YouTube & Shorts Transcript Scraper — SRT, VTT & Viral Hooks MCP server
io.github.ceadigital/youtube-transcript-scraperceadigitalstreamable-httpv1.0.0Scanned
Extract YouTube & Shorts transcripts, .srt/.vtt subtitles, timecoded segments & hooks in <2s.
28 tools: 17 change things and 11 only read.
- Reads private data · 4
- Reads text others write · 28
- Can send data out · 1
- 4 findings
Tools listed without sign-in. Remote posture
With Anlyon
17 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the YouTube & Shorts Transcript Scraper — SRT, VTT & Viral Hooks MCP server can do
The YouTube & Shorts Transcript Scraper — SRT, VTT & Viral Hooks MCP server is published by the GitHub account ceadigital. It has 28 tools. It can create or change data (17 tools: github_repo_pulse, security_cve_audit, package_health_pulse, fdic_bank_health and 13 more), but cannot delete data. 11 tools only read.
4 tools read private data (vault_knowledge_search, cfpb_complaints, depsdev_openssf_scorecard and 1 more); 28 tools bring in text other people can write (gcp_catalog_search, vault_knowledge_search, sec_edgar_cik_lookup and 25 more); 1 tool can send data out of your system (agent_url_to_clean_markdown). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 4 findings (base64-blob and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 10, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
28 tools
Changes things 17Claude Code: ask
agent_base_tx_simulateHigh-velocity Agent Operational Primitive ($0.005 USDC on Base): Pre-execution Base L2 (eip155:8453) calldata simulator & wallet drain guard via eth_call + eth_estimateGas + unlimi…Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The input schema at properties.from_address.default contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.from_address.default: "0x134b5D5BeC05aD5Df49e8aC9b830553581DaD378"
Description, as the server wrote it High-velocity Agent Operational Primitive ($0.005 USDC on Base): Pre-execution Base L2 (eip155:8453) calldata simulator & wallet drain guard via eth_call + eth_estimateGas + unlimited ERC-20 approve detection.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
agent_clean_web_groundingHigh-velocity Agent Operational Primitive ($0.008 USDC on Base): Fast, token-optimized real-time web grounding & clean Markdown synthesis stripped of HTML bloat, ads, and scripts f…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it High-velocity Agent Operational Primitive ($0.008 USDC on Base): Fast, token-optimized real-time web grounding & clean Markdown synthesis stripped of HTML bloat, ads, and scripts for LLM context windows.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
agent_compliance_notary_attestTamper-evident SHA-256 hash-chained Agent Decision & Compliance Notary for EU AI Act, NIST AI RMF, and SOC2 autonomous agent audit trails.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Tamper-evident SHA-256 hash-chained Agent Decision & Compliance Notary for EU AI Act, NIST AI RMF, and SOC2 autonomous agent audit trails.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
agent_token_intel_and_honeypotHigh-velocity Agent Operational Primitive ($0.005 USDC on Base): Real-time DEX pool liquidity, 24h volume, buy/sell execution symmetry, Base bytecode check, and deterministic 0-100…Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The input schema at properties.token_address.description contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.token_address.description: "...tract address (e.g. 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913)"
Description, as the server wrote it High-velocity Agent Operational Primitive ($0.005 USDC on Base): Real-time DEX pool liquidity, 24h volume, buy/sell execution symmetry, Base bytecode check, and deterministic 0-100 Honeypot & Anti-Rug Safety Score.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
agent_url_to_clean_markdownHigh-velocity Agent Operational Primitive ($0.005 USDC on Base): Live URL-to-Clean-Markdown extractor competing with Firecrawl/Jina.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it High-velocity Agent Operational Primitive ($0.005 USDC on Base): Live URL-to-Clean-Markdown extractor competing with Firecrawl/Jina. Fetches any public URL via SSRF-safe HTTP + LegalTDMGuard and returns clean, prompt-injection-scrubbed Markdown.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
corporate_kyb_and_risk_dossier5-Source Parallel Composite Dossier: Joins GLEIF LEI + SEC EDGAR + CFPB Complaints + USASpending Federal Awards + FDIC in <400ms with a 0-100 Counterparty Verification Score.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 5-Source Parallel Composite Dossier: Joins GLEIF LEI + SEC EDGAR + CFPB Complaints + USASpending Federal Awards + FDIC in <400ms with a 0-100 Counterparty Verification Score.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
cyber_supply_chain_security_dossier5-Source Parallel Security Dossier: Joins crt.sh SSL Certs + Google deps.dev OpenSSF Scorecard + FIRST.org EPSS + CISA KEV + OSV.dev CVEs in <400ms with a 0-100 Security Posture Sc…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 5-Source Parallel Security Dossier: Joins crt.sh SSL Certs + Google deps.dev OpenSSF Scorecard + FIRST.org EPSS + CISA KEV + OSV.dev CVEs in <400ms with a 0-100 Security Posture Score.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
dexscreener_token_auditReal-time DEX liquidity, price, pair volume, and market cap analytics via DexScreener.Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The input schema at properties.token_address.description contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.token_address.description: "...token address (e.g. 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913)"
Description, as the server wrote it Real-time DEX liquidity, price, pair volume, and market cap analytics via DexScreener.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
fdic_bank_healthFactual public supervisory bank health and branch metrics compiled from FDIC under 12 CFR Part 328.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Factual public supervisory bank health and branch metrics compiled from FDIC under 12 CFR Part 328.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
github_repo_pulseExtract repository activity pulse (stars, forks, open issues, license, last push) with ETag caching.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Extract repository activity pulse (stars, forks, open issues, license, last push) with ETag caching.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
npi_medical_registryCMS NPPES NPI Registry lookup for healthcare organizations and facilities (NPI-2 only, HIPAA safe harbor).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it CMS NPPES NPI Registry lookup for healthcare organizations and facilities (NPI-2 only, HIPAA safe harbor).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
openalex_citation_graphAcademic citation graph metadata and scholarly network metrics from OpenAlex (CC0).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Academic citation graph metadata and scholarly network metrics from OpenAlex (CC0).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
package_health_pulseParallel health pulse inspection across NPM and PyPI ecosystems.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Parallel health pulse inspection across NPM and PyPI ecosystems.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
provision_free_developer_keyFREE Self-Serve API Key Generator: Instantly mints a 50-call free starter `cea_live_` Bearer token with copy-paste snippets for Claude Desktop, Cursor, Windsurf, ElizaOS, and Coinb…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it FREE Self-Serve API Key Generator: Instantly mints a 50-call free starter `cea_live_` Bearer token with copy-paste snippets for Claude Desktop, Cursor, Windsurf, ElizaOS, and Coinbase AgentKit.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
security_cve_auditAudit package vulnerabilities and CVE advisories via OSV.dev database.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Audit package vulnerabilities and CVE advisories via OSV.dev database.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
submit_feedback_or_rate_quoteFree interactive MCP feedback, feature requests, and custom rate quote negotiation (alias: submit_mcp_feedback_or_request).Reads text others write1 finding
Why it is in this group
- The name "submit_feedback_or_rate_quote" says "submit": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "submit_feedback_or_rate_quote" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "submit_feedback_or_rate_quote" says "submit": a word for a change.
Description, as the server wrote it Free interactive MCP feedback, feature requests, and custom rate quote negotiation (alias: submit_mcp_feedback_or_request).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
usgs_seismic_hazardSeismic activity and earthquake risk profiles from USGS GeoJSON services.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Seismic activity and earthquake risk profiles from USGS GeoJSON services.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
Only reads 11Show 11 read-only tools
cfpb_complaintsQuery US Consumer Financial Protection Bureau (CFPB) complaint database (17 U.S.C.Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "query": a word for reading.
