bridge-watch on-chain intelligence MCP server
top.agentsapi/bridge-watchagentsapi.topstreamable-httpv0.3.1Scanned
Base on-chain address labels (eth-labels 104k category tags), tx explainer, clusters, CCTP USDC.
7 tools: 3 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 4
- Can send data out · 0
- 1 finding
The remote endpoint did not answer the last look. Remote posture
Anlyon alternative
3 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the bridge-watch on-chain intelligence MCP server can do
The bridge-watch on-chain intelligence MCP server is published by agentsapi.top, a domain the MCP Registry verified. It has 7 tools. It can create or change data (3 tools: detect_cluster, alert_stats and track_cctp), but cannot delete data. 4 tools only read.
4 tools bring in text other people can write (explain_transaction, detect_cluster, track_cctp and 1 more).
The fixed checks matched 1 finding (base64-blob). Each one comes with the text it matched.
Last scanned Nov 4, 2026, version 0.3.1.
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.
7 tools
Changes things 3Claude Code: ask
alert_statsAlert statistics overview: totals, breakdown by kind / severity / address, and the latest alert 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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Alert statistics overview: totals, breakdown by kind / severity / address, and the latest alert time.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
detect_clusterDetect the set of addresses funded by a single funder (shared funding-source cluster).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 Detect the set of addresses funded by a single funder (shared funding-source cluster). Useful for sybil / entity detection.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
track_cctpCCTP cross-chain transfer tracking: given a source-chain tx hash, find which transfer it belongs to, how much moved, the destination chain, and whether it arrived.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 CCTP cross-chain transfer tracking: given a source-chain tx hash, find which transfer it belongs to, how much moved, the destination chain, and whether it arrived. Supports Base → Ethereum and other CCTP chains.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
Only reads 4Show 4 read-only tools
explain_transactionExplain what a transaction did: status, sender/receiver (with identity labels), transfer details, and whether it looks like a cross-chain bridge operation.Reads text others writeNo findings
Why it is in this group
- The name "explain_transaction" says "explain": 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 Explain what a transaction did: status, sender/receiver (with identity labels), transfer details, and whether it looks like a cross-chain bridge operation.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
get_labelLook up the identity label of an EVM address (Base, open eth-labels dataset; mostly category tags rather than named entities).1 finding
Why it is in this group
- The name "get_label" says "get": a word for reading.
Findings
- Warn
The input schema at properties.address.description contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.address.description: "...ract on Base), e.g. 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913"
Description, as the server wrote it Look up the identity label of an EVM address (Base, open eth-labels dataset; mostly category tags rather than named entities). Returns which entity the address belongs to; unlabelled addresses return null. Call with no arguments for a free demo result.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_paid_endpointsList every paid HTTP endpoint of this service with its live per-call price in USDC on Base.Reads text others writeNo findings
Why it is in this group
- The name "list_paid_endpoints" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "list" and "http": it reads web pages, which anyone can write.
Description, as the server wrote it List every paid HTTP endpoint of this service with its live per-call price in USDC on Base. Takes no arguments. Call this first to discover what you can buy and what it costs.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
query_alertsQuery historical alert records; filterable by address, rule kind, severity, and time range.No findings
Why it is in this group
- The name "query_alerts" says "query": a word for reading.
Description, as the server wrote it Query historical alert records; filterable by address, rule kind, severity, and time range.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
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 or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- 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, 19:19 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- no
- HTTP status of an anonymous initialize
- not observed
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- 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
The probe stopped: The operation was aborted due to timeout
Posture changes
- Nov 13, 2026
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 3 to 0
- Protocol version: 2025-06-18 to none
Findings
Matches of fixed checks, with the text they matched.
- Warnget_label
The input schema at properties.address.description contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.address.description: "...ract on Base), e.g. 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913"
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 2 more).View diff
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 3 to 0
- Protocol version: 2025-06-18 to none
Install
Pinned to version 0.3.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http bridge-watch https://agentsapi.top/mcpclaude mcp add --transport http bridge-watch https://agentsapi.top/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__bridge-watch__get_label",
"mcp__bridge-watch__explain_transaction",
"mcp__bridge-watch__query_alerts",
"mcp__bridge-watch__list_paid_endpoints"
],
"ask": [
"mcp__bridge-watch__detect_cluster",
"mcp__bridge-watch__alert_stats",
"mcp__bridge-watch__track_cctp"
],
"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 bridge-watch. Review it before you use it.
Capability tags behind 4 rules
- mcp__bridge-watch__explain_transaction untrusted-input
- mcp__bridge-watch__detect_cluster untrusted-input
- mcp__bridge-watch__track_cctp untrusted-input
- mcp__bridge-watch__list_paid_endpoints untrusted-input
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/top.agentsapi/bridge-watch/verify?hash=beb00800921021ec552e640250c6170b8d30843f91d62ef22d3166d5f39d7387" | jq -e '.changed == false'Pinned hash beb008009210, from Nov 4, 2026, 16:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/top.agentsapi/bridge-watch/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/top.agentsapi/bridge-watch)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:55 UTC.
bridge-watch on-chain intelligence MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the bridge-watch on-chain intelligence MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 3 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the bridge-watch on-chain intelligence MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the bridge-watch on-chain intelligence 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 bridge-watch on-chain intelligence MCP server have?
- 7 tools: 3 write, 4 read. detect_cluster, alert_stats, track_cctp, get_label, explain_transaction, query_alerts and list_paid_endpoints.
Does the bridge-watch on-chain intelligence MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the bridge-watch on-chain intelligence MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the bridge-watch on-chain intelligence MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 4, 2026.