mcpField
L
Linkedcamp

Linkedcamp

Remote
linkedcamp.comBusiness & Marketing0Updated 5d ago

About Linkedcamp

LinkedCamp's hosted MCP server lets lead-generation agencies manage LinkedIn and email outreach from an AI assistant. Its grouped tools cover campaigns, inbox, leads, analytics and reporting, with configurable access and confirmation for destructive actions.

Key features

  1. 01Create and manage outreach campaigns
  2. 02Write multi-step sequences
  3. 03Triage LinkedIn and email inboxes
  4. 04Manage prospects and lead actions
  5. 05View analytics and client reports
  6. 06Control tool access and destructive actions

Use cases

  1. 01Launch agency outreach campaigns
  2. 02Review and answer incoming replies
  3. 03Track campaign and account performance
  4. 04Prepare client reports

MCP support

The hosted remote MCP server connects MCP clients to LinkedCamp over Streamable HTTP, using OAuth 2.1 with PKCE or an API key. Its tools support outreach management, and access levels and destructive-action confirmations govern operations.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.linkedcamp.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

LinkedCamp

LinkedCamp MCP server

Run LinkedIn and email outreach from ChatGPT, Claude, Cursor or any MCP client.
LinkedCamp MCP connector mcptry Linkedcamp MCP server Linkedcamp Mcp on AI Agents Listing

Documentation · Product page · Support


LinkedCamp is LinkedIn and email outreach for lead-gen agencies. This is its official hosted MCP server: build and launch campaigns, write multi-step sequences, triage the unified inbox, manage prospects and pull client reports — all from an AI assistant.

Nothing to install and nothing to run. The server is hosted by LinkedCamp; you point your client at one URL.

https://mcp.linkedcamp.com/mcp
TransportStreamable HTTP (remote)
AuthOAuth 2.1 with PKCE and dynamic client registration, or an X-Api-Key header
Tools133 across 14 groups — 64 read-only, 69 write, 28 flagged destructive
RequiresA LinkedCamp Pro or Agency plan. 14-day free trial.
Registrycom.linkedcamp/mcp

Connect

Claude

Settings → Connectors → Add custom connector, then paste the URL above and sign in. Claude handles OAuth for you.

ChatGPT

Install the LinkedCamp app from the ChatGPT directory, or add the URL above as a custom connector. Sign-in is the same OAuth flow.

Cursor, VS Code, Windsurf and other config-file clients
{
  "mcpServers": {
    "linkedcamp": {
      "url": "https://mcp.linkedcamp.com/mcp"
    }
  }
}
Claude Code
claude mcp add --transport http linkedcamp https://mcp.linkedcamp.com/mcp
Without OAuth

Any client that can set a header may send your API key directly instead of running the OAuth flow:

X-Api-Key: <your LinkedCamp API key>

Your key is under Settings → Integrations in LinkedCamp. Treat it as a password: it carries the same access your account has.

What you can do with it

GroupToolsWhat it covers
core3Orientation — the plan, permissions and the enum vocabulary
campaigns19Create, configure, source prospects, launch, and manage once live
flows9Author the sequence a campaign runs, and see how each step performs
leads14Prospects, their history, and the scheduled actions behind it
accounts13The LinkedIn accounts and mailboxes campaigns send from, and their limits
inbox9LinkedIn and email conversations — where replies land and are answered
analytics5Performance by campaign, sending account and whole account
library20Tags, exclusion rules, saved copy, merge fields, blocked dates
personas5Ideal-customer definitions a QUALIFIER step scores leads against
agents13Agents that reply to prospects and book meetings, and their knowledge base
content6LinkedIn posts: drafting, scheduling and the publishing calendar
crm7Connected CRMs and manual follow-up around a conversation
automation4Account-wide, event-driven workflows
settings6Notifications, profile preferences and the team roster

Full reference: docs.linkedcamp.com/mcp/overview

Safety

Outreach reaches real people, so the server is built to make that visible rather than convenient.

  • 28 tools are annotated destructive. Clients surface that in their approval prompt, so a human confirms before anything is deleted or sent. The set is wider than "it deletes something" — launching a campaign, sending a test email, and changing who gets messaged are all flagged, because each reaches outside the account or is hard to undo.
  • You choose what a connection may do when you sign in. Read only, Read and write, or Full access. Read only reaches the 64 tools that change nothing; Read and write adds ordinary writes but withholds the destructive ones; Full access reaches everything and still asks before each destructive call.
  • Your plan and team permissions still apply. A section you cannot open in the web app is hidden from the tool list and refused on the call.
  • Some things are deliberately not exposed at all: rotating your API key, connecting a LinkedIn account (that flow takes a password and a verification PIN), CRM credentials, and billing.

A smaller tool list

Some clients are slower to start against 133 tool definitions, because they read every one before answering anything. Name the groups you want:

https://mcp.linkedcamp.com/mcp?toolsets=campaigns,flows,analytics

Leaving it off gives you everything. core is always included, and an unrecognised name is ignored rather than leaving you with an empty connection.

Support

This repository holds the install documentation and client manifests only. The server itself is hosted by LinkedCamp and is not open source.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.