MCP servers › com.catchy-me › catchy-me
MCP server · registry snapshot 2026-11-17 · last tested 2026-11-17
catchy-me MCP server
Registry name com.catchy-me/catchy-me
by catchy-me.com · domain (the registry's namespace rule)Website ↗
Find B2B leads on LinkedIn that match your ICP, with verified facts and a first message for each. — the publisher's description
Summary
com.catchy-me/catchy-me is a remote MCP server listed in the official MCP registry at version 1.0.0, under the namespace of the domain catchy-me.com. On 2026-11-17 ProtocolProbe connected to it in read-only mode and read its inventory: 66 tools, 0 resources and 0 prompts.
Record checks
1 of 2 record checks met · 7 do not apply
- met: Registry entry is active and says how to run it
- not met: Source repository link opens
- not applicable: Repository is not archived
- not applicable: Code pushed to the repository in the 90 days before our check
- not applicable: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
From public records, not a safety rating. Each check with its reason
Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Your own values
- none declared (not a guarantee)
- Sign-in
- none needed to open a session
- Tools
- 66
- Last tested
- 2026-11-17
Tool list size
22,580 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (66 tools). Counted with Anthropic's token counter on 2026-11-17, from the tool list we read on 2026-11-17. Median across 28,560 counted servers: 2,657 tokens. How it is counted
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-11-17 (app.catchy-me.com), in our read-only connection; no tool was called. It may have changed since. How it is read
Tool list at the three APIs
Not sent yet for this version (1.0.0).
Observed fact
This server accepted a session without any credential and lists 16 tools whose name or declaration suggests they change data (request_password_reset, reset_password, create_search, cancel_subscription, set_outreach_sender and 11 more). That is our reading of the names; we did not call them. Source: our connection, 2026-11-17.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-17
- Mode
- read-only (no tool calls)
- Latest version
- 1.0.0, published 2026-11-17 (registry, as of the 2026-11-17 snapshot)
- First listed version
- 2026-11-17 (earliest version still in the registry; older removed versions would be earlier)
- Registry data
- snapshot 2026-11-17
- Package and repository
- checked 2026-11-17
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Dead or stale signals
None found in the records we hold
Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.
Changes since the last refresh
New in the registry: not in the list of 2026-11-16, listed on 2026-11-17 with version 1.0.0 (published 2026-11-17).
Source: the official MCP Registry list on 2026-11-16 and on 2026-11-17.
What it is
What does this server offer?
Observed inventoryNone of its 66 tools are described as changing anything. For 66 the reading was uncertain, so no mark is shown.
- catchy_info
“What Catchy is and how it works: lead search with facts and AI outreach, plans, briefs and credits, how to connect this MCP server (OAuth or an API key), how an agent signs up by itself, and the link…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- sign_upon 18 other servers
“Registers a new Catchy account and emails a 6-digit code to confirm it (then confirm_sign_up).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
6 inputs, 3 required
namestringrequiredemailstringrequiredpasswordstringlangstring“The account's language (messages, the texts of its searches).”accept_termsbooleanrequired“The user agreed to the Terms of Use and the Privacy Policy.”invitestring“An invite code, when registration is by invitation.”
- resend_sign_up_code
“Sends a new code for a pending registration (at most once a minute; the answer is the same whether or not one is pending).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 1 required
emailstringrequiredlangstring“The account's language (messages, the texts of its searches).”
- confirm_sign_up
“Confirms the registration with the emailed code and the signup_token of sign_up, and returns an API key for this MCP server (shown once).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
7 inputs, 3 required
emailstringrequiredcodestringrequiredsignup_tokenstringrequiredlangstring“The account's language (messages, the texts of its searches).”key_namestring“Name of the API key in Settings (default «MCP agent»).”key_accessstringkey_daysinteger or null“Lifetime of the key in days; null = no limit.”
- sign_inon 12 other servers
“An existing Catchy account: email and password -> an API key for this MCP server (shown once).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
6 inputs, 2 required
emailstringrequiredpasswordstringrequiredlangstring“The account's language (messages, the texts of its searches).”key_namestring“Name of the API key in Settings (default «MCP agent»).”key_accessstringkey_daysinteger or null“Lifetime of the key in days; null = no limit.”
- request_password_reset
“Emails a code to reset the password of an account (the answer is the same whether or not the account exists).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 1 required
emailstringrequiredlangstring“The account's language (messages, the texts of its searches).”
