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.

catchy-me

REMOTE · APP.CATCHY-ME.COM

Find B2B leads on LinkedIn that match your ICP, with verified facts and a first message for each.

65 Trust /100

Last scanned (19 hours ago)

Scores higher than 46% of remote servers

Reachable. Last reached 21 Nov 2026.

Category CRM and Sales

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability61
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 9799 tokens (~148/item across 66 items; 66 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 Management13
  • Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage86
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 57% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 67 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

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.

  • 21 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • The server changed its declared name: catchy → catchy-me security
    • Tool “accept_legal” rewrote its description, which is the text the model reads security
    • Tool “catchy_info” rewrote its description, which is the text the model reads security
    • Tool “get_account” rewrote its description, which is the text the model reads security
    • Tool “list_plans” rewrote its description, which is the text the model reads security
    • Tool “sign_in” rewrote its description, which is the text the model reads security
    • Tool “sign_up” rewrote its description, which is the text the model reads security
    • Tool “subscribe” rewrote its description, which is the text the model reads security
    • Stability: unverified → 0.03 ▲ functional
    • “confirm_sign_up” reworded the description of “lang” cosmetic
    • “request_password_reset” reworded the description of “lang” cosmetic
    • “resend_sign_up_code” reworded the description of “lang” cosmetic
    • “reset_password” reworded the description of “lang” cosmetic
    • “sign_in” reworded the description of “lang” cosmetic
    • “sign_up” reworded the description of “lang” cosmetic
    • Tool “catchy_info” changed its title: About Catchy → About catchy-me cosmetic
    • Tool “sign_up” changed its title: Create a Catchy account → Create a catchy-me account cosmetic
  • 17 Nov 26 63

    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 21 Nov 2026 · Probed https://app.catchy-me.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=app.catchy-me.com CN=YE2,O=Let's Encrypt,C=US 6 Nov 2026 4 Feb 2027 ECDSA 256 ECDSA-SHA384 6e226a72bd51aa5ac50b586e3a61b76cb63
SANs: app.catchy-me.com
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of app.catchy-me.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
catchy-me.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=(), payment=(), usb=(), browsing-topics=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://app.catchy-me.com/mcp Verified 200
http (plaintext) http://app.catchy-me.com/mcp HTTPS enforced 308 https://app.catchy-me.com/mcp
MCP tools · 66 exposed · ~8,920 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
revise_search ~187

Applies chosen proposals of diagnose_search. SPENDS CREDITS: show the price of that combination and pass it as confirm_credits after the user's yes, with the diagnosis' `version`. For a finished search whose people ran out, `more` (and stop_at_target) say how many more leads to find with the changes. [REST: POST /api/tasks/{id}/revise]

NameTypeReqDescription
acceptarrayyes–
confirm_creditsintegeryesThe price in credits the matching quote returned, shown to the user and confirmed by them.
moreinteger––
stop_at_targetboolean––
task_idstringyesThe search id (task id), e.g. from list_searches or create_search.
versioninteger–The spec version from get_search (optional: protects against an edit made meanwhile in the web).

No output schema declared.

No examples provided.

rewrite_message ~240

SPENDS CREDITS: quote_message_rewrite first, show the price, after the user's yes pass its credits, result_id and expected_revision. The new text comes in a few seconds: get_outreach_lead. [REST: POST /api/tasks/{id}/outreach/leads/{cid}/steps/{step_id}/rewrite]

NameTypeReqDescription
cidstringyesThe person's id (cid) from list_leads.
confirm_creditsintegeryesThe price in credits the matching quote returned, shown to the user and confirmed by them.
expected_revisioninteger––
generation_idstring–The outreach generation id (get_outreach campaign.generation.id); omitted: the current one.
modestringyesother_hook (another fact), shorter, warmer, rewrite (with the note).
notestring––
result_idstring––
step_idstringyesThe step id of the message (get_outreach_lead steps[].step_id).
task_idstringyesThe search id (task id), e.g. from list_searches or create_search.

No output schema declared.

No examples provided.

run_search ~201

Starts a ready search for `leads` leads. SPENDS CREDITS: first call quote_search, show the price to the user, and only after their explicit yes call this with confirm_credits = the quote's credits_high. stop_at_target (default true) stops at the number of leads. Returns at once (maybe queued); then poll get_search every 30-60 s. Needs a plan or credits on the balance. [REST: POST /api/tasks/{id}/run]

NameTypeReqDescription
confirm_creditsintegeryesThe price in credits the matching quote returned, shown to the user and confirmed by them.
leadsintegeryes–
stop_at_targetboolean––
task_idstringyesThe search id (task id), e.g. from list_searches or create_search.
versioninteger–The spec version from get_search (optional: protects against an edit made meanwhile in the web).

No output schema declared.

