此 MCP 可以做什么
Finds and analyzes LinkedIn prospects with buying signals, manages lead records and drafts or sends personalized email and LinkedIn outreach.
功能
工具
15
工具
add_leads_from_urls
Add leads from LinkedIn URLs
Save LinkedIn profiles as prospects and enrich them (name, role, company, industry, location, language). Skips anyone already saved. Counts against the import quota.
输入模式
{'type': 'object', 'required': ['linkedinUrls'], 'properties': {'listId': {'type': 'string', 'description': 'Optional list to add them to (see get_icp for list ids)'}, 'linkedinUrls': {'type': 'array', 'items': {'type': 'string'}, 'description': 'LinkedIn profile URLs'}}, 'additionalProperties': False}
analyze_prospects
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: expect up to a few minutes.
输入模式
{'type': 'object', 'properties': {'limit': {'type': 'integer', 'default': 10, 'description': 'Cap when prospectIds is omitted'}, 'prospectIds': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Which prospects to analyze; omit to take those with no signals yet'}}, 'additionalProperties': False}
create_custom_signal
Create a 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.
输入模式
{'type': 'object', 'required': ['name', 'detects'], 'properties': {'name': {'type': 'string', 'description': 'Short display name'}, 'detects': {'type': 'string', 'description': 'What to look for, in plain language'}, 'exampleTitle': {'type': 'string'}, 'exampleDetail': {'type': 'string'}}, 'additionalProperties': False}
draft_email
Draft an 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.
输入模式
{'type': 'object', 'properties': {'language': {'enum': ['english', 'french'], 'type': 'string'}, 'prospectId': {'type': 'string'}, 'regenerate': {'type': 'boolean', 'default': False, 'description': 'Ignore any cached draft'}, 'linkedinUrl': {'type': 'string'}, 'signalIndex': {'type': 'integer', 'default': 0, 'description': 'Which signal to lead with'}}, 'additionalProperties': False}
draft_linkedin_message
Draft a 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.
输入模式
{'type': 'object', 'properties': {'language': {'enum': ['english', 'french'], 'type': 'string'}, 'prospectId': {'type': 'string'}, 'regenerate': {'type': 'boolean', 'default': False}, 'linkedinUrl': {'type': 'string'}}, 'additionalProperties': False}
find_leads_from_signals
Find new leads from signal topics
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.
输入模式
{'type': 'object', 'properties': {'signalType': {'type': 'string', 'description': 'Which signal to source for; omit to use the first enabled one (see list_signals)'}, 'postsPerSignal': {'type': 'integer', 'default': 3}}, 'additionalProperties': False}
get_icp
Get the ideal customer profile
The active ICP: target roles, industries, countries, company sizes, relevant keywords and any exclusions. This is what sourcing and scoring filter against.
只读
输入模式
{'type': 'object', 'properties': {}, 'additionalProperties': False}
get_pipeline_stats
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.
只读
输入模式
{'type': 'object', 'properties': {}, 'additionalProperties': False}
get_prospect
Get one 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.
只读
输入模式
{'type': 'object', 'properties': {'prospectId': {'type': 'string', 'description': 'The prospect id from list_prospects'}, 'linkedinUrl': {'type': 'string', 'description': 'Their LinkedIn profile URL, if the id is unknown'}}, 'additionalProperties': False}
import_sourced_leads
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.
输入模式
{'type': 'object', 'required': ['signalType', 'tokens'], 'properties': {'listId': {'type': 'string'}, 'tokens': {'type': 'array', 'items': {'type': 'string'}, 'description': 'The token values of the candidates to import'}, 'signalType': {'type': 'string', 'description': 'The signalType returned by find_leads_from_signals'}}, 'additionalProperties': False}
list_prospects
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 count, then most recently saved.