- reset_passwordon 1 other server
“Sets a new password with the emailed code (every session of the account ends).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 3 required
emailstringrequiredcodestringrequiredpasswordstringrequiredlangstring“The account's language (messages, the texts of its searches).”
- get_accounton 181 other servers
“The signed-in Catchy account: name, email, language, plan («тариф»: code, status, period end), briefs («брифы») left this period and when they renew, the free brief, the balance in whole credits (ava…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- accept_legal
“Records that the user accepted the current Terms of Use (https://catchy-me.com/terms) and took note of the current Privacy Policy (https://catchy-me.com/privacy).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
confirmbooleanrequired“The user read the links and explicitly agreed.”
- get_balance_historyon 2 other servers
“The account's balance lines, newest first: top-ups, grants and charges (search, facts on request, outreach) in whole credits, with the search each charge was for.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
limitinteger
- list_planson 68 other servers
“The tariff catalog: each plan's monthly price (USD, RUB, EUR), credits and briefs a period, and the Enterprise contact.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- suggest_company_description
“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.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs
urlstring“The company's site, e.g.”textstring“Or: a text about the company.”onboarding_idstring“The onboarding id that ties the assistant calls and create_search into ONE brief.”
Show 54 more tools
- suggest_goals
“Step 2 («Цель»): four goals for the outreach to the people found (e.g.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 1 required
companystringrequired“The company description (step 1).”onboarding_idstring“The onboarding id that ties the assistant calls and create_search into ONE brief.”
- suggest_audiences
“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.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 2 required
companystringrequiredgoalstringrequiredonboarding_idstring“The onboarding id that ties the assistant calls and create_search into ONE brief.”
- parse_exclusions_file
“«Исключить уже знакомых»: a CSV, TSV, TXT or XLSX file with the people the user already knows (LinkedIn links in any column) -> the profile links found (pass them as exclude_urls of create_search) an…”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 2 required
file_namestringrequired“The file's name with its extension.”data_base64stringrequired“The file's bytes, base64.”onboarding_idstring“The onboarding id that ties the assistant calls and create_search into ONE brief.”
- extract_site_file_text
“When the site cannot be read: a saved page (HTML), a PDF or a text file -> its text, to describe the company with suggest_company_description(text=...).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 2 required
file_namestringrequired“The file's name with its extension.”data_base64stringrequired“The file's bytes, base64.”onboarding_idstring“The onboarding id that ties the assistant calls and create_search into ONE brief.”
- list_previous_onboardings
“The user's earlier search onboardings (company, goal, audience), newest first.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- get_onboarding_prefill
“The answers of an earlier onboarding (company, goal, icp, language) to reuse in create_search; pass its id as source_task there too, so the search plan made then is reused when the brief stays the sa…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
task_idstringrequired“The search id (task id), e.g.”
- list_exclusion_sources
“The user's earlier searches whose people can be left out of a new one (exclude_tasks of create_search): all analysed or only the leads.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- create_search
“Creates a new lead search («поиск лидов») from the onboarding answers and starts compiling its requirements (~1-2 minutes; nothing is charged in credits, but it spends the onboarding's brief if no as…”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
11 inputs, 2 required
companystringrequired“What the user's company does (step 1).”goalstring“What the outreach should achieve (step 2).”icpstringrequired“Whom to find: the customer profile (step 3).”languagestring“Language of the outreach messages (default english).”exclude_urlsarray“LinkedIn profile links of people to leave out.”exclude_companiesboolean“Also leave out the companies of those people.”exclude_company_urlsarrayexclude_tasksarray“Earlier searches whose people to leave out.”exclude_scopestring“From those searches: everyone analysed (all) or only leads.”source_taskstring“The earlier onboarding this one was filled from (get_onboarding_prefill).”onboarding_idstring“The onboarding id that ties the assistant calls and create_search into ONE brief.”
- get_subscriptionon 18 other servers
“The account's subscription: plan, status (active, past_due, cancelling, ended), who manages it (admin or lavatop), price and currency, period end, whether it renews, credits and briefs a period.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- subscribeon 1,863 other servers
“Creates a LavaTop payment for a monthly plan (start, growth, scale; prices in list_plans) and returns its payment_url and order id.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 1 required
planstringrequiredcurrencystring
- get_payment_statuson 14 other servers
“The status of a payment order made by subscribe: pending, paid, failed, expired, cancelled.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
order_idstringrequired“The order id from subscribe.”
- cancel_subscriptionon 14 other servers
“Stops the renewal of a LavaTop subscription: the plan stays until the period's end and the credits stay on the balance after it.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
confirmbooleanrequired
- list_leadson 10 other servers
“The people of a search by kind: fit («Подходят»: the leads, in their order), partial («Частично»: some requirement not proven, with what was assumed), miss («Не подходят», with the reason).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
task_idstringrequired“The search id (task id), e.g.”kindstringoffsetintegerlimitinteger
- get_leadon 7 other servers
“One person of a search: the profile card, the company, the verdict and why they fit, each criterion's status with how it was checked, and the facts found (dated, with source links) — the material for…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
task_idstringrequired“The search id (task id), e.g.”cidstringrequired“The person's id (cid) from list_leads.”
- quote_facts_on_request
“After a search: the price in credits of finding facts for chosen partial people and moving them to fit («перевести в подходящие», promote=true), or facts only (promote=false).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 2 required
task_idstringrequired“The search id (task id), e.g.”cidsarrayrequired“Person ids (cid) from list_leads.”promoteboolean
- start_facts_on_request
“SPENDS CREDITS: quote_facts_on_request first, show the price to the user and after their yes pass its `credits` as confirm_credits.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 3 required
task_idstringrequired“The search id (task id), e.g.”cidsarrayrequired“Person ids (cid) from list_leads.”promotebooleanconfirm_creditsintegerrequired“The price in credits the matching quote returned, shown to the user and confirmed by them.”
- demote_lead
“After a search: moves chosen fit people to partial («в частично подходящие»), e.g.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 2 required
task_idstringrequired“The search id (task id), e.g.”cidsarrayrequired“Person ids (cid) from list_leads.”
- diagnose_search
“The criteria revision («Изменить критерии»): while a search asks about a higher price, or when a finished search ran out of people, works out which criteria hold it back and proposes changes, each co…”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
1 input, 1 required
task_idstringrequired“The search id (task id), e.g.”
- revise_search
“Applies chosen proposals of diagnose_search.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
6 inputs, 3 required
task_idstringrequired“The search id (task id), e.g.”acceptarrayrequiredversioninteger“The spec version from get_search (optional: protects against an edit made meanwhile in the web).”confirm_creditsintegerrequired“The price in credits the matching quote returned, shown to the user and confirmed by them.”moreintegerstop_at_targetboolean
- get_search_funnel
“A finished search's funnel in plain words: how many people were seen, checked, rejected and why, and how many became leads.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
task_idstringrequired“The search id (task id), e.g.”
- export_search
“A download link for the search's leads as Excel (xlsx) or PDF: chosen kinds (default fit and partial), with the facts and the brief.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
task_idstringrequired“The search id (task id), e.g.”formatstringkindsarray
- get_outreachon 2 other servers
“The outreach («Рассылка») of a finished search: the campaign (sender with its card, essence = offer / ask / tone / rules / language, the accounts, counts, the current generation, credits charged) and…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
task_idstringrequired“The search id (task id), e.g.”offsetintegerlimitinteger
- list_outreach_presets
“The user's saved outreach setups across searches (sender, offer, ask, language, accounts, source search), newest used first; new_outreach with preset_id copies one into a fresh generation.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
cursorstringlimitinteger
- new_outreach
“A fresh outreach generation of the search: empty, or with this search's previous setup (reuse_previous) or a saved one (preset_id).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 1 required
task_idstringrequired“The search id (task id), e.g.”reuse_previousbooleanpreset_idstringgeneration_idstring“The outreach generation id (get_outreach campaign.generation.id); omitted: the current one.”
- set_outreach_sender
“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.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 2 required
task_idstringrequired“The search id (task id), e.g.”modestringrequiredlinkedin_urlstringtextstringgeneration_idstring“The outreach generation id (get_outreach campaign.generation.id); omitted: the current one.”
- edit_sender_card
“Correct the sender's card the analysis made (name, role, company, voice = how they write, summary, background, interests).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
9 inputs, 1 required
task_idstringrequired“The search id (task id), e.g.”namestringrolestringcompanystringvoicestringsummarystringbackgroundarrayinterestsarraygeneration_idstring“The outreach generation id (get_outreach campaign.generation.id); omitted: the current one.”
