Recall Data Omnifeeds (recallnet/external-mcp) is an MCP server listed on the M8ven Trust Index. It scores 47 out of 100, grade D. It declares 1 tool. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
D
Caution
47/100

Recall Data Omnifeeds

This server enables AI models & Agents to interact with and search data from multiple curated sources through a unified MCP (model context protocol) server..

→ recallnet/external-mcp· listed on mcp_so

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

recallnet

Source: mcp.so

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

mcp.sonot 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: 14 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.
🔐
You'll be asked for 6 credentials: COINGECKO_API_KEY, TWITTER_ACCESS_SECRET, TWITTER_ACCESS_TOKEN, TWITTER_APP_KEY, TWITTER_APP_SECRET, TWITTER_PASSWORD
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes48 tools · 47 behind config

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.

calculate-statistics
substack-get-post-slugsbehind config

Gets a lightweight list of recent posts with only basic info (slug, title, date). Best for browsing publications quickly.

substack-get-recent-postsbehind config

Retrieves recent posts from a Substack publication. Returns minimal metadata by default, or full content when fullData=true.

substack-get-postsbehind config

Gets posts from a Substack publication with pagination support. Use offset to navigate through older posts.

substack-get-post-by-slugbehind config

Retrieves a specific post by its slug identifier. Use fullData=true to get complete content.

substack-get-post-contentbehind config

Fetches full content of a post given its complete URL. Returns full article content.

substack-get-latest-post-contentbehind config

Retrieves the most recent post from a publication. Set fullData=true to get complete content.

substack-get-commentsbehind config

Retrieves comments for a specific post.

substack-search-postsbehind config

Searches for posts containing the specified term. Returns matching posts with metadata.

substack-get-publication-infobehind config

Gets information about a Substack publication including description, stats, and metadata.

substack-list-categoriesbehind config

Lists all available Substack content categories.

substack-get-category-newslettersbehind config

Gets list of newsletters in a specific category.

substack-get-user-profilebehind config

Gets public profile information for a Substack user.

substack-get-newsletter-authorsbehind config

Gets the authors of a Substack publication.

substack-get-latest-post-simplifiedbehind config

Retrieves the most recent post from a publication in simplified text format without HTML markup.

substack-get-newsletter-recommendationsbehind config

Gets recommended newsletters for a specific publication.

substack-search-and-get-contentbehind config

Searches for posts by term and returns the first match. Use fullData=true to get complete content.

substack-get-post-summariesbehind config

Gets lightweight summaries of posts (without full content) - optimized for efficient browsing.

twitter-get-profilebehind config

Gets public profile information for a Twitter user.

twitter-get-tweetsbehind config

Gets recent tweets from a specific user (doesn't include replies).

twitter-get-tweets-and-repliesbehind config

Gets recent tweets and replies from a specific user (includes conversations).

twitter-get-latest-tweetbehind config

Gets only the most recent tweet from a user (optionally include retweets).

twitter-get-tweetbehind config

Gets a single tweet by its ID.

twitter-get-quoted-tweetsbehind config

Gets tweets that quote (retweet with comment) a specific tweet.

twitter-get-retweetersbehind config

Gets users who retweeted a specific tweet.

twitter-get-list-tweetsbehind config

Gets tweets from a Twitter list (curated collection of users).

twitter-get-trendsbehind config

Gets current trending topics on Twitter.

twitter-search-tweetsbehind config

Searches for tweets containing specific keywords or matching search criteria.

twitter-search-profilesbehind config

Searches for Twitter user profiles matching the search query.

twitter-get-user-idbehind config

Converts a Twitter username to its numeric user ID.

twitter-get-usernamebehind config

Converts a Twitter user ID to its username (screen name).

twitter-get-followersbehind config

Gets users who follow a specific Twitter user.

twitter-get-followingbehind config

Gets users that a specific Twitter user follows.

twitter-get-articlebehind config

Gets an article published via Twitter.

twitter-send-tweetbehind config

Posts a new tweet to the authenticated user's account.

twitter-like-tweetbehind config

Likes a tweet as the authenticated user.

twitter-retweetbehind config

Retweets a tweet as the authenticated user.

twitter-follow-userbehind config

Follows a user as the authenticated user.

twitter-get-home-timelinebehind config

Gets the home timeline for the authenticated user.

twitter-get-following-timelinebehind config

Gets tweets from accounts the authenticated user follows.

twitter-get-dm-conversationsbehind config
twitter-send-dmbehind config
twitter-grok-chatbehind config
coingecko-get-featuresbehind config

Gets available CoinGecko API features and capabilities.

coingecko-get-pricebehind config

Gets current price of a cryptocurrency token in specified currency.

coingecko-get-contractsbehind config

Gets blockchain contract addresses for a token across different chains.

coingecko-searchbehind config

Searches for cryptocurrency tokens by name or symbol.

coingecko-trendingbehind config

Gets currently trending tokens in the cryptocurrency market.

// known CVEs in dependencies14 high5 medium11 low

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

high@modelcontextprotocol/sdk@1.8.0GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.8.0GHSA-w48q-cv73-mx4w

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

highaxios@1.8.3GHSA-35jp-ww65-95wh

axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`

highaxios@1.8.3GHSA-3g43-6gmg-66jw

axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge

highaxios@1.8.3GHSA-43fc-jf86-j433

Axios is Vulnerable to Denial of Service via __proto__ Key in mergeConfig

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.
🔐 secretCOINGECKO_API_KEY
🔐 secretTWITTER_ACCESS_SECRET
🔐 secretTWITTER_ACCESS_TOKEN
🔐 secretTWITTER_APP_KEY
🔐 secretTWITTER_APP_SECRET
configTWITTER_EMAIL
🔐 secretTWITTER_PASSWORD
configTWITTER_USERNAME
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
// 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

48/48 tools missing one or more hints — calculate-statistics (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); substack-get-post-slugs (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); substack-get-recent-posts (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +45 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

47/48 tool handlers declare input schemas (98%)

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

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tool test coverage

Only 0/48 tools referenced in tests (0%)

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

Production dependencies are patched

0 critical, 14 high severity in production deps — @modelcontextprotocol/sdk@1.8.0 (high), @modelcontextprotocol/sdk@1.8.0 (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 6 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/recallnet/external-mcp?variant=verified)](https://m8ven.ai/mcp/recallnet/external-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 9d55a0ec36c3c467c792ea44b92e0e9628e2b304
code hash: 3d2e31a4d43fa7b495c2527e3ea5f22586fecf72c966925d5d8dcc2235be5c01
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