Lookup MCP server
online · 100% uptimecom.verirouteintel/lookup·v1.2.3Is this number safe to call or text right now? Live carrier, CNAM, spam and SMS checks for agents.
0 stars33 downloads/wk
Reviews
Write oneNobody has reviewed Lookup yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Lookup tools (10, 1 write)
write = sends, deletes, buys or postsvri_account_infoFreeFree: available balance, connection limits and allowed products.
vri_bulk_lookupFreeLive lookup for up to 100 North American phone numbers in one call (carrier, line type, routing; optional cnam/spam/messaging). Each number is a fresh paid read — spend scope required. Live customer keys spend balance. Repeating a call can charge again; reuse a stable request_id with identical arguments for a safe retry. Use max_cost to cap the quote. Use a test key for integration tests.
vri_bulk_statusFreeStatus and progress of a VRI bulk lookup job by job id.
vri_job_resultsFreeFree, owner-scoped stored results. Follow next_cursor until null; never re-submit a completed job.
vri_number_lookupFreeLive intelligence for ONE North American phone number: current carrier of record, line type, LRN routing data, porting activation date, and optionally caller-ID name (cnam), spam reputation, and messaging provider. Always a fresh read of live numbering infrastructure — never cached carrier data. Live customer keys spend balance. Repeating a call can charge again; reuse a stable request_id with identical arguments for a safe retry. Use max_cost to cap the quote. Use a test key for integration tests.
vri_operation_statusFreeFree: check an operation after an interrupted call; pending work must not be resubmitted with a new ID.
vri_quoteFreeFree estimate using account pricing and deduplicated valid numbers; no lookup.
vri_sms_deliverabilityFreeLine-type-based SMS capability and reputation signals for a North American number. Not an actual delivery test or guarantee. Unknown reputation never clears a number to message. Returns sms_capable (live line-type read), VoIP flag, spam reputation, the recipient's approximate local time with an 8am-9pm calling-window flag, and plain-language reasons. Deliverability and reputation signals only — not a legal compliance determination (no DNC/reassigned-number/litigator data). Performs its own LRN and spam lookup; avoid calling after number_lookup for the same data. Live customer keys spend balance. Repeating a call can charge again; reuse a stable request_id with identical arguments for a safe retry. Use max_cost to cap the quote. Use a test key for integration tests.
vri_spam_checkFreeSpam/scam/robocall reputation for one North American phone number, with an explainable `risk` block: the verdict, a confidence band, and the individual reasons behind it (complaint volume and recency, complaint category, community reports, line type, recent porting). Live customer keys spend balance. Repeating a call can charge again; reuse a stable request_id with identical arguments for a safe retry. Use max_cost to cap the quote. Use a test key for integration tests.
vri_submit_jobwrite actionFreeSubmit an ASYNC bulk lookup job for up to 10000 North American phone numbers. Balance is reserved up front and the job runs in the background; check progress with vri_bulk_status. Requires a customer API key (jobs bill the account that owns the key). Live customer keys spend balance. Repeating a call can charge again; reuse a stable request_id with identical arguments for a safe retry. Use max_cost to cap the quote. Use a test key for integration tests.
Public scan report
scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it
- Code scan3 source files scanned25/25
- Live reliabilityremote reachable in 954ms20/20
- Tool poisoning10 tool descriptions checked15/15
- Auth qualityAPI key sent as a header8/15
- Maintenancelast push 40 days ago12/15
- Maintainer identityregistry namespace matches repository owner; website matches verified namespace9/10
How Lookup compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 89/100
- higher than 80% of 48,243 servers
- Tools
- 10
- the typical server has 7
- Tools that change things
- 10%
- 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
- 325 ms
- faster than 49% of 30,027 servers
- Downloads a week
- 33
- more than 21% of 12,306 servers with a package
What its tools let an agent do: 9 read · 1 change
Install Lookup in Claude Code, Cursor or VS Code
claude mcp add --transport http lookup https://verirouteintel.com/api/mcp
What the publisher says
From the Lookup repository's README, as published. We do not edit it. Read it on GitHub
VeriRoute Intel MCP Server
Tells your agent whether a number is safe to call or text right now. Live reads of the U.S. and Canadian phone networks — carrier of record, line type, LRN, CNAM caller ID, spam/scam reputation, SMS deliverability, and a TCPA 8 a.m.–9 p.m. calling-window verdict — plus bulk lookups. Every query gets a fresh dip, never stale cached data. Free sandbox key, no card required. Pay per lookup with no minimums.
This is a hosted (remote) MCP server — nothing to install or run.
return deterministic sample data with zero charges, perfect for wiring an agent up before funding.
- Endpoint: https://verirouteintel.com/api/mcp (Streamable HTTP, JSON-RPC 2.0)
- Auth: Authorization: Bearer
- Docs: https://verirouteintel.com/api-docs/mcp
- Get a key: https://verirouteintel.com/dashboard/api-keys — free sandbox test keys
Connect
Claude Code (CLI)
claude mcp add --transport http vri https://verirouteintel.com/api/mcp \
--header "Authorization: Bearer YOUR_API_KEY"Claude.ai / Claude Desktop
Add a custom connector with URL https://verirouteintel.com/api/mcp and header Authorization: Bearer YOURAPIKEY.
Cursor and other MCP clients (mcp.json)
{
"mcpServers": {
"vri": {
"url": "https://verirouteintel.com/api/mcp",
"headers": { "Authorization": "Bearer YOUR_API_KEY" }
}
}
}Tools
Billing
Live keys pay the same per-lookup rates as the REST API from a prepaid balance. Every result reports what it cost; failed lookups are never charged, and a call that would exceed your available balance is refused up front.
Use cases
- Clean calling lists before dialing (dead/ported/VoIP detection)
- Check your own outbound caller IDs for "Spam Likely" labeling
- Verify line type before sending SMS
- Enrich CRM records with live carrier data — from inside an agent workflow
© First Light Holdings, LLC, DBA VeriRoute Intel · Terms · Privacy
Directories
Published in the Official MCP Registry as com.verirouteintel/lookup · Smithery · MCP.so
Local stdio (CI, offline, or clients without remote MCP)
A zero-dependency Node shim, published to npm, forwards to the hosted server:
VRI_API_KEY=YOUR_API_KEY npx veriroute-intel-mcpOr in an mcp.json-style client config:
{
"mcpServers": {
"vri": {
"command": "npx",
"args": ["-y", "veriroute-intel-mcp"],
"env": { "VRI_API_KEY": "YOUR_API_KEY" }
}
}
}Discovery works without a key; tool calls need one (free sandbox test keys return sample data with zero charges). Prefer the hosted endpoint whenever your client supports remote MCP.
Nothing above is checked by us. What we check is on the safety report.
Lookup: common questions
- Is Lookup MCP server safe?
- Yes, by our scan: it is graded A (89/100). Read the Lookup safety report
- How do I install Lookup?
- It runs remotely at verirouteintel.com. 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 Lookup need an API key?
- Yes. The registry entry asks for
VRI_API_KEY,Authorization. - Is Lookup maintained?
- The last commit was 60 days ago (2026-09-06). The latest release is v1.2.3.
- Is Lookup up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- How does Lookup compare with other MCP servers?
- safety score 89/100 (higher than 80% of 48,243 servers); tools 10 (the typical server has 7); tools that change things 10% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.