Get AngelList Link

Connect AngelList Link

The Model Context Protocol (MCP) server provides a standardized interface that allows any compatible AI model or agent to access your AngelList data in a simple and secure way.

Connect to our MCP server natively in Claude, ChatGPT, Grok, and other clients or use the mcp-remote module for backwards compatibility with clients that do not support remote MCP.

The AngelList MCP server has tools for finding and reading your fund data in AngelList, including firms, vehicles, capital accounts, assets, distributions, financial statements, and documents, with more functionality on the way.

For help getting started after setup, see some of our example prompts. If you run into issues in the setup, reach out to your AngelList account team.

Setup

General

Our MCP server uses Streamable HTTP as the primary transport, accessible at the following address. The interactive setup flow uses OAuth 2.1 with dynamic client registration.

https://mcp.angellist.com/mcp

In every tool, connecting works the same way: add AngelList, then sign in with your regular AngelList account when the browser opens. It's the same email and password you use for the dashboard. There are no API keys or credentials to manage.

For instructions for specific clients, read on.

Claude

Navigate to the connectors page and connect AngelList. On Claude desktop, you can also go to Settings > Connectors and add the AngelList connector.

ChatGPT

Custom connectors in ChatGPT require a Plus, Pro, Business, Enterprise, or Edu plan with Developer Mode enabled.

Click your account icon, then Settings > Apps & connectors > Advanced settings, and toggle Developer mode on.

In Apps & connectors, click Create. Name it AngelList, enter https://mcp.angellist.com/mcp, confirm the authentication method is OAuth, and click Create.

In a new chat, enable AngelList from the message bar and ask about your fund data.

Grok

Custom connectors are available on Grok's paid plans. For Grok Business and Enterprise, a team admin must first provision the connector.

Go to grok.com/connectors and click New Connector, then select Custom.

Enter https://mcp.angellist.com/mcp as the MCP server URL.

Perplexity

Custom remote connectors require Perplexity Pro or Max.

Open Perplexity and go to Settings > Connectors > Add Connector > Advanced.

Name it AngelList, enter https://mcp.angellist.com/mcp, and save.

OpenClaw

Save the server definition and log in:

openclaw mcp set angellist '{"url":"https://mcp.angellist.com/mcp","transport":"streamable-http","auth":"oauth"}'

openclaw mcp login angellist

OpenClaw prints an authorization URL. Approve it in your browser, then verify the connection with:

openclaw mcp doctor angellist --probe

Hermes Agent

Add the following to ~/.hermes/config.yaml:

mcp_servers:
  angellist:
    url: "https://mcp.angellist.com/mcp"
    auth: oauth

On first connect, Hermes prints an authorize URL and opens your browser to complete the AngelList sign-in.

Claude Code

claude mcp add --transport http angellist https://mcp.angellist.com/mcp

Then run /mcp once you've opened a Claude Code session to go through the authentication flow.

Codex

The setup steps for the MCP server are the same regardless of whether you use the IDE Extension or the CLI since the configuration is shared.

Configuration via CLI:

Run the following command in Terminal:

codex mcp add angellist --url https://mcp.angellist.com/mcp

This will automatically prompt you to log in with your AngelList account and connect it to your Codex.

Note: If this is the first time you are using an MCP in Codex you will need to enable the rmcp feature for this to work. Add the following into your ~/.codex/config.toml:

[features]
experimental_use_rmcp_client = true

Configuration through environment variables:

Open the ~/.codex/config.toml file in your preferred editor

Add the following:

[features]
experimental_use_rmcp_client = true

[mcp_servers.angellist]
url = "https://mcp.angellist.com/mcp"

Run codex mcp login angellist to move through the authentication flow.

Cursor

To add the MCP to Cursor, you can install by clicking here, or add it manually: open Cursor Settings > MCP > Add new MCP server, or add the following to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "angellist": {
      "url": "https://mcp.angellist.com/mcp"
    }
  }
}

Gemini CLI

gemini mcp add --transport http angellist https://mcp.angellist.com/mcp

Then run /mcp auth angellist inside a Gemini CLI session to go through the authentication flow.

Visual Studio Code (GitHub Copilot)

CTRL/CMD + P and search for MCP: Add Server.

Select Command (stdio)

Enter the following configuration, and hit enter.

npx mcp-remote https://mcp.angellist.com/mcp

Enter the name AngelList and hit enter.

Activate the server using MCP: List Servers and selecting AngelList, and selecting Start Server.

Windsurf

CTRL/CMD + , to open Windsurf settings.

Under Scroll to Cascade → MCP servers

Select Add Server → Add custom server

Add the following:

{
  "mcpServers": {
    "angellist": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.angellist.com/mcp"]
    }
  }
}

Others

Hundreds of other tools now support MCP servers, you can configure them to use AngelList's MCP server with the following settings:

Command: npx

Arguments: y mcp-remote https://mcp.angellist.com/mcp

Environment: None

Next Steps

Common use cases

The MCP server lets you work with your AngelList data from any compatible AI client. To help get started with the AngelList MCP tooling, feel free to copy some example prompts into your own client to explore what's possible.

▾Quarterly LP update

Use case

Use this workflow to turn the latest quarterly financials into a ready-to-send LP update, grounded in the fund's reported figures.

Example prompt

Draft a quarterly LP update for the fund below. Pull the latest financial statement and the prior quarter's for comparison, and use reported metrics exactly as they appear (paid-in capital, NAV, TVPI, DPI, IRR, distributions, fees) rather than recomputing them. Include a snapshot table comparing the two quarters, capital called and deployed, valuation changes, and a short look ahead. If a figure is missing, say so instead of estimating.

[Fund name]

▾Portfolio performance review

Use case

Use this workflow to review how a fund's portfolio is performing, position by position, using the latest reported valuations.

Example prompt

Review the fund's portfolio using its assets and latest financial statement. Show each position's cost, fair value, and unrealized gain or loss, flag markups and markdowns since the prior statement, and note which positions are still held at cost. List the reported fund-level metrics (TVPI, DPI, IRR, NAV) without recomputing them.

[Fund name]

▾Capital call check-in

Use case

Use this workflow to check where a capital call stands and how much has been called to date.

Example prompt

List the fund's recent capital calls with dates and amounts, then detail the most recent one: amount called, total called to date against commitments, and how much has been contributed so far. Lead with a short summary, and do not estimate amounts that are not recorded.

[Fund name]

▾LP position summary

Use case

Use this workflow to answer an LP's question about their position using reported balances, ready to paste into a reply.

Example prompt

Summarize this partner's position in the fund from their capital account: commitment, contributed capital, and distributions received, with dates and allocations. Then draft a short note I can send to the LP using only reported figures. If they hold positions in more than one vehicle, cover each separately.

[LP name]

[Fund name]

▾Subscription pipeline

Use case

Use this workflow to see where every LP stands in the subscription process during a raise or ahead of a close.

Example prompt

List the vehicle's subscriptions grouped by state, from initial interest through signing and funding, with totals for committed, signed but unfunded, and funded. Flag subscriptions that appear stalled, and end with the most recent closes and the commitments they accepted.

[Vehicle name]

▾Company exposure across vehicles

Use case

Use this workflow to see your total exposure to a single company across every vehicle you manage.

Example prompt

Find every investment in this company across my vehicles, including funds, SPVs, and rolling fund quarters. Report each position's vehicle, instrument, cost, and reported value, then total the exposure. Note any deployment currently in progress, and do not conflate similarly named companies.

[Company name]