Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "linkedin-mcp": {
      "type": "http",
      "url": "https://www.apex.new/mcp"
    }
  }
}

claude mcp add --transport http linkedin-mcp https://www.apex.new/mcp

[mcp_servers.linkedin-mcp]
url = "https://www.apex.new/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "linkedin-mcp": {
      "type": "remote",
      "url": "https://www.apex.new/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "linkedin-mcp": {
      "type": "http",
      "url": "https://www.apex.new/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=linkedin-mcp&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vd3d3LmFwZXgubmV3L21jcCJ9"
}

{
  "servers": {
    "linkedin-mcp": {
      "type": "http",
      "url": "https://www.apex.new/mcp"
    }
  }
}

{
  "mcpServers": {
    "linkedin-mcp": {
      "httpUrl": "https://www.apex.new/mcp"
    }
  }
}

extensions:
  "linkedin-mcp":
    enabled: true
    name: "linkedin-mcp"
    type: streamable_http
    uri: "https://www.apex.new/mcp"
    timeout: 300

Quality 79 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene71 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
fail
tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_setup_steps (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); about_apex (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); first_plays (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
pass
tools.token_costabout 176 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changes1 tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

3 tools, about 176 tokens to load them all · tool set 81dfa45cb94b · tools last changed 2026-10-04 · checked 2026-10-20 10:35 UTC

Tool changes

2026-10-04get_setup_stepschangeddescription
before
The 5-step flow to connect an AI agent to the real Apex MCP server: LeadShark account → LinkedIn → 24h Apex unlock → mount MCP → first Loadout.
after · 91% of words in common
The 5-step flow to connect an AI agent to the real Apex MCP server: LeadShark account → LinkedIn → 72h Apex unlock → mount MCP → first Loadout.

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 90 / 100

provenance90

liveness100

freshness65

hygiene100

+repository +namespace-matches-repo +website +reachable +uptime-100% ~updated-107d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://www.apex.new/mcp` streamable-http	none	yes	100%	314 ms	2025-06-18	2026-10-20

Tools (3)

`about_apex`	Read-only: returns what Apex by LeadShark is, tier pricing, and the URL of the real authenticated MCP server. Call this first — this endpoint is a discovery stub with no LinkedIn powers.
`first_plays`	Read-only: returns copy-paste starter prompts for the first session after connecting the real Apex server — verify, discover, enrich, act.
`get_setup_steps`	The 5-step flow to connect an AI agent to the real Apex MCP server: LeadShark account → LinkedIn → 72h Apex unlock → mount MCP → first Loadout.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "io.github.rzere/linkedin-mcp",
  "icons": [
    {
      "src": "https://www.apex.new/brand/leadshark-black.png",
      "sizes": [
        "256x256"
      ],
      "mimeType": "image/png"
    }
  ],
  "title": "Apex by LeadShark — discovery",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://www.apex.new/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "repository": {
    "url": "https://github.com/rzere/linkedin-mcp",
    "source": "github"
  },
  "websiteUrl": "https://www.apex.new",
  "description": "No-auth discovery endpoint for Apex by LeadShark — governed LinkedIn hands for AI agents."
}