- suggest_outreach_essence
“A draft of «Что предлагаем» (the offer) from the search's onboarding.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
1 input, 1 required
task_idstringrequired“The search id (task id), e.g.”
- set_outreach_essence
“«Суть»: offer (what we offer), ask (what we want from the person), optional tone and client_rules, and the message language.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
7 inputs, 3 required
task_idstringrequired“The search id (task id), e.g.”offerstringrequiredaskstringrequiredtonestringclient_rulesstringlanguagestringgeneration_idstring“The outreach generation id (get_outreach campaign.generation.id); omitted: the current one.”
- set_outreach_funnel
“«Аккаунты»: what the user can write from — email (bool), linkedin (none | basic | sales_navigator), threads (bool), linkedin_comments (public comments on LinkedIn posts, bool).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
6 inputs, 4 required
task_idstringrequired“The search id (task id), e.g.”emailbooleanrequiredlinkedinstringrequiredthreadsbooleanrequiredlinkedin_commentsbooleangeneration_idstring“The outreach generation id (get_outreach campaign.generation.id); omitted: the current one.”
- quote_outreach
“The price in credits of researching and writing messages for the chosen fit people (per person, total, the most it may hold), the balance, and who is skipped.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 2 required
task_idstringrequired“The search id (task id), e.g.”cidsarrayrequired“Fit people (cid) of the search; get_outreach lists them.”generation_idstring“The outreach generation id (get_outreach campaign.generation.id); omitted: the current one.”
- start_outreach
“SPENDS CREDITS: quote_outreach first, show the price to the user and after their yes pass its `credits` as confirm_credits.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 3 required
task_idstringrequired“The search id (task id), e.g.”cidsarrayrequired“Fit people (cid) of the search; get_outreach lists them.”confirm_creditsintegerrequired“The 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.”
- quote_outreach_retry
“The price in credits of retrying the people whose messages failed, from where they stopped.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 1 required
task_idstringrequired“The search id (task id), e.g.”cidsarray“The failed people to retry; omitted: every failed person of the generation.”generation_idstring“The outreach generation id (get_outreach campaign.generation.id); omitted: the current one.”
- retry_outreach
“SPENDS CREDITS: quote_outreach_retry first, show the price, after the user's yes pass its `credits` as confirm_credits.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 2 required
task_idstringrequired“The search id (task id), e.g.”cidsarray“The failed people to retry; omitted: every failed person of the generation.”confirm_creditsintegerrequired“The 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.”
- get_outreach_lead
“One person of the outreach: the messages by step (network, kind, text, character limit, hook and the fact it uses, the post of a comment), the route and why, the findings of the research with sources…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
task_idstringrequired“The search id (task id), e.g.”cidstringrequired“The person's id (cid) from list_leads.”
- edit_outreach_message
“Saves the user's own text of one message step (free).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
6 inputs, 4 required
task_idstringrequired“The search id (task id), e.g.”cidstringrequired“The person's id (cid) from list_leads.”step_idstringrequired“The step id of the message (get_outreach_lead steps[].step_id).”textstringrequiredresult_idstringexpected_revisioninteger
- quote_message_rewrite
“The price in credits of rewriting one message by AI (mode).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 4 required
task_idstringrequired“The search id (task id), e.g.”cidstringrequired“The person's id (cid) from list_leads.”step_idstringrequired“The step id of the message (get_outreach_lead steps[].step_id).”modestringrequired“other_hook (another fact), shorter, warmer, rewrite (with the note).”generation_idstring“The outreach generation id (get_outreach campaign.generation.id); omitted: the current one.”
- rewrite_message
“SPENDS CREDITS: quote_message_rewrite first, show the price, after the user's yes pass its credits, result_id and expected_revision.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
9 inputs, 5 required
task_idstringrequired“The search id (task id), e.g.”cidstringrequired“The person's id (cid) from list_leads.”step_idstringrequired“The step id of the message (get_outreach_lead steps[].step_id).”modestringrequired“other_hook (another fact), shorter, warmer, rewrite (with the note).”notestringconfirm_creditsintegerrequired“The price in credits the matching quote returned, shown to the user and confirmed by them.”result_idstringexpected_revisionintegergeneration_idstring“The outreach generation id (get_outreach campaign.generation.id); omitted: the current one.”
- get_message_variant
“A finished AI variant of a person's messages that was not applied because the text was edited meanwhile (its id from get_outreach_lead).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 3 required
task_idstringrequired“The search id (task id), e.g.”cidstringrequired“The person's id (cid) from list_leads.”candidate_idstringrequired
- apply_message_variant
“Replaces the person's messages with that variant (free); result_id and expected_result_revision from get_outreach_lead.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 3 required
task_idstringrequired“The search id (task id), e.g.”cidstringrequired“The person's id (cid) from list_leads.”candidate_idstringrequiredresult_idstringexpected_result_revisioninteger
- export_outreachon 1 other server
“A download link for the whole outreach as one Excel sheet (every person with the messages by touch, the route, the facts).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
task_idstringrequired“The search id (task id), e.g.”
- list_searcheson 3 other servers
“The user's searches («Мои поиски»), newest first: id, title, status, leads / partial found, target, credits charged, progress of a running one.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
statusstringoffsetintegerlimitinteger
- get_searchon 5 other servers
“One search: status, progress, counts, credits charged, the estimate (price examples), what to do next (`next`); for a search that asks about a higher price, the question (`ask`).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
task_idstringrequired“The search id (task id), e.g.”detailstring
- get_search_requirements
“The requirements of a search as the results sheet shows them (how each criterion is checked, where the facts come from).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
task_idstringrequired“The search id (task id), e.g.”
- edit_search_spec
“Before the run (status ready): change the role of criteria (required = must be proven, plus = a bonus) and how strictly they are proven (inference = may be inferred, explicit = needs an explicit sour…”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
4 inputs, 1 required
task_idstringrequired“The search id (task id), e.g.”criteriaarraysource_orderarrayversioninteger“The spec version from get_search (optional: protects against an edit made meanwhile in the web).”
- edit_criterion
“Before the run: action=add (a new requirement in words; an AI call adds it), edit (new wording and/or role / standard of criterion_id), remove («Неверно»: drop it; `confirm` true when the answer warn…”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
8 inputs, 2 required
task_idstringrequired“The search id (task id), e.g.”actionstringrequiredcriterion_idstringtextstringrolestringstandardstringconfirmbooleanversioninteger“The spec version from get_search (optional: protects against an edit made meanwhile in the web).”
- edit_pain
“Before the run: the pains («боли») the search looks for in a lead's facts.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 3 required
task_idstringrequired“The search id (task id), e.g.”pain_idstringrequiredactionstringrequiredtextstringversioninteger“The spec version from get_search (optional: protects against an edit made meanwhile in the web).”
- edit_counter_signal
“Before the run: the counter-signals («контрсигналы») that make a lead partial or a miss.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 3 required
task_idstringrequired“The search id (task id), e.g.”signal_idstringrequiredactionstringrequiredversioninteger“The spec version from get_search (optional: protects against an edit made meanwhile in the web).”
- set_search_strategy
“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 d…”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs, 2 required
task_idstringrequired“The search id (task id), e.g.”strategystringrequiredversioninteger“The spec version from get_search (optional: protects against an edit made meanwhile in the web).”
- quote_searchon 1 other server
“The price in whole credits of running a ready search for `leads` leads (or of continuing a finished one for `leads` more): a low-high range; the start holds the high figure and charges what it really…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
task_idstringrequired“The search id (task id), e.g.”leadsinteger
- run_searchon 2 other servers
“Starts a ready search for `leads` leads.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 3 required
task_idstringrequired“The search id (task id), e.g.”leadsintegerrequiredconfirm_creditsintegerrequired“The price in credits the matching quote returned, shown to the user and confirmed by them.”stop_at_targetbooleanversioninteger“The spec version from get_search (optional: protects against an edit made meanwhile in the web).”
- continue_search
“«Продолжить поиск»: a finished or stopped search goes on for `more` more leads with the same requirements (no new brief).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 3 required
task_idstringrequired“The search id (task id), e.g.”moreintegerrequiredconfirm_creditsintegerrequired“The price in credits the matching quote returned, shown to the user and confirmed by them.”stop_at_targetboolean
- control_search
“A started search: pause, resume, stop (the leads found are kept and charged), or continue — the answer to a search that asks about a higher price (status asking): it SPENDS the extra credits of get_s…”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 2 required
task_idstringrequired“The search id (task id), e.g.”actionstringrequiredconfirm_creditsinteger“The price in credits the matching quote returned, shown to the user and confirmed by them.”
