bsv.cx MCP server
cx.bsv/bsv-cxbsv.cxstreamable-httpv0.1.1Scanned
Timestamp & verify evidence on-chain, free. Proofpack: a portable BEEF+BUMP proof bundle per txid.
9 tools: 1 can delete or cancel things, 5 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- 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 bsv.cx MCP server can do
The bsv.cx MCP server is published by bsv.cx, a domain the MCP Registry verified. It has 9 tools. It can delete or cancel things (1 tool: archive_url) and create or change data (5 tools: notarize_hash, verify_hash, spv_verify, proofpack and 1 more). 3 tools only read.
2 tools bring in text other people can write (get_archive and verifiable_fetch); 1 tool can send data out of your system (verifiable_fetch).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 14, 2026, version 0.1.1.
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.
9 tools
Deletes or cancels 1Claude Code: deny
archive_urlCapture a web page as it looks right now — screenshot and text — and anchor a hash of that capture on-chain.No findings
Why it is in this group
- The name "archive_url" says "archive": a word for removing or ending something.
Description, as the server wrote it Capture a web page as it looks right now — screenshot and text — and anchor a hash of that capture on-chain. Use this before relying on a page you cite, so a later edit or deletion cannot be denied. Free.
Changes things 5Claude Code: ask
batch_timestampAnchor a Merkle root over many sha256 digests in a single transaction — far cheaper per item than notarizing each one.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Anchor a Merkle root over many sha256 digests in a single transaction — far cheaper per item than notarizing each one. Each hash gets an inclusion proof. Priced per call (pay over HTTP with an x402 payment — see /pay).
notarize_hashAnchor a sha256 digest in a Bitcoin SV transaction, proving the content existed at this time.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Anchor a sha256 digest in a Bitcoin SV transaction, proving the content existed at this time. Send ONLY the hash — the content never leaves your machine, and bsv.cx cannot see what was hashed. Free. Idempotent: the same hash returns the same record.
proofpackFor any CONFIRMED BSV transaction id, get a freshly SPV-verified bundle: BEEF (BRC-62) and BUMP (BRC-74) plus bsv.cx's own self-synced header-tip attestation.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it For any CONFIRMED BSV transaction id, get a freshly SPV-verified bundle: BEEF (BRC-62) and BUMP (BRC-74) plus bsv.cx's own self-synced header-tip attestation. bsv.cx fetches the Merkle proof and folds it against block headers it syncs over the BSV P2P network BEFORE serving, so you receive a bundle that already confirms — verifiable by any @bsv/sdk client with no bsv.cx-specific code. Verification itself is free at /spv/verify; this does the fetch + fold + package for you and is priced per call (pay over HTTP with an x402 payment — see /pay).
spv_verifyVerify ANY Bitcoin (BSV) Merkle inclusion proof — a BEEF envelope (BRC-62), a BUMP (BRC-74), or a raw TSC proof — against block headers bsv.cx syncs itself over the BSV P2P network…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Verify ANY Bitcoin (BSV) Merkle inclusion proof — a BEEF envelope (BRC-62), a BUMP (BRC-74), or a raw TSC proof — against block headers bsv.cx syncs itself over the BSV P2P network, NOT an explorer. Returns confirmed / rejected / inconclusive. This is the trustless core: you send only the proof (never the root), we fold the root ourselves and check it against a header we hold — so you never have to trust bsv.cx. Works for ANY txid's proof, not just bsv.cx's own anchors. Free.
verify_hashLook up a sha256 across EVERY bsv.cx protocol — notary timestamps, verifiable-fetch receipts, notarized captures, web-page archives, Merkle batch roots and attestations — and retur…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Look up a sha256 across EVERY bsv.cx protocol — notary timestamps, verifiable-fetch receipts, notarized captures, web-page archives, Merkle batch roots and attestations — and return when it was anchored and the transaction that proves it. A hash anchored by any of these counts as found. Free, and never rate-limited into unavailability.
Only reads 3Show 3 read-only tools
get_archiveFetch the manifest for a previous archive_url capture: when it was taken, and its proof.Reads text others writeNo findings
Why it is in this group
- The name "get_archive" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Fetch the manifest for a previous archive_url capture: when it was taken, and its proof. Free.
service_statusReport whether anchoring is currently working.No findings
Why it is in this group
- The name "service_status" says "status": a word for reading.
Description, as the server wrote it Report whether anchoring is currently working. Call this if a tool reports something stored but not anchored.
verifiable_fetchFetch a URL as readable text AND get a receipt anchoring a hash of the exact bytes returned, so you can later prove what the page said when you read it.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "verifiable_fetch" says "fetch": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Fetch a URL as readable text AND get a receipt anchoring a hash of the exact bytes returned, so you can later prove what the page said when you read it. Priced per call (pay over HTTP with an x402 payment — see /pay).
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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
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 20, 2026, 18:51 UTC, unchanged since Oct 22, 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
- 6
- Protocol version
- 2025-06-18
- 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (1 destructive, 5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://bsv.cx/mcp: tools/list returned 9 tools to an anonymous client, including archive_url (destructive), notarize_hash (write), verify_hash (write), spv_verify (write), proofpack (write) and 1 more
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
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 0.1.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http bsv-cx https://bsv.cx/mcpclaude mcp add --transport http bsv-cx https://bsv.cx/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__bsv-cx__get_archive",
"mcp__bsv-cx__service_status"
],
"ask": [
"mcp__bsv-cx__notarize_hash",
"mcp__bsv-cx__verify_hash",
"mcp__bsv-cx__spv_verify",
"mcp__bsv-cx__proofpack",
"mcp__bsv-cx__verifiable_fetch",
"mcp__bsv-cx__batch_timestamp"
],
"deny": [
"mcp__bsv-cx__archive_url"
]
}
}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 bsv-cx. Review it before you use it.
Capability tags behind 2 rules
- mcp__bsv-cx__get_archive untrusted-input
- mcp__bsv-cx__verifiable_fetch 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/cx.bsv/bsv-cx/verify?hash=978952484ff1d517d0d0f082570051cd0df09509aa2a89a70324ce9481e79567" | jq -e '.changed == false'Pinned hash 978952484ff1, from Nov 14, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/cx.bsv/bsv-cx/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/cx.bsv/bsv-cx)Source: MCP Registry. Synced Oct 21, 2026, 18:11 UTC.
bsv.cx MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the bsv.cx MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 6 of which can change, send or delete something, and 0 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 bsv.cx MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: archive_url.
Can the bsv.cx 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 bsv.cx MCP server have?
- 9 tools: 1 destructive, 5 write, 3 read. archive_url, notarize_hash, verify_hash, spv_verify, proofpack, batch_timestamp, get_archive, verifiable_fetch and 1 more.
Does the bsv.cx MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the bsv.cx 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): verifiable_fetch.
Has the bsv.cx MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 14, 2026.