No examples provided.

set_outreach_essence ~145

«Суть»: offer (what we offer), ask (what we want from the person), optional tone and client_rules, and the message language. [REST: PUT /api/tasks/{id}/outreach/essence]

NameTypeReqDescription
askstringyes–
client_rulesstring––
generation_idstring–The outreach generation id (get_outreach campaign.generation.id); omitted: the current one.
languagestring––
offerstringyes–
task_idstringyesThe search id (task id), e.g. from list_searches or create_search.
tonestring––

No output schema declared.

No examples provided.

set_outreach_funnel ~163

«Аккаунты»: what the user can write from — email (bool), linkedin (none | basic | sales_navigator), threads (bool), linkedin_comments (public comments on LinkedIn posts, bool). At least one. The route of each person's messages is chosen from these. [REST: PUT /api/tasks/{id}/outreach/funnel]

NameTypeReqDescription
emailbooleanyes–
generation_idstring–The outreach generation id (get_outreach campaign.generation.id); omitted: the current one.
linkedinstringyes–
linkedin_commentsboolean––
task_idstringyesThe search id (task id), e.g. from list_searches or create_search.
threadsbooleanyes–

No output schema declared.

No examples provided.

set_outreach_sender ~153

Who writes the messages: mode=linkedin with the sender's LinkedIn link (the profile and posts are analysed, about a minute), or mode=text with a few sentences about them. The first paid setup step of a generation spends its brief. Then poll get_outreach. [REST: PUT /api/tasks/{id}/outreach/sender]

NameTypeReqDescription
generation_idstring–The outreach generation id (get_outreach campaign.generation.id); omitted: the current one.
linkedin_urlstring––
modestringyes–
task_idstringyesThe search id (task id), e.g. from list_searches or create_search.
textstring––

No output schema declared.

No examples provided.

set_search_strategy ~136

Before the run: the search method («способ поиска») — people (search people directly), companies_first (find the companies, then the people in them), via_related_people; only the options get_search detail=spec lists for this spec. The plan and the estimate are made again. [REST: POST /api/tasks/{id}/strategy]

NameTypeReqDescription
strategystringyes–
task_idstringyesThe search id (task id), e.g. from list_searches or create_search.
versioninteger–The spec version from get_search (optional: protects against an edit made meanwhile in the web).

No output schema declared.

No examples provided.

sign_in ~166

An existing catchy-me account: email and password -> an API key for this MCP server (shown once). The web's login limits apply. [REST: POST /api/auth/login]

NameTypeReqDescription
emailstringyes–
key_accessstring––
key_daysinteger|null–Lifetime of the key in days; null = no limit. Default 365.
key_namestring–Name of the API key in Settings (default «MCP agent»).
langstring–The account's language: ru, en, es (Spanish), de (German), fr (French), pt (Brazilian Portuguese) or ja (Japanese); the messages, the emails and the texts of its searches. Default en.
passwordstringyes–

No output schema declared.

No examples provided.

sign_up ~213

Registers a new catchy-me account and emails a 6-digit code to confirm it (then confirm_sign_up). Set accept_terms=true ONLY after the user has read and agreed to the Terms of Use and the Privacy Policy (their links: catchy_info terms_of_use / privacy_policy) — ask them first. Without a password one is generated and returned once: give it to the user. Returns signup_token for confirm_sign_up. [REST: POST /api/auth/register/start]

NameTypeReqDescription
accept_termsbooleanyesThe user agreed to the Terms of Use and the Privacy Policy.
emailstringyes–
invitestring–An invite code, when registration is by invitation.
langstring–The account's language: ru, en, es (Spanish), de (German), fr (French), pt (Brazilian Portuguese) or ja (Japanese); the messages, the emails and the texts of its searches. Default en.
namestringyes–
passwordstring––

No output schema declared.

No examples provided.

start_facts_on_request ~146

SPENDS CREDITS: quote_facts_on_request first, show the price to the user and after their yes pass its `credits` as confirm_credits. The work runs in the background; poll get_search / list_leads. [REST: POST /api/tasks/{id}/manual]

NameTypeReqDescription
cidsarrayyesPerson ids (cid) from list_leads.
confirm_creditsintegeryesThe price in credits the matching quote returned, shown to the user and confirmed by them.
promoteboolean––
task_idstringyesThe search id (task id), e.g. from list_searches or create_search.

No output schema declared.

No examples provided.

start_outreach ~182

SPENDS CREDITS: quote_outreach first, show the price to the user and after their yes pass its `credits` as confirm_credits. Needs the sender ready, the essence and the accounts. Runs in the background (minutes); poll get_outreach every 30-60 s. [REST: POST /api/tasks/{id}/outreach/start]

NameTypeReqDescription
cidsarrayyesFit people (cid) of the search; get_outreach lists them.
confirm_creditsintegeryesThe price in credits the matching quote returned, shown to the user and confirmed by them.
generation_idstring–The outreach generation id (get_outreach campaign.generation.id); omitted: the current one.
task_idstringyesThe search id (task id), e.g. from list_searches or create_search.

