter user profile by ID or username. Use identifierType="id" for numeric user ID, identifierType="username" for username. For username: Use ONL

searchTwitterUsers

Search users by person name, partial username, or fuzzy match using real-time external API. PRIMARY USE: When given person's name (e.g., "Elon Musk",

getTwitterUserConnections

Get Twitter user connections (followers or following). Use connectionType="followers" for users who follow them, connectionType="following" for users

getTwitterUsersByKeywords

Search for USERS who authored tweets/comments/quotes/retweets matching keywords. USE CASE: Find users who have posted content about specific topics, k

getTwitterPostsByIds

Get multiple Twitter posts by numeric IDs (1-100 IDs per request). Returns results directly. Returns only found tweets, omitting not-found IDs for fle

getTwitterPostsByAuthor

Get posts from author by username with multiple response modes. FAST (default, omit responseType or responseType="fast"): Returns up to 300 results di

getTwitterPostsByKeywords

Search posts by keywords. FAST (default, omit responseType or responseType="fast"): Returns up to 300 results directly (use limit param to reduce, e.g

getTwitterPostRetweets

Get retweets of specific post. FAST (default, omit responseType or responseType="fast"): Returns up to 300 results directly (use limit param to reduce

getTwitterPostQuotes

Get quote posts of specific post. FAST (default, omit responseType or responseType="fast"): Returns up to 300 results directly (use limit param to red

getTwitterPostComments

Get comments (replies) to specific post. FAST (default, omit responseType or responseType="fast"): Returns up to 300 results directly (use limit param

countTweets

Count tweets containing a specific phrase within a date range. Returns the total count of matching tweets (int) directly, or zero if none found. QUERY

getTwitterPostInteractingUsers

Get users who interacted with a specific Twitter post (commenters, quoters, or retweeters). INTERACTION TYPES: "commenters" (users who replied to the

checkOperationStatus

checkOperationStatus: poll an async operation and retrieve its results or CSV download URL. Use this after any tool call made with responseType="pagin

cancelOperation

Cancel running operation. Required: operationId. Gracefully stops operation at next checkpoint. Returns confirmation. Use checkOperationStatus to veri

getInstagramPostsByIds

Get multiple Instagram posts by IDs (1-100 IDs per request). Returns results directly. Returns only found posts, omitting not-found IDs for flexibilit

getInstagramPostsByUser

Get posts from Instagram user by ID or username with two response modes. Use identifierType="id" for numeric user ID, identifierType="username" for us

getInstagramPostsByKeywords

Search Instagram posts by keywords with two response modes. Searches in both post captions and video subtitles. FAST (default, omit responseType or re

+30 more tools

Spec conformance20%80

✓ initialize → protocolVersion 2025-06-18
✓ initialize HTTP 200
✗ unknown method → no JSON-RPC error
✓ tools/list → 48 tools
✓ every tool has name + inputSchema

Security (OWASP MCP)30%100

48 tools scanned
no injection markup
no secret-path refs

Reliability / performance20%70

single-probe latency 1795ms (PRELIMINARY — continuous uptime/p95 from proxy telemetry lands in v2)

Tool hygiene15%80

100% of tools have typed inputSchema
0/48 declare outputSchema
no unannotated destructive tools

Transparency / provenance15%90

HTTPS ✓
RFC 9728 oauth-protected-resource metadata ✓
advertises protocol 2025-06-18

Observed behavior

No proxied traffic observed for this host yet. Connect it at /connect and its grade gains a measured Reliability score + per-tool behavioral evidence — the half a static scan can't produce.

Findings

No blocking issues found in the static + spec checks.

Grade another server

We re-grade mcp.xpoz.ai on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — mcp.xpoz.ai grade B

Share on X Open card image

https://wmcp.sh/mcp/grade/mcp.xpoz.ai

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

Markdown (for your README)

[![MCP Trust Grade B](https://wmcp.sh/mcp/grade/mcp.xpoz.ai/badge.svg)](https://wmcp.sh/mcp/grade/mcp.xpoz.ai)

HTML

<a href="https://wmcp.sh/mcp/grade/mcp.xpoz.ai"><img src="https://wmcp.sh/mcp/grade/mcp.xpoz.ai/badge.svg" alt="MCP Trust Grade B · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust

How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.