What it can reach
- private-dataThe description's first sentence says "query" and "database": it reads databases.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Query US Consumer Financial Protection Bureau (CFPB) complaint database (17 U.S.C. § 105 public domain).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
cisa_kev_exploited_vulnsQuery US CISA Known Exploited Vulnerabilities (KEV) Catalog for active in-the-wild exploitation, mandatory federal patch due dates, and ransomware usage.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "query": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Query US CISA Known Exploited Vulnerabilities (KEV) Catalog for active in-the-wild exploitation, mandatory federal patch due dates, and ransomware usage.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
crtsh_cert_reconQuery Sectigo Certificate Transparency logs (crt.sh) for issued SSL/TLS certificates and subdomains.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "query": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Query Sectigo Certificate Transparency logs (crt.sh) for issued SSL/TLS certificates and subdomains.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
depsdev_openssf_scorecardQuery Google Open Source Insights (deps.dev) and Linux Foundation OpenSSF Security Scorecard (0-10) for any GitHub repository or package (#1 in MCP Registry).Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "query": a word for reading.
What it can reach
- private-dataThe description's first sentence says "query" and "repository": it reads repositories.
- private-dataThe input names a repo (input.github_repo), and the tool reads: it reads repositories.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Query Google Open Source Insights (deps.dev) and Linux Foundation OpenSSF Security Scorecard (0-10) for any GitHub repository or package (#1 in MCP Registry).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
epss_exploit_scoreQuery FIRST.org Exploit Prediction Scoring System (EPSS) for 30-day real-world exploit probability.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "query": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Query FIRST.org Exploit Prediction Scoring System (EPSS) for 30-day real-world exploit probability.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
gcp_catalog_searchSub-millisecond FTS5 search across 17,671 Google Cloud, Vertex AI, and A2A service records.Reads text others writeNo findings
Why it is in this group
- The name "gcp_catalog_search" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Sub-millisecond FTS5 search across 17,671 Google Cloud, Vertex AI, and A2A service records.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
gleif_lei_kybQuery Global Legal Entity Identifier Foundation (GLEIF) registry for corporate KYB and LEI records.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "query": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Query Global Legal Entity Identifier Foundation (GLEIF) registry for corporate KYB and LEI records.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
nyfed_sofr_reference_ratesQuery Federal Reserve Bank of New York official Secured Overnight Financing Rate (SOFR) benchmark rates, percentiles, and daily repo volume (#1 in MCP Registry).Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "query": a word for reading.
What it can reach
- private-dataThe description's first sentence says "query" and "repo": it reads repositories.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Query Federal Reserve Bank of New York official Secured Overnight Financing Rate (SOFR) benchmark rates, percentiles, and daily repo volume (#1 in MCP Registry).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
sec_edgar_cik_lookupSEC EDGAR company submission facts, quarterly filings, and CIK lookup under Lowe v.Reads text others writeNo findings
Why it is in this group
- The name "sec_edgar_cik_lookup" says "lookup": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it SEC EDGAR company submission facts, quarterly filings, and CIK lookup under Lowe v. SEC Publisher's Exclusion.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
usaspending_awardsQuery USASpending.gov Federal Awards and Contractor Intelligence (17 U.S.C.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "query": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Query USASpending.gov Federal Awards and Contractor Intelligence (17 U.S.C. § 105 public domain).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
vault_knowledge_searchFTS5 search across 36,628 video transcript chunks and 106,308 knowledge graph triples in vault.db.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "vault_knowledge_search" says "search": a word for reading.
What it can reach
- private-dataThe name "vault_knowledge_search" says "search" and "vault": it reads secrets.
