bridge-watch on-chain intelligence MCP server
online · 100% uptimetop.agentsapi/bridge-watch·v0.3.1Base on-chain address labels (eth-labels 104k category tags), tx explainer, clusters, CCTP USDC.
0 stars365 downloads/wk
Reviews
Write oneNobody has reviewed bridge-watch on-chain intelligence yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
bridge-watch on-chain intelligence tools (7)
write = sends, deletes, buys or postsalert_statsFreeAlert statistics overview: totals, breakdown by kind / severity / address, and the latest alert time.
detect_clusterFreeDetect the set of addresses funded by a single funder (shared funding-source cluster). Useful for sybil / entity detection.
explain_transactionFreeExplain what a transaction did: status, sender/receiver (with identity labels), transfer details, and whether it looks like a cross-chain bridge operation.
get_labelFreeLook 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.
list_paid_endpointsFreeList 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.
query_alertsFreeQuery historical alert records; filterable by address, rule kind, severity, and time range.
track_cctpFreeCCTP 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.
Public scan report
scanner v0.1.10 · 2026-10-13 · same rubric, same numbers if you re-run it
- Code scan3 source files scanned25/25
- Live reliabilityremote reachable in 3805ms17/20
- Tool poisoning7 tool descriptions checked15/15
- Auth qualityopen endpoint, read-only tools10/15
- Maintenancelast push 1 days ago15/15
- Maintainer identityendpoint served from the registry-verified namespace domain8/10
How bridge-watch on-chain intelligence compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 90/100
- higher than 83% of 48,255 servers
- Tools
- 7
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Uptime
- 100%
- of our recent checks; the typical remote server answers 100%
- Response time
- 2,527 ms
- faster than 4% of 30,031 servers
- Downloads a week
- 365
- more than 84% of 12,191 servers with a package
What its tools let an agent do: 7 read
Release history: 2 versions in the registry since 2026-10-08, latest 2026-10-11, typically one every 3 days.
Install bridge-watch on-chain intelligence in Claude Code, Cursor or VS Code
claude mcp add --transport http bridge-watch https://agentsapi.top/mcp
What the publisher says
From the bridge-watch on-chain intelligence repository's README, as published. We do not edit it. Read it on GitHub
bridge-watch-mcp
Zero-dependency MCP stdio bridge for the Bridge Watch server: 104,209 on-chain address labels (Base / Ethereum), funding-cluster and CCTP tracing, transaction explanation, plus 7 metered tools paid per call over x402 in USDC on Base.
Node >= 18. No dependencies, no build step, ~10 KB.
Install / run
npx -y bridge-watch-mcp --tools # print the live tool list (server reachability check)
npx -y bridge-watch-mcp # run the stdio bridge (this is what MCP clients call)MCP client config (Claude Desktop, Cursor, Windsurf, Cline, ...):
{
"mcpServers": {
"bridge-watch": {
"command": "npx",
"args": ["-y", "bridge-watch-mcp"]
}
}
}Free tier
Every IP gets 3 free tool calls per day, no key and no wallet required. getlabel accepts no arguments** and returns a real demo result, so a fresh client can see working data on the very first call:
{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_label","arguments":{}}}Paying
- Send USDC (Base) to 0x381cdbb664608bf7b1dd4f9403a572c1c57332c2.
- Reuse that same address as the credential:
BRIDGE_WATCH_BEARER=0xYourPayerAddress npx -y bridge-watch-mcpLive per-call prices are published by the server itself — ask the model to call listpaidendpoints, or read https://agentsapi.top/.well-known/x402. Prices are never hardcoded in this package.
Environment
How it works
Reads newline-delimited JSON-RPC on stdin, POSTs each message to the remote Streamable HTTP endpoint, and writes back the (SSE-unwrapped) JSON-RPC responses. Notifications (202 Accepted) produce no output. Nothing is logged, nothing is persisted, and the process exits as soon as stdin closes and every in-flight request is answered.
Remote-first alternative
You do not need this package if your client speaks HTTP: point it at https://agentsapi.top/mcp directly.
License
MIT
Nothing above is checked by us. What we check is on the safety report.
bridge-watch on-chain intelligence: common questions
- Is bridge-watch on-chain intelligence MCP server safe?
- Yes, by our scan: it is graded A (90/100). Read the bridge-watch on-chain intelligence safety report
- How do I install bridge-watch on-chain intelligence?
- It runs remotely at agentsapi.top. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does bridge-watch on-chain intelligence need an API key?
- No secret keys are declared. It reads 2 settings from the environment.
- Is bridge-watch on-chain intelligence maintained?
- The last commit was 24 days ago (2026-10-11). The latest release is v0.3.1.
- Is bridge-watch on-chain intelligence up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- How does bridge-watch on-chain intelligence compare with other MCP servers?
- safety score 90/100 (higher than 83% of 48,255 servers); tools 7 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.