- rename_search
“The name a search card shows (1-80 characters).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
2 inputs, 2 required
task_idstringrequired“The search id (task id), e.g.”titlestringrequired
- delete_search
“Deletes a search with its leads and outreach; a running one is stopped first.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
2 inputs, 2 required
task_idstringrequired“The search id (task id), e.g.”confirmbooleanrequired
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-17.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).
Counted from the listing
- Parameters with a description
- 57% of 215
- Tools with a description
- 100% of 66
- Typical description length
- 284 characters
The tool set
Counted from the listing
- Tools
- 66
- Size of the list
- about 16,229 tokens for an agent to load (characters ÷ 4)
- Naming
- 65 of 66 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 66 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-11-17 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://app.catchy-me.com/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"catchy-me": {
"url": "https://app.catchy-me.com/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"catchy-me": {
"type": "http",
"url": "https://app.catchy-me.com/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"catchy-me","type":"http","url":"https://app.catchy-me.com/mcp"}'Claude Code
claude mcp add --transport http catchy-me https://app.catchy-me.com/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"catchy-me": {
"type": "streamableHttp",
"url": "https://app.catchy-me.com/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"catchy-me": {
"httpUrl": "https://app.catchy-me.com/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.catchy-me] url = "https://app.catchy-me.com/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"catchy-me": {
"url": "https://app.catchy-me.com/mcp"
}
}
}Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://app.catchy-me.com/mcp --transport http
- Optional settings the entry also lists (left out above): Authorization.
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
What do the published files and outside lists say?
Read as text · nothing run · no tool called
Package files
- MCP SDK in the package files. Not read yet: added with the next daily run.
- Build workflow. Not read yet: added with the next daily run.
Outside lists
- CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-17. This product uses the NVD API but is not endorsed or certified by the NVD.
- GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-17. GitHub Advisory Database, CC BY 4.0
- Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-17. Source: read 2026-11-17.
- Cline marketplace. Not in the Cline marketplace on 2026-11-17. Source: read 2026-11-17.
Own host
- security.txt. No security.txt at https://app.catchy-me.com/.well-known/ (HTTP 404, 2026-11-17). No security.txt at https://catchy-me.com/.well-known/ (HTTP 404, 2026-11-17). Source: app.catchy-me.com/.well-known/security.txt · read 2026-11-17.
- A2A agent card. No A2A agent card at https://app.catchy-me.com/.well-known/ (HTTP 404, 2026-11-17). No A2A agent card at https://catchy-me.com/.well-known/ (HTTP 404, 2026-11-17). Source: app.catchy-me.com/.well-known/agent-card.json · read 2026-11-17.
Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read
Does the registry listing match what we found?
Feature #6The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint app.catchy-me.com/mcp | Session opened | matches | our test · 2026-11-17 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-17 |
Choosing
Record checks
Public records · not a safety rating1 of 2 record checks met · 7 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- Not metSource repository link opensThe registry entry gives no repository link.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
- Does not applyRepository is not archivedNo public GitHub repository to read.
- Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
- Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-17. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral
Common questions about com.catchy-me/catchy-me
Answered from the data aboveWho publishes com.catchy-me/catchy-me?
The registry ties the namespace com.catchy-me to the domain catchy-me.com; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.
Does com.catchy-me/catchy-me need an API key or sign-in?
It opened a session without any credential on 2026-11-17. The registry entry declares no required credential; no declaration is not a guarantee.
Has com.catchy-me/catchy-me been security tested?
Partly. 3 of the 15 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. ProtocolProbe publishes no security verdict for a named server.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Open without sign-in
It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: exercised
3 exercised12 not run (reason given)3 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable
Source: our own test, 2026-11-17, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 1,029 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 66 tools, 0 resources, 0 prompts.
- 3,723 msFinished: 3 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “com.catchy-me/catchy-me: MCP server record.” Data checked 2026-11-17. https://protocolprobe.com/mcp/servers/com.catchy-me/catchy-me
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/com.catchy-me/catchy-me)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here, except for a server whose operator has claimed it and given permission (that server's page says so).
Write to hello@protocolprobe.com · corrections log · methodology