The safest LinkedIn MCP for your Agents.
Connect Claude, ChatGPT, Claude Code, Codex, Cursor, VS Code or any remote MCP client to your own LinkedIn account.
Your agent reads your LinkedIn conversations, searches your network, enriches profiles with email and phone, and drafts the messages. You review them and hit send.
https://api.talktohumans.app/mcpLinkedIn has no official MCP server, and its public API doesn't give access to your private messages. Every LinkedIn MCP is third-party, and most fall into one of three groups:
| Open-source scrapers | Cloud LinkedIn tools | TalkToHumans | |
|---|---|---|---|
| Pace | Whatever pace your agent sets | Daily caps sized for campaigns | Human pace, enforced: daily limits plus a gap between every action, per LinkedIn account. Nobody can override them |
| What 100 agent calls do | 100 trips to LinkedIn | 100 trips to LinkedIn, from their servers | Read a synced cache, so no more LinkedIn activity than one call |
| Where LinkedIn actions run | A script driving a browser on your machine | Their servers, often behind proxy IPs | The browser you already use. No cloud automation, no proxy IP |
| Where you work | In your agent's chat | In your agent's chat | Wherever suits the task: your agent's chat, the TalkToHumans app, or right inside LinkedIn and Sales Navigator |
| Who presses send | Usually the agent | The agent or a campaign | You. The MCP only drafts |
No LinkedIn tool is completely risk-free. Here is how TalkToHumans keeps the risk down:
- Human pace, enforced. Every action type has its own conservative daily limit and a slightly random gap between actions, so nothing goes out in bursts. Limits belong to the LinkedIn account, so every teammate and every agent shares them. Nobody can raise them, not even your agent.
- Cache-based sync. Your agent reads a synced copy of your LinkedIn data, not LinkedIn itself. Ask it 100 questions about your inbox and your account sees the same activity as one, with no hopping from profile to profile. The background sync that fills that copy is paced the same way.
- Posts and searches skip your account. Posts, comments, the people engaging with them and people searches come from a data provider, never from your LinkedIn session.
- Runs in your browser. LinkedIn actions go through the browser you already use. No cloud automation, no proxy IPs and no virtual browsers acting on your behalf.
- Work in the chat, the app or LinkedIn. Everything your agent does also lands in the TalkToHumans app and in panels embedded in LinkedIn's own pages. Check conversations, see what's scheduled and take over by hand wherever you are.
- Drafts only. The MCP can write a reply or stage a full follow-up sequence. Nothing goes out until you hit send.
Founders, consultants, sales teams and agencies use it for these jobs, most common first:
- Fresh leads, ready to contact. Your agent works out who you sell to, finds new leads warmest first (people who engaged with you, posts on your topic, then a LinkedIn search by role, company or location), scores them on your ICP and stages a sequence in your voice for each. You review and launch them from one view.
- Find deals buried in your inbox. Scan hundreds of LinkedIn, Sales Navigator and Recruiter threads for the ones where someone is waiting on you, or showed interest and went quiet, every morning if you like.
- Follow up on silent accepts. Follow-ups for people who accepted but never replied, written for each person. They stop when the lead replies, and wait for you to launch them.
- Log chats in your CRM. Combine it with your CRM's MCP to match contacts by LinkedIn URL and log LinkedIn conversations, or use the native HubSpot integration.
- Import a lead list. Bring in a list from an event, a webinar or Sales Navigator, up to 500 profiles at a time, and get a ready-to-work view with first messages drafted.
- Leads already in your network. Describe your ideal customer, and your agent scores your connections. They're already connected to you, so you can message them today.
- Coffees on your next trip. See the people in the city you're visiting on a map, and get coffee invites drafted, to network or sell.
- Leads from post comments. Find posts on a topic or by a competitor, and import the people who commented or reacted, each with a signal saying how.
- Organize your inbox. Set up tags and inboxes that fit your business, then tag hundreds of contacts the way your team already works.
- What works in your outbound. Analyze acceptance rates, reply rates and templates, from connection request to booked meeting, and what to change next.
- Score leads by ICP. Fill an ICP score for every contact, so you can sort them by best fit.
- What works in your content. See which of your posts bring engagement and which bring the people you want to reach, compared with the best and worst posts in your niche.
- Find your quick wins. Ask what you can do today, with little effort, that pays off.
Your agent also gets work email and mobile phone for the people you talk to, from 20+ providers in a waterfall.
Click this link to add TalkToHumans to Claude
Click Add, then Connect, and sign in to TalkToHumans.
On Team and Enterprise plans, only an owner can add it: add it as an owner.
Members then click Connect in Customize > Connectors.
Not showing in a chat? Click + > Connectors and turn TalkToHumans on.
Add it by hand
- Open Customize > Connectors, click + Add > Add custom connector
- Name it "TalkToHumans" and paste the URL:
https://api.talktohumans.app/mcp
- Click Add, then Connect, and sign in to TalkToHumans
- Open ChatGPT plugins, click + and choose Add custom MCP server
- Name it "TalkToHumans" and paste the URL:
https://api.talktohumans.app/mcp
- Choose OAuth, click Create, then sign in to TalkToHumans
Custom MCP servers depend on your ChatGPT plan. On Business, Enterprise and Edu, an admin may need to allow them.
In a terminal, run:
claude mcp add --transport http --scope user talktohumans https://api.talktohumans.app/mcpThen run /mcp in Claude Code, pick talktohumans and choose Authenticate.
Already connected Claude? It shows up in Claude Code with the same account.
In a terminal, run:
codex mcp add talktohumans --url https://api.talktohumans.app/mcpIf no browser opened to sign in, run:
codex mcp login talktohumansThe Codex app and IDE extension share this setup. In the ChatGPT desktop app, add it in Settings > MCP servers.
Click this link to add TalkToHumans to Cursor
Add it by hand
Add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"talktohumans": {
"url": "https://api.talktohumans.app/mcp"
}
}
}Click this link to add TalkToHumans to VS Code
Add it by hand
- Open the Command Palette and run MCP: Add Server
- Choose HTTP and paste the URL:
https://api.talktohumans.app/mcp
- Name it
talktohumans, choose Global, and sign in when VS Code asks
In a terminal, run:
gemini mcp add --transport http talktohumans https://api.talktohumans.app/mcpThen run /mcp auth talktohumans in Gemini CLI.
- On grok.com, open Connectors, then New Connector > Custom
- Paste the URL, then sign in to TalkToHumans:
https://api.talktohumans.app/mcp
- On Perplexity, open Connectors, then Add custom > Remote MCP
- Paste the URL, choose OAuth and Streamable HTTP:
https://api.talktohumans.app/mcp
- Sign in to TalkToHumans
Custom connectors need Perplexity Pro, Max or Enterprise.
- In Le Chat connections, click Add connector, then Custom MCP
- Paste the URL, then sign in to TalkToHumans:
https://api.talktohumans.app/mcp
Add a custom MCP server (Streamable HTTP, OAuth) with this URL, then sign in:
https://api.talktohumans.app/mcp
| Area | Tools |
|---|---|
| Accounts | list_accounts, get_credit_balance |
| Conversations | list_conversations, list_messages, write_message_draft, upload_file |
| Contacts | list_contacts, search_people, import_contacts, get_import_progress, update_contact, delete_contacts, list_field_definitions, create_field_definition, list_tags, update_tag, delete_tag, create_signals |
| Companies | list_companies |
| Content | list_content, search_posts, find_content, import_content, import_content_engagers, track_content, update_content |
| Enrichment | enrich_profile, find_email, find_phone |
| Views | list_views, create_view, update_view, delete_view |
| Templates & sequences | list_templates, create_template, update_template, update_sequence, delete_sequence |
| Reporting | list_activity, get_activity_summary |
| Skills | load_skill |
| Feedback | send_feedback |
write_message_draft saves a draft, a sequence or a connection request for you to review, or clears one. It never sends. Imports, searches, enrichment and tracking use TalkToHumans credits. list_accounts also gives your agent your own LinkedIn profile, for free, so it knows who you are.
MCP (Model Context Protocol) is the open standard that lets AI assistants like Claude, ChatGPT and Cursor use outside tools. A LinkedIn MCP server connects your agent to your LinkedIn data. It can read your conversations, search your network and prepare messages, instead of you copying everything into a chat.
No. LinkedIn doesn't offer an MCP server, and its public API doesn't cover private messages. Every LinkedIn MCP is third-party.
No, and that's on purpose. Your agent can read, sort and draft, down to a full follow-up sequence. Every message that carries your name still gets your approval.
No. TalkToHumans works through your logged-in browser session. Your AI client signs in to TalkToHumans, not to LinkedIn.
Your workspace syncs while your browser is open with the TalkToHumans extension on, newest conversations first. Older message history loads when you open a conversation in TalkToHumans.
Yes. The LinkedIn CLI (tth) is the same workspace from the terminal, for Claude Code, Codex, scripts and cron jobs. It only drafts too. See the CLI docs.
Yes. Every paid plan also includes a REST API for contacts, companies, conversations, content, drafts, views and activity. See the developer docs.
MCP, CLI and API access come with every paid plan, from Starter. Pro adds sequences, post engagers, analytics and CRM integrations.
This repo holds the MCP Registry entry (server.json) and setup docs for the hosted TalkToHumans server. The server runs at https://api.talktohumans.app/mcp, and its code isn't in this repo.
Found a bug or a missing tool? Open an issue.
Built by TalkToHumans.