No output schema declared.

No examples provided.

subscribe ~200

Creates a LavaTop payment for a monthly plan (trial, start, growth, scale; prices in list_plans) and returns its payment_url and order id. Confirm the plan, price and currency with the user first. GIVE THE LINK TO THE USER: a person pays on LavaTop's page by card, SBP or PayPal (an agent cannot). Currency is also the method: RUB — Russian cards and SBP; USD — foreign cards, PayPal, Apple Pay (Russian cards pay only in RUB). A USD link lives 15 minutes, a RUB link 24 hours. A plan not yet sold online answers plan_unavailable: the user writes to support. Then poll get_payment_status every 15-30 s until paid; the plan's credits and briefs arrive with the payment and renew monthly until cancel_subscription. [REST: POST /api/billing/checkout]

NameTypeReqDescription
currencystring––
planstringyes–

No output schema declared.

No examples provided.

suggest_audiences ~187

Step 3 («Кому пишем»): three customer profiles (ICP) to search for, from the company and the goal; each with a short title, the profile text and why. The chosen text is the `icp` of create_search. Part of a new search's onboarding: the first assistant call of an onboarding spends one brief (a free account has one search brief and may call each assistant once); pass the returned onboarding_id to the next calls and to create_search. [REST: POST /api/assist/audiences]

NameTypeReqDescription
companystringyes–
goalstringyes–
onboarding_idstring–The onboarding id that ties the assistant calls and create_search into ONE brief. Omit it on the first call: the answer gives one; pass it to every later assistant call and to create_search of the sa…

No output schema declared.

No examples provided.

suggest_company_description ~207

Step 1 of a new search («Компания»): reads the user's company site (url) or a text about it and writes a short plain-language description of what it sells, to whom and why it matters. The user may edit it before create_search. Takes up to a minute. Part of a new search's onboarding: the first assistant call of an onboarding spends one brief (a free account has one search brief and may call each assistant once); pass the returned onboarding_id to the next calls and to create_search. [REST: POST /api/assist/company]

NameTypeReqDescription
onboarding_idstring–The onboarding id that ties the assistant calls and create_search into ONE brief. Omit it on the first call: the answer gives one; pass it to every later assistant call and to create_search of the sa…
textstring–Or: a text about the company.
urlstring–The company's site, e.g. acme.com.

No output schema declared.

No examples provided.

suggest_goals ~171

Step 2 («Цель»): four goals for the outreach to the people found (e.g. invite to a call), from the company description. The user picks or writes one. Part of a new search's onboarding: the first assistant call of an onboarding spends one brief (a free account has one search brief and may call each assistant once); pass the returned onboarding_id to the next calls and to create_search. [REST: POST /api/assist/goals]

NameTypeReqDescription
companystringyesThe company description (step 1).
onboarding_idstring–The onboarding id that ties the assistant calls and create_search into ONE brief. Omit it on the first call: the answer gives one; pass it to every later assistant call and to create_search of the sa…

No output schema declared.

No examples provided.

suggest_outreach_essence ~85

A draft of «Что предлагаем» (the offer) from the search's onboarding. Free for the user (it may spend the generation's brief). [REST: POST /api/tasks/{id}/outreach/essence/suggest]

NameTypeReqDescription
task_idstringyesThe search id (task id), e.g. from list_searches or create_search.

No output schema declared.

No examples provided.

Install

How do I install the catchy-me MCP server?

catchy-me is a hosted endpoint at https://app.catchy-me.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · app.catchy-me.com

# add to Claude Code
claude mcp add --transport http com-catchy-me-catchy-me 'https://app.catchy-me.com/mcp'
Common questions

What is the catchy-me MCP server?

catchy-me is an MCP server listed in the public MCP registry as com.catchy-me/catchy-me. Find B2B leads on LinkedIn that match your ICP, with verified facts and a first message for each. This page covers its hosted endpoint (https://app.catchy-me.com/mcp).

Is the catchy-me MCP server safe to use?

catchy-me scores 65 out of 100 on VerifyMCP. 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 catchy-me MCP server expose?

catchy-me exposes 66 tools: catchy_info, sign_up, resend_sign_up_code, confirm_sign_up, sign_in, and 61 more. Their descriptions and schemas cost roughly 8,920 tokens of context every time the server is loaded.

Does the catchy-me MCP server require authentication?

No. We connected to catchy-me without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the catchy-me MCP server still maintained?

catchy-me is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the catchy-me MCP server?

VerifyMCP ran 13 checks on catchy-me, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.