只读
输入模式
{'type': 'object', 'properties': {'limit': {'type': 'integer', 'default': 20, 'description': 'How many to return (max 50)'}, 'title': {'type': 'string', 'description': 'Job title contains this text'}, 'offset': {'type': 'integer', 'default': 0}, 'search': {'type': 'string', 'description': 'Free text matched against first name, last name, company and title'}, 'company': {'type': 'string'}, 'country': {'type': 'string'}, 'hasEmail': {'type': 'boolean'}, 'industry': {'type': 'string'}, 'minSignals': {'type': 'integer', 'description': 'Only prospects with at least this many signals'}, 'signalType': {'type': 'string', 'description': 'Only prospects carrying a signal of this type (see list_signals)'}, 'notContacted': {'type': 'boolean', 'description': 'Only prospects with no email sent yet'}, 'enrichmentStatus': {'enum': ['pending', 'enriched', 'failed'], 'type': 'string'}}, 'additionalProperties': False}
list_signals
List signal definitions
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.
只读
输入模式
{'type': 'object', 'properties': {'enabledOnly': {'type': 'boolean', 'default': True}}, 'additionalProperties': False}
mark_email_sent
Mark as contacted
Record that a prospect was emailed outside getcleed, so reporting and follow-ups stay correct.
输入模式
{'type': 'object', 'properties': {'prospectId': {'type': 'string'}, 'linkedinUrl': {'type': 'string'}}, 'additionalProperties': False}
send_email
Send an 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 under Integrations.
可能执行破坏性操作
输入模式
{'type': 'object', 'properties': {'body': {'type': 'string', 'description': 'Omit to use the saved draft'}, 'subject': {'type': 'string', 'description': 'Omit to use the saved draft'}, 'prospectId': {'type': 'string'}, 'linkedinUrl': {'type': 'string'}}, 'additionalProperties': False}
send_linkedin_message
Send a LinkedIn connection request
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.
可能执行破坏性操作
输入模式
{'type': 'object', 'properties': {'message': {'type': 'string', 'description': 'The note, max 300 characters. Omit to use the saved draft'}, 'prospectId': {'type': 'string'}, 'linkedinUrl': {'type': 'string'}}, 'additionalProperties': False}
历史
近期工具变更
已添加
create_custom_signal
2026年9月26日 02:40
已添加
mark_email_sent
2026年9月26日 02:40
已添加
send_linkedin_message
2026年9月26日 02:40
已添加
send_email
2026年9月26日 02:40
已添加
draft_linkedin_message
2026年9月26日 02:40
已添加
draft_email
2026年9月26日 02:40
已添加
analyze_prospects
2026年9月26日 02:40
已添加
import_sourced_leads
2026年9月26日 02:40
已添加
find_leads_from_signals
2026年9月26日 02:40
已添加
add_leads_from_urls
2026年9月26日 02:40
已添加
get_icp
2026年9月26日 02:40
已添加
list_signals
2026年9月26日 02:40
已添加
get_pipeline_stats
2026年9月26日 02:40
已添加
get_prospect
2026年9月26日 02:40
已添加
list_prospects
2026年9月26日 02:40
发现
类似的 MCP 服务器
LinkedIn MCP Server (Salesbot)
cz.salesbot/linkedin-mcp-server
Supports LinkedIn lead discovery, contact enrichment, CRM pipelines, campaign sequencing, message approval and human-reviewed out…
Pro Reach LinkedIn Outreach
ai.proreach/outreach
Supports planning and managing LinkedIn outreach, including templates, leads, confirmation-gated launches, metrics, and replies.
Zevari
ai.zevari/mcp
Supports review-gated LinkedIn prospecting and go-to-market outreach workflows.
neuron
io.github.conquext/neuron
Operates AI chatbots and messaging workflows across WhatsApp and social channels, including contacts, campaigns, conversations, p…
Meta Council
com.meta-council/decision-intelligence
Provides governed workflows for consulting, outreach, sales deals, invoices, marketing campaigns, content approvals, accounting a…
captapi
io.github.CDCStream/captapi
Retrieves social media profiles, posts, engagement metrics, comments, marketplace listings, events, and Meta advertising data acr…
SendIt
io.github.Shree-git/sendit
Plans, generates, approves, schedules, publishes, and analyzes social media content across LinkedIn, Instagram, Threads, TikTok, …
aidelly
io.github.wilzer/aidelly
Supports agency social media operations including content creation, approvals, scheduling, publishing, repurposing, analytics, ec…