Linkedin Buying Signals is an MCP server with 38 tools an agent can call, among them add_exclusion, add_leads_from_urls, add_leads_to_sequence. It answers at https://www.getcleed.com/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 25 September 2026; the last check, on 8 November 2026, succeeded.
Find B2B prospects showing buying signals on LinkedIn and draft the outreach.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
add_exclusion | Save an exclusion in the account targeting so later searches skip matching people: a job title keyword, an industry, or a company size limit. With candidateId (a result just rejected), matching people still waiting in that same search are r Inputs: kind, value, direction, candidateId |
add_leads_from_urls | Save LinkedIn profiles as prospects and enrich them (name, role, company, industry, location, language). Skips anyone already saved. Counts against the import quota. Inputs: linkedinUrls, listId |
add_leads_to_sequence | Put saved leads (prospect ids from list_prospects) into a sequence. Leads already in a sequence, dismissed, or who replied are skipped. If the sequence is running, the first call returns what will be sent and needs confirm: true. Without Li Inputs: sequenceId, prospectIds, confirm |
analyze_prospects | Run the signal pipeline on prospects: enrich anyone missing company data, read their recent LinkedIn activity, and detect buying signals. Every signal kept must quote its source verbatim. Counts against the monthly analysis quota. Slow: exp Inputs: prospectIds, limit |
approve_leads | Save people from the review queue as leads (in a list named after their search), and optionally add them to a sequence. Pass ids from one search, or a searchId to approve everyone still waiting in it. If the sequence is running, the first c Inputs: ids, searchId, sequenceId, confirm |
create_custom_signal | Teach the account a new buying signal to look for, described in plain language (for example "people complaining their onboarding takes too long"). Future analyses and sourcing will use it. Inputs: name, detects, exampleTitle, exampleDetail |
create_sequence | Create an outreach sequence. approach "signal": a connection request, then an opener Getcleed writes for each lead from their own signals and two follow-ups (the default, and what the product is for). "simple": four short generic messages. Inputs: name, approach, messages, reviewBeforeSend, dailyLimit |
draft_email | Write a personalised email for a prospect, built from their detected signals, in their language. Saves the draft on the prospect and returns it. Does not send. Inputs: prospectId, linkedinUrl, signalIndex, regenerate, language |
draft_linkedin_message | Write a short LinkedIn connection note for a prospect from their detected signals, in their language. Saves the draft and returns it. Does not send. Drafts follow the house rules (one fact about them, one question, no pitch, under 200 chara Inputs: prospectId, linkedinUrl, regenerate, language |
find_leads | Search for a few new people (5 by default, up to 50) matching the account targeting (see get_icp; change it with update_targeting or add_exclusion first if the user wants someone else). Runs in the background for two to five minutes and put Inputs: name, count |
find_leads_from_signals | Search recent LinkedIn posts on the topics of this account's own signal definitions, keep only posts a check can prove are on topic, and return the people who wrote, commented on or reacted to them, filtered against the ICP (role, industry, Inputs: signalType, postsPerSignal |
get_account_status | Where the account stands: plan and allowances, whether the targeting exists, whether LinkedIn and a mailbox are connected, the sending schedule, and the next steps the product suggests. Steps that need a browser (connecting LinkedIn or a ma |
get_conversation | The messages of one conversation with a lead, oldest first, each marked as written by the user or by the lead. Read it before writing a reply. Inputs: channel, id, cursor |
get_icp | The active targeting (ICP): target roles, industries, countries, company sizes, relevant keywords and every saved exclusion. This is what find_leads searches for and what scoring filters against. Change it with update_targeting, add_exclusi |
get_pipeline_stats | How the pipeline stands: how many prospects, how many carry signals, enrichment state, how many have an email address, how many were contacted, what was added in the last 7 days, the most common signal types, and the remaining plan quota. |
get_prospect | Everything known about one prospect: role, company, location, language, every detected signal with the verbatim quote from its source and the LinkedIn URL it came from, any existing email or LinkedIn draft, and outreach state. Inputs: prospectId, linkedinUrl |
get_sample_pipeline | A fictional pipeline in exactly the shapes the real tools return: an ICP, the signal definitions, pipeline stats and six prospects with their signals, verbatim quotes and drafts. Works without any credential, so an agent can show what Getcl |
get_search_status | Whether a find_leads search is running or finished, how many people are waiting in the review queue per search, and the weekly discovery allowance left. |
get_sequence | One sequence in full: its steps, its sections (the search each group of leads came from, which can be stopped or resumed on its own), and each lead with where they are, what happens next and when. Inputs: sequenceId, limit, offset |
import_sourced_leads | Save candidates returned by find_leads_from_signals. They arrive already enriched and with the signal attached, including the verbatim quote from the post that surfaced them. Counts against the import quota. Inputs: signalType, tokens, listId |
list_prospects | Search the saved prospects in the account. Filter by company, industry, job title, country, signal type, minimum number of signals, whether an email address is known, enrichment state, or whether they have been contacted. Ordered by signal Inputs: search, company, industry, title, country, signalType |
list_replies | Conversations where a lead answered the outreach and the user has not replied yet, newest first, on LinkedIn and by email. Use the id and channel with get_conversation and send_reply. Inputs: channel, days, cursor |
