Connect Retriever MCP to Cursor, Claude Desktop, and ChatGPT: The Complete Guide

The guide

A guide by Emma Guetta, founder of Retriever

---

Why give your AI tools live B2B intelligence?

Most AI assistants are brilliant at writing code and answering general questions, but completely blind when it comes to the live market.

If you ask Cursor, Claude Desktop, or ChatGPT:

• "Which European B2B SaaS companies raised Series A in the last 6 months and are currently expanding their sales team?"
• "Find the verified work email and mobile phone for the VP Sales at Pigment."
• "Check what advertising campaigns Pennylane is running on Meta right now."

The model will either hallucinate convincing-sounding names, quote obsolete information from its pre-training cutoff, or tell you to go look it up on LinkedIn manually.

The Model Context Protocol (MCP), originally created by Anthropic and rapidly adopted by Cursor and OpenAI, solves this by giving AI models a standardized way to call external tools and retrieve structured context in real time.

By connecting Retriever's MCP Server to your AI environment, you give your models direct programmatic access to:

• 35M+ indexed company profiles across Europe and the US,
• Live hiring intent extracted from global job boards,
• Fresh website and tech-stack crawling signals,
• Verified contact intelligence (work emails, direct mobile numbers, LinkedIn URLs),
• Autonomous prospecting agents that can research markets, score ICP fit from 0 to 100 with cited evidence, and build full lead tables.

This guide walks you through the exact setup for Cursor, Claude Desktop, and ChatGPT, followed by real-world workflows and troubleshooting advice.

---

The three clients at a glance

Before configuring your tools, here is how each platform connects to Retriever:

---

Step 0 — Get your Retriever API key

All three platforms connect to the same underlying Retriever backend. You will need an active API key:

1. Sign in to your account at app.retriever.run.
2. Click Settings in the left sidebar, then navigate to API Keys.
3. Click Generate New Key.
4. Copy your key (it starts with ret_sk_...). Keep it safe—it gives access to your credit balance.

(New accounts come with free credits to test all capabilities).

---

1. Setting up Retriever in Cursor

Cursor is one of the most powerful hosts for MCP because its AI agent (Cursor Composer) can query Retriever tools while simultaneously writing code, populating CSV files, or scaffolding internal scrapers.

Cursor supports two setup methods: through its graphical settings interface, or through a project-scoped .cursor/mcp.json file.

Method A: Via Cursor Settings (Fastest & Global)

This method makes Retriever available across all your Cursor windows and projects.

1. Open Cursor.

2. Open Settings:

   • macOS: Press Cmd + ,
   • Windows / Linux: Press Ctrl + ,

3. In the sidebar, select Features, then scroll down to MCP Servers (or Tools & MCP depending on your Cursor version).

4. Click the + Add New MCP Server button.

5. Enter the following parameters:

   • Name: retriever
   • Type: http
   • URL: https://api.retriever.run/mcp
   • Headers:

6. Click Save.

Within a few seconds, a green status circle will appear next to retriever, indicating that Cursor has connected and registered all tools (service_discover, service_execute, retriever_research_start, table_*, etc.).

---

Method B: Via .cursor/mcp.json (Project-Scoped)

If you work in a team repository and want everyone on the team to share the same MCP configuration, create a .cursor/mcp.json file at the root of your project:

Running over local stdio in Cursor

If your network or corporate firewall blocks outgoing HTTP streaming connections from Cursor, you can also run Retriever locally via stdio:

Verification in Cursor:
Open Composer (Cmd + I on Mac, Ctrl + I on Windows). Click the tool selector icon at the bottom of the input. You should see retriever listed with all available capabilities.

---

2. Setting up Retriever in Claude Desktop

Claude Desktop runs MCP servers locally on your machine using standard input/output (stdio). It invokes the official Retriever MCP package via npx in the background.

Step 1: Open your Claude Desktop configuration file

The configuration file is stored in your user profile:

• On macOS:
  ~/Library/Application Support/Claude/claude_desktop_config.json
• On Windows:
  %APPDATA%\Claude\claude_desktop_config.json

Shortcut: In Claude Desktop, click Claude in the top menu → Settings → Developer → click Edit Config. This will automatically open the folder containing claude_desktop_config.json in Finder or File Explorer.

Step 2: Add the Retriever configuration

Open claude_desktop_config.json in your favorite text editor. If the file is empty, paste the following JSON. If it already contains other MCP servers, add retriever inside the mcpServers object:

Replace YOUR_RETRIEVER_API_KEY with your actual key starting with ret_sk_.

Step 3: Completely restart Claude Desktop

Saving the file is not enough: Claude Desktop only initializes MCP servers on boot.

1. Completely quit Claude:
   • On macOS: Press Cmd + Q (do not just click the red close circle).
   • On Windows: Right-click the Claude icon in the system tray and select Quit.
2. Relaunch Claude Desktop.

Step 4: Verify the connection

Look at the bottom-right corner of the prompt box: you should see a small hammer icon (🔨). Click it. A popover will list all registered Retriever tools:

• credits
• service_discover
• service_inspect
• service_execute
• retriever_research_start
• retriever_build_list_start
• table_get_rows
• sequence_list

---

3. Setting up Retriever in ChatGPT

Unlike desktop tools that run local processes on your computer, ChatGPT operates entirely in OpenAI's cloud. It requires a remote HTTPS endpoint that supports the Streamable HTTP MCP specification.

Retriever's public server at https://api.retriever.run/mcp implements the official OAuth 2.1 protocol with dynamic client registration and PKCE S256 (/.well-known/oauth-authorization-server). This allows ChatGPT to link directly to your Retriever workspace without even requiring you to copy-paste a token.

Prerequisites

• A paid ChatGPT plan: ChatGPT Plus, Team, Pro, or Enterprise.
• Access to Developer Mode or Connectors / Apps in ChatGPT.

Step-by-step Setup

1. Open ChatGPT on the web (chatgpt.com).
2. Click your profile photo in the bottom-left corner and open Settings.
3. In the settings modal, navigate to Security & login (or Connectors / Apps).
4. Turn on the Developer Mode toggle.
5. In the Connectors section, click Create connector (or Add app).
6. Fill in the connection details:
   • Name: Retriever
   • