media-mcp (woosal1337/media-mcp) is an MCP server listed on the M8ven Trust Index. It scores 58 out of 100, grade D. It declares 30 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
D
Caution
58/100

media-mcp

MCP server enabling interaction with Twitter, YouTube, Instagram, and video processing via 31 tools, with local Whisper transcription and frame extraction for visual verification.

→ woosal1337/media-mcp· listed on glama

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

woosal1337

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Known vulnerabilities in dependencies: 3 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 3 credentials: CLOUDFLARE_API_TOKEN, COBALT_API_KEY, TWITTER_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes30 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

get_tweet

Fetch a tweet by URL. Returns tweet text, author info, metrics, and media. If the tweet contains a video, automatically transcribes the audio with segment-level timestamps AND per-token confidence — the output includes **Uncertainty zones** (spans where Whisper is guessing, with midpoint_s timestamp…

get_user_profile

Fetch a Twitter/X user's profile by username. Returns bio, follower/following counts, tweet count, verification status, location, and website.

get_user_tweets

Fetch recent tweets from a Twitter/X user. Returns up to 20 tweets per page with text, metrics, and media. Use cursor for pagination.

get_user_followers

Fetch followers of a Twitter/X user. Returns up to 200 per page with profile info.

get_user_following

Fetch accounts a Twitter/X user follows. Returns up to 200 per page with profile info.

get_tweet_replies

Fetch replies to a specific tweet. Returns up to 20 replies per page.

get_tweet_quotes

Fetch quote tweets of a specific tweet. Returns up to 20 per page.

get_tweet_retweeters

Fetch users who retweeted a specific tweet. Returns up to 100 per page.

search_tweets

Search Twitter/X with advanced query syntax. Returns up to 20 tweets per page. Supports operators like 'from:user', 'to:user', '#hashtag', 'min_faves:100', date ranges, etc.

get_trends

Fetch current trending topics on Twitter/X. Optionally specify a WOEID for location-specific trends (1 = worldwide, 23424977 = US, 23424969 = Turkey).

get_user_about

Fetch extended profile/about info for a Twitter/X user. Returns additional bio details beyond the basic profile.

get_user_mentions

Fetch tweets that mention a specific Twitter/X user. Returns up to 20 mentions per page. Use to see who's talking about you or any user.

search_users

Search for Twitter/X users by keyword. Find influencers, competitors, or accounts in any niche.

get_verified_followers

Fetch verified (blue check) followers of a Twitter/X user. 20 per page. Use to identify high-value followers on any account.

check_follow_relationship

Check if user A follows user B and vice versa. Use to verify mutual follows or check if a target already follows you.

get_tweet_replies_v2

Fetch replies to a tweet with sorting. Sort by Relevance, Latest, or Likes to find the most engaging responses.

get_list_timeline

Fetch tweets from a Twitter/X list. Use list IDs from curated lists to get niche-specific content feeds.

get_community_tweets

Fetch tweets from a Twitter/X community. Browse community content for engagement opportunities.

get_space_detail

Fetch details about a Twitter/X Space — title, host, speakers, listener count, state.

monitor_user_add

Start monitoring a Twitter/X user for real-time tweet notifications. Use to track when competitors or influencers post.

monitor_user_list

List all Twitter/X users currently being monitored for real-time tweets.

monitor_user_remove

Stop monitoring a Twitter/X user for real-time tweets.

filter_rule_add

Add a tweet filter rule for real-time keyword monitoring. Matches tweets containing specific terms.

filter_rule_list

List all active tweet filter rules for real-time monitoring.

filter_rule_delete

Delete a tweet filter rule to stop real-time keyword monitoring.

get_youtube_transcript

Fetch the transcript/subtitles of a YouTube video with timestamps. First tries YouTube captions (instant, already timestamped). If no captions exist, downloads the audio and transcribes locally with Whisper, producing segment-level timestamps AND per-token confidence — the output includes **Uncertai…

get_instagram_post

Fetch an Instagram post or reel by URL. Downloads ALL media (carousel images, videos) to a local folder with a unique ID. Videos are transcribed with Whisper with segment-level timestamps AND per-token confidence — the output includes **Uncertainty zones** (spans where Whisper is guessing, with midp…

extract_video_frames

Extract frames from any video as images. Supports YouTube, Instagram, Twitter, TikTok, and direct video URLs. Downloads the video, extracts frames at a specified rate (e.g., 1 frame/sec or 2 frames/sec), and saves them to a local folder. Returns file paths so Claude can read/analyze each frame visua…

get_video_frames_at

Precision frame extraction — grab ONE frame at each specified timestamp from a video URL. Use this as the companion to the transcription tools (get_tweet, get_youtube_transcript, get_instagram_post) to verify on-screen content at timestamps where transcription is unreliable. Triggers: (1) the transc…

fetch_markdown

Extract clean markdown from any webpage using Cloudflare Browser Run. Works on JS-heavy pages, SPAs, and sites where simple fetch fails. Use as a fallback when WebFetch returns empty or broken content. Requires CLOUDFLARE_ACCOUNT_ID and CLOUDFLARE_API_TOKEN env vars.

// known CVEs in dependencies3 high

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.12.1GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.12.1GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.12.1GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configCLOUDFLARE_ACCOUNT_ID=your_account_id (optional, for fetch_markdown)
🔐 secretCLOUDFLARE_API_TOKEN=your_api_token (optional, for fetch_markdown)
🔐 secretCOBALT_API_KEY=your_cobalt_key (optional)
configCOBALT_API_URL=http://localhost:9000 (optional, for Instagram)
configMEDIA_MCP_CACHE_DIRNo Where the 24h video cache lives (defaults to ~/.media-mcp/cache)
configMEDIA_MCP_MODEL_DIRNo Where auto-downloaded Whisper models live (defaults to ~/.media-mcp/models)
🔐 secretTWITTER_API_KEYyour_key npx media-mcp
configWHISPER_MODEL_PATH=/absolute/path/to/models/ggml-base.bin
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

30/30 tools missing one or more hints — get_tweet (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_user_profile (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_user_tweets (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +27 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool inputs are validated

28/30 tool handlers declare input schemas (93%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool test coverage

Only 1/30 tools referenced in tests (3%)

Write tests that reference each tool by name so every tool has at least one test.

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.1 (high), @modelcontextprotocol/sdk@1.12.1 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/woosal1337/media-mcp?variant=verified)](https://m8ven.ai/mcp/woosal1337/media-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 59ec676c7d8043d27c2cc53658a2f5f4c1eb74c5
code hash: cd695e5f02fa4dccb4f977bc08b2db4becf5e34c3dbbccd06051d9a9ab48bb81
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client