com.getcleed/linkedin-buying-signals
REMOTE · WWW.GETCLEED.COM
Find B2B prospects showing buying signals on LinkedIn and draft the outreach.
Available components
Last scanned (18 hours ago)
Scores higher than 96% of remote servers
Reachable. Last reached 21 Nov 2026.
Category CRM and Sales
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 Security94
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
- The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents. View diagnostics → Partial
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability68
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 4534 tokens (~119/item across 38 items; 38 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage83
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 50% 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 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 39 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
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 →
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.
- 15 Nov 26 0
- Tool “find_leads” rewrote its description, which is the text the model reads security
- “find_leads” added an optional parameter “count” cosmetic
- 14 Nov 26 0
- A breaking change shipped without a version bump: still 1.0.0 ▼ security
- “send_reply” added a required parameter “requestId”, so existing callers break ▼ functional
- 13 Nov 26 −1
- The server rewrote its instructions, which are the text every model session reads security
- New tool “add_leads_to_sequence”, which the server declares destructive security
- New tool “approve_leads”, which the server declares destructive security
- New tool “send_reply”, which the server declares destructive security
- New tool “start_sequence”, which the server declares destructive security
- New tool “update_sending_settings”, which the server declares destructive security
- New tool “update_sequence_lead”, which the server declares destructive security
- Tool “get_icp” rewrote its description, which is the text the model reads security
- Schema quality: pass → fail ▼ functional
- New tool “add_exclusion” functional
- New tool “create_sequence” functional
- New tool “find_leads” functional
- New tool “get_account_status” functional
- New tool “get_conversation” functional
- New tool “get_search_status” functional
- New tool “get_sequence” functional
- New tool “list_replies” functional
- New tool “list_search_results” functional
- New tool “list_sequence_messages” functional
- New tool “list_sequences” functional
- New tool “reject_leads” functional
- New tool “remove_exclusion” functional
- New tool “set_lead_status” functional
- New tool “stop_sequence” functional
- New tool “update_targeting” functional
- 11 Nov 26 0
- Stability: 0.97 → pass security
- 10 Nov 26 0
- Stability: pass → 0.97 functional
- 9 Nov 26 0
- Stability: 0.97 → pass security
- 8 Nov 26 0
- Stability: pass → 0.97 functional
- 6 Nov 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
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://www.getcleed.com/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=www.getcleed.com | CN=YR2,O=Let's Encrypt,C=US | 6 Oct 2026 | 4 Jan 2027 | RSA 2048 | SHA256-RSA | 6144939075a9b0d8511daf6aa5994e689b0 |
| SANs: www.getcleed.com | ||||||
| CN=YR2,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | 4ebd24947e24d394802d84a52fd5b319 |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of www.getcleed.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| getcleed.com. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer resource_metadata="https://www.getcleed.com/.well-known/oauth-protected-resource"
Bearer resource_metadata="https://www.getcleed.com/.well-known/oauth-protected-resource" | Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains; preload |
| content-security-policy | default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval' https://vercel.live https://ddwl4m2hdecbv.cloudfront.net https://r2.leadsy.ai; worker-src 'self' blob: data:; style-src 'self' 'unsafe-inline'; img-src 'self' data: blob: https:; connect-src 'self' https: wss:; font-src 'self' data:; object-src 'none'; base-uri 'self'; form-action 'self'; frame-src 'self' https://www.loom.com; frame-ancestors 'none'; upgrade-insecure-requests |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=(), payment=() |
Protected resource metadata
| Document | https://www.getcleed.com/.well-known/oauth-protected-resource |
|---|---|
| Retrieved | Yes |
| Resource | https://www.getcleed.com/api/mcp |
| Authorisation server | https://www.getcleed.com |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://www.getcleed.com/api/mcp | Verified | 200 | |
| http (plaintext) | http://www.getcleed.com/api/mcp | HTTPS enforced | 308 | https://www.getcleed.com/api/mcp |
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 →
add_exclusion Exclude a kind of lead ~174
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 removed too. The user can see and remove exclusions with get_icp and remove_exclusion.
| Name | Type | Req | Description |
|---|---|---|---|
| candidateId | string | – | A result from the search whose queue should also be cleared of matching people |
| direction | string | – | For size: exclude companies over or under that many employees |
| kind | string | yes | title = a word in the job title, industry = a company industry, size = a company headcount limit |
| value | – | yes | The title keyword (at least 5 characters: it hides every title containing it), the industry name, or the number of employees |
No output schema declared.
No examples provided.
add_leads_from_urls Add leads from LinkedIn URLs ~79
Save LinkedIn profiles as prospects and enrich them (name, role, company, industry, location, language). Skips anyone already saved. Counts against the import quota.
| Name | Type | Req | Description |
|---|---|---|---|
| linkedinUrls | array | yes | LinkedIn profile URLs |
| listId | string | – | Optional list to add them to (see get_icp for list ids) |
No output schema declared.
No examples provided.
add_leads_to_sequence Add saved leads to a sequence ~125
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 LinkedIn connected and a sending schedule on, the leads wait in the sequence until start_sequence.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm | boolean | – | Set to true only after the user agreed to what the first call (without it) said would happen. |
| prospectIds | array | yes | – |
| sequenceId | string | yes | – |
No output schema declared.
No examples provided.
analyze_prospects Analyze prospects ~95
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: expect up to a few minutes.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Cap when prospectIds is omitted |
| prospectIds | array | – | Which prospects to analyze; omit to take those with no signals yet |
No output schema declared.
No examples provided.
approve_leads Approve search results ~168
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 call returns what will be sent and needs confirm: true. Without LinkedIn connected the leads wait inside the sequence until it is started.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm | boolean | – | Set to true only after the user agreed to what the first call (without it) said would happen. |
| ids | array | – | Result ids from list_search_results, all from the same search |
| searchId | string | – | Approve everyone still to review in this search |
| sequenceId | string | – | Also add them to this sequence (see list_sequences) |
No output schema declared.
No examples provided.
create_custom_signal Create a custom signal ~85
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.
| Name | Type | Req | Description |
|---|---|---|---|
| detects | string | yes | What to look for, in plain language |
| exampleDetail | string | – | – |
| exampleTitle | string | – | – |
| name | string | yes | Short display name |
No output schema declared.
No examples provided.
create_sequence Create a sequence ~209
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. "own": fixed messages you pass, sent to everyone with {{first_name}} and {{company|your team}} filled in (write a fallback after | for company). The sequence is created stopped and empty: nothing is sent until leads are added and start_sequence is confirmed. Does not need LinkedIn connected.
| Name | Type | Req | Description |
|---|---|---|---|
| approach | string | – | – |
| dailyLimit | integer | – | Most leads started per day |
| messages | array | – | For approach "own": the messages in order. The first goes out the day after they accept the connection request. |
| name | string | yes | – |
| reviewBeforeSend | boolean | – | true: every message waits for an approval before it is sent. false (the product default): messages go out on schedule. |
No output schema declared.
No examples provided.
draft_email Draft an email ~87
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.
| Name | Type | Req | Description |
|---|---|---|---|
| language | string | – | – |
| linkedinUrl | string | – | – |
| prospectId | string | – | – |
| regenerate | boolean | – | Ignore any cached draft |
| signalIndex | integer | – | Which signal to lead with |
No output schema declared.
No examples provided.
draft_linkedin_message Draft a LinkedIn message ~105
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 characters) and so must any note passed to send_linkedin_message.
| Name | Type | Req | Description |
|---|---|---|---|
| language | string | – | – |
| linkedinUrl | string | – | – |
| prospectId | string | – | – |
| regenerate | boolean | – | – |
No output schema declared.
No examples provided.
find_leads Find leads (Deep Search) ~159
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 puts the people found in the review queue: nobody is saved until approve_leads. Counts against the weekly discovery allowance. Call get_search_status to follow it, then list_search_results.
| Name | Type | Req | Description |
|---|---|---|---|
| count | – | – | How many people to find: 5, 10, 20 or 50. Start small and search again for more. |
| name | string | – | A name for this search. It titles its list and its section in a sequence. Defaults to the targeting name. |
No output schema declared.
No examples provided.
find_leads_from_signals Find new leads from signal topics ~127
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, country) and ranked. Nothing is saved: pass the returned candidates to import_sourced_leads. Spends a little of the monthly sourcing budget.
| Name | Type | Req | Description |
|---|---|---|---|
| postsPerSignal | integer | – | – |
| signalType | string | – | Which signal to source for; omit to use the first enabled one (see list_signals) |
No output schema declared.
No examples provided.
get_account_status Account status and what to set up next ~76
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 mailbox, billing) come with the link to give the user. Call this first in a new conversation.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_conversation Read a conversation ~67
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.
| Name | Type | Req | Description |
|---|---|---|---|
| channel | string | yes | – |
| cursor | string | – | – |
| id | string | yes | The id from list_replies |
No output schema declared.
No examples provided.
get_icp Get the ideal customer profile ~61
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_exclusion and remove_exclusion.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_pipeline_stats Pipeline stats ~60
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_prospect Get one prospect ~90
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.
| Name | Type | Req | Description |
|---|---|---|---|
| linkedinUrl | string | – | Their LinkedIn profile URL, if the id is unknown |
| prospectId | string | – | The prospect id from list_prospects |
No output schema declared.
No examples provided.
get_sample_pipeline Sample pipeline (no account needed) ~71
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 Getcleed produces before an account exists. Nothing in it is a real person.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_search_status Search status ~39
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_sequence Get one sequence ~79
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.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | How many leads to return |
| offset | integer | – | – |
| sequenceId | string | yes | – |
No output schema declared.
No examples provided.
import_sourced_leads Import sourced leads ~92
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.
| Name | Type | Req | Description |
|---|---|---|---|
| listId | string | – | – |
| signalType | string | yes | The signalType returned by find_leads_from_signals |
| tokens | array | yes | The token values of the candidates to import |
No output schema declared.
No examples provided.
list_prospects List prospects ~208
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 count, then most recently saved.
| Name | Type | Req | Description |
|---|---|---|---|
| company | string | – | – |
| country | string | – | – |
| enrichmentStatus | string | – | – |
| hasEmail | boolean | – | – |
| industry | string | – | – |
| limit | integer | – | How many to return (max 50) |
| minSignals | integer | – | Only prospects with at least this many signals |
| notContacted | boolean | – | Only prospects with no email sent yet |
| offset | integer | – | – |
| search | string | – | Free text matched against first name, last name, company and title |
| signalType | string | – | Only prospects carrying a signal of this type (see list_signals) |
| title | string | – | Job title contains this text |
No output schema declared.
No examples provided.
list_replies List replies waiting for an answer ~79
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.
| Name | Type | Req | Description |
|---|---|---|---|
| channel | string | – | – |
| cursor | string | – | nextCursor from the previous call |
| days | string | – | How far back to look |
No output schema declared.
No examples provided.
list_search_results List search results to review ~113
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 against the targeting and the reason for it.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| offset | integer | – | – |
| searchId | string | – | Only this search (ids from get_search_status) |
| status | string | – | – |
No output schema declared.
No examples provided.
list_sequence_messages Read the messages a sequence will send ~111
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 when review is on (pass the evidenceFingerprint to update_sequence_lead).
| Name | Type | Req | Description |
|---|---|---|---|
| awaitingApprovalOnly | boolean | – | – |
| limit | integer | – | How many leads |
| offset | integer | – | – |
| sequenceId | string | yes | – |
No output schema declared.
No examples provided.
list_sequences List sequences ~50
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.
| Name | Type | Req | Description |
|---|---|---|---|
| includeArchived | boolean | – | – |
No output schema declared.
No examples provided.
list_signals List signal definitions ~65
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.
| Name | Type | Req | Description |
|---|---|---|---|
| enabledOnly | boolean | – | – |
No output schema declared.
No examples provided.
mark_email_sent Mark as contacted ~44
Record that a prospect was emailed outside getcleed, so reporting and follow-ups stay correct.
| Name | Type | Req | Description |
|---|---|---|---|
| linkedinUrl | string | – | – |
| prospectId | string | – | – |
No output schema declared.
No examples provided.
reject_leads Reject search results ~114
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_exclusion.
| Name | Type | Req | Description |
|---|---|---|---|
| ids | array | yes | – |
| note | string | – | – |
| reason | string | – | function = wrong job function, seniority, company_type, company_size, other |
| undo | boolean | – | Restore these rejected people to the review queue |
No output schema declared.
No examples provided.
remove_exclusion Remove an exclusion ~108
Take one saved exclusion out of the account targeting. Pass it as get_icp lists it under exclusions.
| Name | Type | Req | Description |
|---|---|---|---|
| direction | string | – | For size: exclude companies over or under that many employees |
| kind | string | yes | title = a word in the job title, industry = a company industry, size = a company headcount limit |
| value | – | yes | The title keyword (at least 5 characters: it hides every title containing it), the industry name, or the number of employees |
No output schema declared.
No examples provided.
send_email Send an email ~104
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 under Integrations.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | – | Omit to use the saved draft |
| linkedinUrl | string | – | – |
| prospectId | string | – | – |
| subject | string | – | Omit to use the saved draft |
No output schema declared.
No examples provided.
send_linkedin_message Send a LinkedIn connection request ~106
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 connected in getcleed under Integrations.
| Name | Type | Req | Description |
|---|---|---|---|
| linkedinUrl | string | – | – |
| message | string | – | The note, max 300 characters. Omit to use the saved draft |
| prospectId | string | – | – |
No output schema declared.