- private-dataThe description's first sentence says "vault": it reads secrets.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it FTS5 search across 36,628 video transcript chunks and 106,308 knowledge graph triples in vault.db.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
112 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data4
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write28
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- agent_base_tx_simulate
- agent_clean_web_grounding
- agent_compliance_notary_attest
- agent_token_intel_and_honeypot
- agent_url_to_clean_markdown
- cfpb_complaints
- cisa_kev_exploited_vulns
- corporate_kyb_and_risk_dossier
- crtsh_cert_recon
- cyber_supply_chain_security_dossier
- depsdev_openssf_scorecard
- dexscreener_token_audit
- and 16 more
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__youtube-transcript-scraper__agent_url_to_clean_markdown"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 18, 2026, 16:24 UTC, unchanged since Nov 11, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 17
- Protocol version
- 2025-03-26
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 17 tools that change things (17 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://ceadigital.io/mcp: tools/list returned 28 tools to an anonymous client, including github_repo_pulse (write), security_cve_audit (write), package_health_pulse (write), fdic_bank_health (write), openalex_citation_graph (write) and 12 more
Findings
Matches of fixed checks, with the text they matched.
The input schema at properties.token_address.description contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.token_address.description: "...token address (e.g. 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913)"
The server marks "submit_feedback_or_rate_quote" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "submit_feedback_or_rate_quote" says "submit": a word for a change.
The input schema at properties.token_address.description contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.token_address.description: "...tract address (e.g. 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913)"
The input schema at properties.from_address.default contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.from_address.default: "0x134b5D5BeC05aD5Df49e8aC9b830553581DaD378"
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http youtube-transcript-scraper https://ceadigital.io/mcpclaude mcp add --transport http youtube-transcript-scraper https://ceadigital.io/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__youtube-transcript-scraper__gcp_catalog_search",
"mcp__youtube-transcript-scraper__vault_knowledge_search",
"mcp__youtube-transcript-scraper__sec_edgar_cik_lookup",
"mcp__youtube-transcript-scraper__crtsh_cert_recon",
"mcp__youtube-transcript-scraper__epss_exploit_score",
"mcp__youtube-transcript-scraper__gleif_lei_kyb",
"mcp__youtube-transcript-scraper__cfpb_complaints",
"mcp__youtube-transcript-scraper__usaspending_awards",
"mcp__youtube-transcript-scraper__depsdev_openssf_scorecard",
"mcp__youtube-transcript-scraper__nyfed_sofr_reference_rates",
"mcp__youtube-transcript-scraper__cisa_kev_exploited_vulns"
],
"ask": [
"mcp__youtube-transcript-scraper__github_repo_pulse",
"mcp__youtube-transcript-scraper__security_cve_audit",
"mcp__youtube-transcript-scraper__package_health_pulse",
"mcp__youtube-transcript-scraper__fdic_bank_health",
"mcp__youtube-transcript-scraper__openalex_citation_graph",
"mcp__youtube-transcript-scraper__usgs_seismic_hazard",
"mcp__youtube-transcript-scraper__dexscreener_token_audit",
"mcp__youtube-transcript-scraper__npi_medical_registry",
"mcp__youtube-transcript-scraper__corporate_kyb_and_risk_dossier",
"mcp__youtube-transcript-scraper__cyber_supply_chain_security_dossier",
"mcp__youtube-transcript-scraper__agent_compliance_notary_attest",
"mcp__youtube-transcript-scraper__submit_feedback_or_rate_quote",
"mcp__youtube-transcript-scraper__agent_token_intel_and_honeypot",
"mcp__youtube-transcript-scraper__agent_clean_web_grounding",
"mcp__youtube-transcript-scraper__agent_base_tx_simulate",
"mcp__youtube-transcript-scraper__provision_free_developer_key",
"mcp__youtube-transcript-scraper__agent_url_to_clean_markdown"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as youtube-transcript-scraper. Review it before you use it.
