Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

CallerKit

NPM · CALLERKIT-MCP · 2 COMPONENTS

Caller ID and phone lookup: names, spam reports, fraud risk score, name/email search.

+4 this week 68 Trust /100

Last scanned (12 hours ago)

Scores higher than 38% of npm servers

Category CRM and Sales

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 94 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
  • Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 10 days ago).Pass
  • Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability70
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1018 tokens (~203/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 22 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 21 Oct 26 +3
    • Stability: unverified → 0.23 ▲ functional
  • 14 Oct 26 +31
    • Injection markers: unverified → pass ▲ security
    • First check of Judged manipulation: pass security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • Tool coverage: unverified → 100 ▲ functional
    • MCP protocol: unverified → pass ▲ functional
    • First check of Schema quality: excellent functional
    • First check of Destructive annotations: pass functional
    • First check of Schema quality: fail functional
    • First check of Tool coverage: 100 functional
    • First check of Schema quality: fail functional
  • 12 Oct 26 33

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 22 Oct 2026 · Analysed npm/callerkit-mcp@0.3.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 94 packages
Packages resolved 94
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 5 exposed · ~924 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
callerkit_assess_number_risk ~249

Fraud / lead-quality check for ONE phone number. Looks the number up and returns a 0-100 risk score, a level (low/medium/high/unknown) and the reasons. Optionally pass expected_name (e.g. the name on an order or signup) to check it against the names on record. The score is a transparent heuristic over spam reports, line type, name consistency and name match, NOT a verdict: 'unknown' means no record, which is not the same as safe. Use before shipping cash-on-delivery orders, accepting signups, or calling back a lead. Costs 1 credit when a name is found.

NameTypeReqDescription
countrystring–ISO 3166-1 alpha-2 country code, e.g. AE, SA, EG.
expected_namestring–Name the customer gave (Latin or Arabic script). Compared against the primary name and aliases on record.
phonestringyesPhone number, ideally in international E.164 format, e.g. +971501234567. Spaces and dashes are tolerated. A national number (e.g. 0501234567) also needs `country`.

No output schema declared.

No examples provided.

callerkit_bulk_lookup ~156

Look up and risk-score up to 25 phone numbers in one call (the CallerKit API itself has no bulk endpoint; this runs single lookups with limited concurrency). Returns a compact row per number (name, spam count, risk level/score). Duplicates are removed and invalid numbers are reported separately. Costs 1 credit per number with a name on record, so confirm with the user before running large lists. For deeper detail on one number call callerkit_lookup_phone.

NameTypeReqDescription
countrystring–Default ISO country for any national-format numbers in the list.
phonesarrayyesPhone numbers in E.164 format, e.g. ["+971501234567", "+201001234567"].

No output schema declared.

No examples provided.

callerkit_lookup_phone ~187

Reverse phone lookup: find the registered name, aliases (with how many people saved each one), spam report count, emails, social profiles, carrier, line type and country for ONE phone number. Strongest coverage in the Middle East and Arab countries. Costs 1 CallerKit credit when a name is found; a miss is free. Returns personal data. Use only for a legitimate, lawful purpose (identifying a caller, fraud or lead checks) and do not compile profiles of private individuals.

NameTypeReqDescription
countrystring–ISO 3166-1 alpha-2 country code, e.g. AE, SA, EG.
phonestringyesPhone number, ideally in international E.164 format, e.g. +971501234567. Spaces and dashes are tolerated. A national number (e.g. 0501234567) also needs `country`.

No output schema declared.

No examples provided.

callerkit_search_by_email ~141

Find the person or business details associated with an EMAIL address (names, phone numbers, social profiles where available). Requires a paid CallerKit plan (Pro or Custom). Costs 1 credit per result returned (at most 10). Returns personal data. Use only for a legitimate, lawful purpose (identifying a caller, fraud or lead checks) and do not compile profiles of private individuals.

NameTypeReqDescription
emailstringyesEmail address to look up.
pageinteger–Result page, starting at 1 (default 1).
per_pageinteger–Results per page (default 10). Every result returned costs a credit.

No output schema declared.

No examples provided.

callerkit_search_by_name ~191

Find phone numbers, aliases and metadata matching a person or business NAME within a country. Requires a paid CallerKit plan (Pro or Custom). Costs 1 credit per result returned; results are paged (default 10 per page). Prefer business names or a person the user already has a legitimate reason to contact. Returns personal data. Use only for a legitimate, lawful purpose (identifying a caller, fraud or lead checks) and do not compile profiles of private individuals.

NameTypeReqDescription
countrystringyesISO 3166-1 alpha-2 country code to search in, e.g. AE, SA, EG. Required.
namestringyesPerson or business name to search.
pageinteger–Result page, starting at 1 (default 1).
per_pageinteger–Results per page (default 10). Every result returned costs a credit.

No output schema declared.

No examples provided.

Install

How do I install the CallerKit MCP server?

CallerKit runs locally as an npm package, launched with npx -y callerkit-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · callerkit-mcp

# add to Claude Code
claude mcp add com-caller-kit-callerkit-mcp -- npx -y callerkit-mcp
Common questions

What is the CallerKit MCP server?

CallerKit is an MCP server listed in the public MCP registry as com.caller-kit/callerkit-mcp. Caller ID and phone lookup: names, spam reports, fraud risk score, name/email search. This page covers its npm package (callerkit-mcp).

Is the CallerKit MCP server safe to use?

CallerKit scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 October 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the CallerKit MCP server expose?

CallerKit exposes 5 tools: callerkit_lookup_phone, callerkit_assess_number_risk, callerkit_search_by_name, callerkit_search_by_email, callerkit_bulk_lookup. Their descriptions and schemas cost roughly 924 tokens of context every time the server is loaded.

Is the CallerKit MCP server still maintained?

CallerKit is still listed as active in the MCP registry. We last reached this channel on 22 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the CallerKit MCP server under?

CallerKit declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.