mcp-services (san-npm/mcp-services) is an MCP server listed on the M8ven Trust Index. It scores 73 out of 100, grade C. It declares 29 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Caution
73/100

mcp-services

Multi-tool MCP server for AI agents with 29 tools across web scraping, SEO analysis, screenshot and PDF generation, domain intelligence, content extraction, multi-chain EVM blockchain queries, and security toolkit. Free tier available with no auth required.

→ san-npm/mcp-services· 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

⚡ 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

san-npm

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
⚠️
Tool descriptions don’t match what handlers do
1 tool describes read intent but its handler mutates — ssl (line 424: spawn('openssl', args, { timeout }))
✅
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 5 credentials: ABUSEIPDB_API_KEY, ADMIN_SECRET, ETHERSCAN_API_KEY, STRIPE_WEBHOOK_SECRET, VT_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes29 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.

screenshot

Take a screenshot of any URL. Returns base64 PNG/JPEG image.

pdf

Generate a PDF of any URL.

pdf2docx

Convert a PDF file (from URL) to DOCX/Word format. Extracts text and structure from the PDF and builds a Word document.

whois

Look up WHOIS information for a domain.

dns

Look up DNS records for a domain.

balance

Get native token balance for an address on any supported chain.

erc20_balance

Get ERC20 token balance for an address.

transaction

Get transaction details by hash.

html2md

Fetch a URL and convert the page content to clean Markdown. Removes nav, ads, scripts.

ocr

Extract text from an image URL using OCR.

ssl

Check SSL certificate details for a domain. Returns issuer, validity dates, expiry status.

scrape

Scrape a URL and convert to clean Markdown. Returns title, markdown content, word count, and links found.

crawl

Crawl a website starting from a URL. Follows internal links up to specified depth. Returns markdown for each page.

extract

Extract structured data from a URL: JSON-LD, Open Graph, meta tags, headings, links, images, tables.

serp

Scrape Google search results for a keyword. Returns organic results, People Also Ask, featured snippets, and related searches.

onpage_seo

Full on-page SEO analysis of a URL. Scores title, meta description, headings, images, links, schema markup, Open Graph, and more.

keywords_suggest

Get keyword suggestions using Google Autocomplete. Returns up to 100 related keyword ideas.

memory_store

Store a memory in persistent storage. Memories are scoped by namespace. Upserts on key conflict.

memory_get

Retrieve a memory by namespace and key.

memory_search

Search memories by text query within a namespace. Uses full-text search.

memory_list

List all memories in a namespace with pagination.

memory_delete

Delete a memory by namespace and key.

url_scan

Scan a URL for phishing, typosquatting, homoglyphs, and malware. Uses VirusTotal (if configured) and heuristic analysis. Returns severity (clean/suspicious/malicious) with detailed risk indicators.

wallet_check

Check a wallet address for scam reports, OFAC sanctions, contract verification status, and suspicious transaction patterns. Supports Ethereum, Base, Arbitrum, Optimism, Polygon.

contract_scan

Scan a smart contract for honeypot detection, rug pull indicators (mint functions, blacklists, fee manipulation, proxy patterns), and source verification status.

email_headers

Validate email authentication for a domain. Checks SPF, DKIM (common selectors), DMARC policy, and MX records. Detects spoofing vulnerabilities.

threat_intel

Look up an IOC (IP, domain, URL, or file hash) across threat intelligence sources. Uses AbuseIPDB, VirusTotal, and OTX AlienVault with weighted confidence scoring.

header_audit

Audit security headers of a URL. Checks HSTS, CSP, X-Content-Type-Options, X-Frame-Options, Referrer-Policy, Permissions-Policy, and cookie security. Returns a score (0-100).

vuln_headers

Detect information leakage in HTTP response headers. Checks for exposed server versions, debug headers, X-Powered-By, CORS misconfigurations, and error responses.

// 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.
🔐 secretABUSEIPDB_API_KEYSecurity tools degrade gracefully without API keys (heuristics-only mode). Optional keys: VT_API_KEY, , ETHERSCAN_API_KEY.
🔐 secretADMIN_SECRETSecret for admin endpoints
configALLOW_APIKEY_QUERYFor migration only, query-string API keys (?apikey=) can be temporarily re-enabled with =true. This mode is deprecated; prefer X-Api-Key.
configAPI_KEYSComma-separated valid API keys
configCHECKOUT_LIMIT_PER_HOURPer-IP Stripe checkout creation limit
configCHROMIUM_PATHPath to Chromium
configDOMAIN
🔐 secretETHERSCAN_API_KEYSecurity tools degrade gracefully without API keys (heuristics-only mode). Optional keys: VT_API_KEY, ABUSEIPDB_API_KEY, .
configFREE_DAILY_LIMITFree tier request limit
configFREE_WINDOW_MSFree-tier rate-limit window in ms
configKEYS_FILEPersist , MEMORY_DB_PATH, and X402_TX_CACHE_FILE on durable storage
configMAX_BROWSERSMax concurrent browser instances
configMAX_SSE_PER_IPMax concurrent SSE sessions per client IP
configMAX_SSE_SESSIONSMax MCP SSE sessions
configMEMORY_DB_PATHSQLite memory database path
configSSE_CONNECT_MAX_PER_WINDOWMax SSE connection attempts per IP per window
configSSE_CONNECT_WINDOW_MSSSE connect rate-limit window in ms
configSTRIPE_SKStripe API key for Pro subscriptions
configSTRIPE_WEBHOOK_IP_ALLOWLISTOptional CSV allowlist for webhook source IPs
🔐 secretSTRIPE_WEBHOOK_SECRETStripe webhook signing secret
configTRUST_PROXYExpress trust proxy setting (false, true, hop count like 1, or subnet names/CIDRs like loopback/10.0.0.0/8)
🔐 secretVT_API_KEYSecurity tools degrade gracefully without API keys (heuristics-only mode). Optional keys: , ABUSEIPDB_API_KEY, ETHERSCAN_API_KEY.
configX402_MAX_TX_AGE_SECONDSMaximum accepted payment tx age in seconds (stale txs are rejected)
configX402_PRICE_USDx402 price per call
configX402_RECEIVERx402 payment receiver address
configX402_TEST_MODESet to 1 only for local/offline testing; ignored in production
configX402_TX_CACHE_FILEPersistent replay-protection cache for used x402 tx hashes
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
deployREDIS_URL
// quality suggestions

Dependencies

12 runtime dependencies, 1 flagged: puppeteer-core

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

29/29 tools missing one or more hints — screenshot (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); pdf (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); pdf2docx (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +26 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.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — ssl (line 424: spawn('openssl', args, { timeout }))

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool inputs are validated

Only 0/29 tool handlers declare input schemas (0%)

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

Tests exist

No test files found

Add tests that exercise each declared tool.

Tool description accuracy

ssl: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.

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/san-npm/mcp-services?variant=verified)](https://m8ven.ai/mcp/san-npm/mcp-services)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 49069264b541fa8ccceede03fd55c040018af82c
code hash: 4d46b19f8fd78cbce384449d2ffb30d3546d81764f0da6cf4504363e6d93c3af
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