list_search_results | People found by searches, best fit first. "to_review" is the queue waiting for a decision, "approved" the ones saved as leads, "rejected" the ones marked not a fit (they can be restored with reject_leads undo). Each person has a fit level a Inputs: status, searchId, limit, offset |
list_sequence_messages | For each lead in a sequence, the messages still to be sent to them, with the text when it is already written, and the evidence about the lead the text is based on. Use it to show the user what will go out, and before approving a message whe Inputs: sequenceId, awaitingApprovalOnly, limit, offset |
list_sequences | Every outreach sequence in the account: whether it is running, whether each message is reviewed before sending, its steps in short, and how many leads are in each state. Inputs: includeArchived |
list_signals | The buying signals this account looks for: the predefined ones and the custom ones, each with the definition used to detect it and whether it is enabled. Use the returned type values with list_prospects and find_leads_from_signals. Inputs: enabledOnly |
mark_email_sent | Record that a prospect was emailed outside getcleed, so reporting and follow-ups stay correct. Inputs: prospectId, linkedinUrl |
reject_leads | Mark people in the review queue as not a fit, optionally with the reason. They leave the queue and later searches skip them. With undo: true, brings rejected people back to the queue. When the reason would apply to others too, offer add_exc Inputs: ids, reason, note, undo |
remove_exclusion | Take one saved exclusion out of the account targeting. Pass it as get_icp lists it under exclusions. Inputs: kind, value, direction |
send_email | Send an email to a prospect from the connected mailbox. This reaches a real person immediately and cannot be undone. Pass the subject and body you want sent, or omit them to send the saved draft. Requires a mailbox connected in getcleed und Inputs: prospectId, linkedinUrl, subject, body |
send_linkedin_message | Send a LinkedIn connection request with a note to a prospect from the connected LinkedIn account. This reaches a real person immediately and cannot be undone. Pass the note you want sent, or omit it to use the saved draft. Requires LinkedIn Inputs: prospectId, linkedinUrl, message |
send_reply | Send a reply in a conversation, from the user's own LinkedIn account or mailbox. It reaches the lead immediately and cannot be undone: show the user the exact text and get their agreement first. Only conversations started by Getcleed outrea Inputs: channel, id, requestId, text |
set_lead_status | Dismiss saved leads (prospect ids from list_prospects): no more outreach goes to them and any sequence they are in is paused for them. "restored" brings dismissed leads back. Inputs: prospectIds, status |
start_sequence | Start a sequence: its leads are enrolled and steps begin going out on the sending schedule, from the user's own LinkedIn account. The first call returns how many people it reaches and whether messages are reviewed first; it only starts with Inputs: sequenceId, section, confirm |
stop_sequence | Stop a running sequence: nothing more is sent until it is started again. With section, stops only the leads that came from that search and leaves the rest running. Stopping never unsends anything. Inputs: sequenceId, section |
update_sending_settings | When and how fast sequences send: time zone, days, hours, daily limits, and whether sending is on at all. Fields left out keep their value. Turning it on lets running sequences send: that first call returns the schedule and needs confirm: t Inputs: confirm, enabled, timezone, activeDays, startHour, endHour |
update_sequence_lead | Act on one lead inside a sequence (enrollmentId from get_sequence or list_sequence_messages). editText rewrites a message not sent yet. status "active" approves the waiting message when review is on (pass the evidenceFingerprint that list_s Inputs: enrollmentId, editText, status, evidenceFingerprint, confirm |
update_targeting | Change who find_leads looks for: target job titles, industries, countries and company sizes. Each field passed replaces that field; fields left out stay as they are. Show the user the current targeting (get_icp) and the change before callin Inputs: roles, industries, countries, companySize |
Every block below points at https://www.getcleed.com/api/mcp. Pick your client and copy.
claude mcp add --transport http linkedin-buying-signals https://www.getcleed.com/api/mcp
{
"mcpServers": {
"linkedin-buying-signals": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://www.getcleed.com/api/mcp"]
}
}
}{
"mcpServers": {
"linkedin-buying-signals": {
"url": "https://www.getcleed.com/api/mcp"
}
}
}{
"servers": {
"linkedin-buying-signals": {
"type": "http",
"url": "https://www.getcleed.com/api/mcp"
}
}
}{
"context_servers": {
"linkedin-buying-signals": {
"url": "https://www.getcleed.com/api/mcp"
}
}
}{
"mcpServers": {
"linkedin-buying-signals": {
"serverUrl": "https://www.getcleed.com/api/mcp"
}
}
}{
"mcpServers": {
"linkedin-buying-signals": {
"url": "https://www.getcleed.com/api/mcp"
}
}
}name: Linkedin Buying Signals
version: 0.0.1
schema: v1
mcpServers:
- name: Linkedin Buying Signals
type: streamable-http
url: https://www.getcleed.com/api/mcp{
"mcpServers": {
"linkedin-buying-signals": {
"httpUrl": "https://www.getcleed.com/api/mcp"
}
}
}{
"mcpServers": {
"linkedin-buying-signals": {
"type": "http",
"url": "https://www.getcleed.com/api/mcp"
}
}
}{
"mcpServers": {
"linkedin-buying-signals": {
"url": "https://www.getcleed.com/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fwww.getcleed.com%2Fapi%2Fmcp&type=streamable_http&id=linkedin-buying-signals&name=Linkedin%20Buying%20Signals
It answered our last check on 8 November 2026 in 1170 ms. Over 4 checks since 25 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by getcleed.com and served from www.getcleed.com, the vendor's own domain: https://www.getcleed.com/api/mcp.
38, as returned by the server's own tools/list on 15 November 2026: add_exclusion, add_leads_from_urls, add_leads_to_sequence, analyze_prospects, approve_leads, create_custom_signal, create_sequence, draft_email, and 30 more.
It answered our last check on 8 November 2026 in 1170 ms. Over 4 checks since 25 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://www.getcleed.com/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.getcleed. Endpoint host: www.getcleed.com. ARD identifier: urn:air:com.getcleed:mcp:linkedin-buying-signals.
First indexed 25 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.