No examples provided.
send_reply Send a reply ~114
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 outreach can be answered here.
| Name | Type | Req | Description |
|---|---|---|---|
| channel | string | yes | – |
| id | string | yes | The id from list_replies |
| requestId | string | yes | Generate once for this reply and reuse on every retry. Never generate a new ID after a timeout. |
| text | string | yes | – |
No output schema declared.
No examples provided.
set_lead_status Dismiss or restore saved leads ~65
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.
| Name | Type | Req | Description |
|---|---|---|---|
| prospectIds | array | yes | – |
| status | string | yes | – |
No output schema declared.
No examples provided.
start_sequence Start or resume a sequence ~160
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 confirm: true. With section, resumes just that section after stop_sequence (also confirmed first when the sequence is running). Needs LinkedIn connected and the sending schedule on (see get_account_status).
| Name | Type | Req | Description |
|---|---|---|---|
| confirm | boolean | – | Set to true only after the user agreed to what the first call (without it) said would happen. |
| section | object | – | One section of the sequence, as get_sequence lists it (sourceId and sourceName; leave both out for leads added manually) |
| sequenceId | string | yes | – |
No output schema declared.
No examples provided.
stop_sequence Stop a sequence ~88
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.
| Name | Type | Req | Description |
|---|---|---|---|
| section | object | – | One section of the sequence, as get_sequence lists it (sourceId and sourceName; leave both out for leads added manually) |
| sequenceId | string | yes | – |
No output schema declared.
No examples provided.
update_sending_settings Set the sending schedule ~209
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: true, and the first time it also needs the time zone. Needs LinkedIn connected.
| Name | Type | Req | Description |
|---|---|---|---|
| activeDays | array | – | Days sending is allowed: 0 Sunday to 6 Saturday |
| confirm | boolean | – | Set to true only after the user agreed to what the first call (without it) said would happen. |
| dailyLimit | integer | – | Messages per day |
| enabled | boolean | – | Whether sequences may send |
| endHour | integer | – | – |
| invitationsPerDay | integer | – | – |
| invitationsPerWeek | integer | – | – |
| minutesBetweenSends | integer | – | – |
| startHour | integer | – | – |
| timezone | string | – | IANA time zone, e.g. Europe/Paris |
No output schema declared.
No examples provided.
update_sequence_lead Edit, approve, pause or skip one lead in a sequence ~176
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_sequence_messages returned with the text the user read) or resumes a paused lead (approving first returns the text and needs confirm: true); "paused" holds them; "skipped" takes them out of the sequence for good. An approved message is sent on schedule and cannot be unsent.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm | boolean | – | Set to true only after the user agreed to what the first call (without it) said would happen. |
| editText | object | – | – |
| enrollmentId | string | yes | – |
| evidenceFingerprint | string | – | – |
| status | string | – | – |
No output schema declared.
No examples provided.
update_targeting Update the targeting ~113
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 calling. To exclude people, use add_exclusion instead.
| Name | Type | Req | Description |
|---|---|---|---|
| companySize | array | – | – |
| countries | array | – | Country names |
| industries | array | – | – |
| roles | array | – | Job titles to reach, e.g. "Head of Sales" |
No output schema declared.
No examples provided.
How do I install the com.getcleed/linkedin-buying-signals MCP server?
com.getcleed/linkedin-buying-signals is a hosted endpoint at https://www.getcleed.com/api/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 · www.getcleed.com
claude mcp add --transport http com-getcleed-linkedin-buying-signals 'https://www.getcleed.com/api/mcp'
What is the com.getcleed/linkedin-buying-signals MCP server?
com.getcleed/linkedin-buying-signals is an MCP server listed in the public MCP registry as com.getcleed/linkedin-buying-signals. Find B2B prospects showing buying signals on LinkedIn and draft the outreach. This page covers its hosted endpoint (https://www.getcleed.com/api/mcp).
Is the com.getcleed/linkedin-buying-signals MCP server safe to use?
com.getcleed/linkedin-buying-signals scores 89 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 com.getcleed/linkedin-buying-signals MCP server expose?
com.getcleed/linkedin-buying-signals exposes 38 tools: get_sample_pipeline, list_prospects, get_prospect, get_pipeline_stats, list_signals, and 33 more. Their descriptions and schemas cost roughly 4,075 tokens of context every time the server is loaded.
Does the com.getcleed/linkedin-buying-signals MCP server require authentication?
Yes. com.getcleed/linkedin-buying-signals asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the com.getcleed/linkedin-buying-signals MCP server still maintained?
com.getcleed/linkedin-buying-signals 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 com.getcleed/linkedin-buying-signals MCP server?
VerifyMCP ran 13 checks on com.getcleed/linkedin-buying-signals, 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.