Capability tags behind 28 rules
- mcp__youtube-transcript-scraper__gcp_catalog_search untrusted-input
- mcp__youtube-transcript-scraper__vault_knowledge_search private-data, untrusted-input
- mcp__youtube-transcript-scraper__sec_edgar_cik_lookup untrusted-input
- mcp__youtube-transcript-scraper__github_repo_pulse untrusted-input
- mcp__youtube-transcript-scraper__security_cve_audit untrusted-input
- mcp__youtube-transcript-scraper__package_health_pulse untrusted-input
- mcp__youtube-transcript-scraper__fdic_bank_health untrusted-input
- mcp__youtube-transcript-scraper__openalex_citation_graph untrusted-input
- mcp__youtube-transcript-scraper__usgs_seismic_hazard untrusted-input
- mcp__youtube-transcript-scraper__dexscreener_token_audit untrusted-input
- mcp__youtube-transcript-scraper__npi_medical_registry untrusted-input
- mcp__youtube-transcript-scraper__crtsh_cert_recon untrusted-input
- mcp__youtube-transcript-scraper__epss_exploit_score untrusted-input
- mcp__youtube-transcript-scraper__gleif_lei_kyb untrusted-input
- mcp__youtube-transcript-scraper__cfpb_complaints private-data, untrusted-input
- mcp__youtube-transcript-scraper__usaspending_awards untrusted-input
- mcp__youtube-transcript-scraper__depsdev_openssf_scorecard private-data, untrusted-input
- mcp__youtube-transcript-scraper__nyfed_sofr_reference_rates private-data, untrusted-input
- mcp__youtube-transcript-scraper__cisa_kev_exploited_vulns untrusted-input
- mcp__youtube-transcript-scraper__corporate_kyb_and_risk_dossier untrusted-input
- mcp__youtube-transcript-scraper__cyber_supply_chain_security_dossier untrusted-input
- mcp__youtube-transcript-scraper__agent_compliance_notary_attest untrusted-input
- mcp__youtube-transcript-scraper__submit_feedback_or_rate_quote untrusted-input
- mcp__youtube-transcript-scraper__agent_token_intel_and_honeypot untrusted-input
- mcp__youtube-transcript-scraper__agent_clean_web_grounding untrusted-input
- mcp__youtube-transcript-scraper__agent_base_tx_simulate untrusted-input
- mcp__youtube-transcript-scraper__provision_free_developer_key untrusted-input
- mcp__youtube-transcript-scraper__agent_url_to_clean_markdown untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.ceadigital/youtube-transcript-scraper/verify?hash=8ee17c52ffbafd4b6c300058cb24fb290aeb540e7b6a608b953a9c786a96c1a1" | jq -e '.changed == false'Pinned hash 8ee17c52ffba, from Nov 10, 2026, 18:19 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.ceadigital/youtube-transcript-scraper/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.ceadigital/youtube-transcript-scraper)Source: MCP Registry. Synced Nov 10, 2026, 18:18 UTC.
YouTube & Shorts Transcript Scraper — SRT, VTT & Viral Hooks MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the YouTube & Shorts Transcript Scraper — SRT, VTT & Viral Hooks MCP server safe?
- No scan can promise that. What its definitions show: 28 tools, 17 of which can change, send or delete something, and 4 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the YouTube & Shorts Transcript Scraper — SRT, VTT & Viral Hooks MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the YouTube & Shorts Transcript Scraper — SRT, VTT & Viral Hooks MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the YouTube & Shorts Transcript Scraper — SRT, VTT & Viral Hooks MCP server have?
- 28 tools: 17 write, 11 read. github_repo_pulse, security_cve_audit, package_health_pulse, fdic_bank_health, openalex_citation_graph, usgs_seismic_hazard, dexscreener_token_audit, npi_medical_registry and 20 more.
Does the YouTube & Shorts Transcript Scraper — SRT, VTT & Viral Hooks MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the YouTube & Shorts Transcript Scraper — SRT, VTT & Viral Hooks MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): agent_url_to_clean_markdown.
Has the YouTube & Shorts Transcript Scraper — SRT, VTT & Viral Hooks MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.