Connect LinkedIn to Codex
Point OpenAI Codex at Crispy's LinkedIn MCP server. Search, message, and automate LinkedIn from the Codex CLI - agentic LinkedIn, no extension.
Can Codex send LinkedIn connection requests and messages for me?
OpenAI Codex can send LinkedIn connection requests and messages for you once Crispy is added to ~/.codex/config.toml, using the Crispy send_invitation tool for connection requests and send_message for new or existing conversations, all from the Codex CLI.
You describe the job in plain language. Codex picks the tools and makes the calls from your own connected LinkedIn account.
How do I set up the OpenAI Codex LinkedIn integration via MCP?
The OpenAI Codex LinkedIn integration uses MCP, so setup means adding an [mcp_servers.crispy] table to ~/.codex/config.toml that runs npx -y mcp-remote with the Crispy endpoint and your Crispy key, then starting a new Codex session.
- 1
Connect LinkedIn and copy your API key
Sign up, connect your account from the dashboard, and copy your key (it starts with
crispy_) - 2
Add Crispy to config.toml
Edit
~/.codex/config.tomland paste the block below with your key - 3
Restart Codex
Start a new session. Codex auto-discovers every LinkedIn tool - ask it to do anything that touches LinkedIn.
[mcp_servers.crispy] command = "npx" args = [ "-y", "mcp-remote", "https://crispy.sh/api/mcp", "--header", "Authorization: Bearer YOUR_API_KEY" ]
How do I run LinkedIn prospecting from the Codex CLI?
LinkedIn prospecting from the Codex CLI starts with a plain-language prompt that describes the people you want to reach, and Codex then calls the Crispy search_people tool to find them and send_invitation to send each one a connection request.
Outreach from the CLI
Run prospect search, draft personalized notes, and send connection requests from the Codex CLI. Describe the target and it calls the right tools.
“Find CTOs at Series A startups and send each a personalized connection request”
Data pulls and enrichment
Ask Codex to pull LinkedIn profiles, company data, and conversation history, and enrich your lead lists straight from the terminal.
“Enrich this CSV of leads with their LinkedIn profile data and company size”
Automated LinkedIn workflows
Chain search, messaging, and follow-up into a single agent task. Codex runs the workflow; Crispy keeps it inside safe limits.
“Message everyone who accepted my request this week and flag replies that sound like buying signals”
Inbox triage
Let Codex surface the messages that need you. Pull unread threads, rank the warm ones, and draft replies in your voice.
“Pull my unread LinkedIn messages and flag the ones that look like warm leads”
Why MCP Instead of a REST API?
When you connect Crispy via MCP, Codex doesn't just get API access - it gets tool awareness. It knows what each LinkedIn tool does, what parameters it takes, and how to chain them into a workflow.
Ask it to “find prospects and send personalized outreach” and it will use search_people, get_profile, and send_invitation in the right order - without you writing a single API call.
You still get full REST access too. Crispy supports both MCP and standard HTTP requests through the same endpoint.
How much does Crispy cost for Codex?
Crispy costs $49/seat/mo, or $39/seat/mo billed annually ($468/yr), and each seat connects one LinkedIn account that OpenAI Codex can use to search people, send messages, and run prospecting from the Codex CLI. One plan, everything included.
View full pricingFrequently Asked Questions
Can Codex send LinkedIn connection requests and messages for me?
Yes. After you add Crispy to ~/.codex/config.toml, OpenAI Codex can send LinkedIn connection requests with the Crispy send_invitation tool and messages with send_message. You describe the task in plain language and Codex makes the calls from your own connected LinkedIn account. Crispy applies daily safety limits to invitations and messages.
How do I run LinkedIn prospecting from the Codex CLI?
Start a Codex session with Crispy configured and describe the people you want to find. Codex calls the Crispy search_people tool to pull matching LinkedIn profiles, get_profile to read the details, and send_invitation to reach out. You can also ask Codex to write the results to a CSV file in your working directory.
How does the OpenAI Codex LinkedIn integration work via MCP?
Codex reads MCP servers from ~/.codex/config.toml. The Crispy entry is an [mcp_servers.crispy] table that runs npx -y mcp-remote against the Crispy endpoint with your key as a bearer header. Start a new Codex session after you save the file, and the LinkedIn tools become available to the agent.
Why use the mcp-remote bridge for Codex?
Crispy authenticates with an Authorization: Bearer header. The mcp-remote bridge connects to the remote Crispy endpoint and injects that header for you, which is the dependable way to attach a header-authenticated remote MCP server from config.toml.
Do I need Node installed?
The mcp-remote bridge runs via npx, so you need Node.js available. Any client that can send a custom header can also point directly at https://crispy.sh/api/mcp.
Run LinkedIn workflows from the AI client you already use.
Create your account, connect LinkedIn, create an API key, then add Crispy to your client. Review the docs for supported workflows and safety controls.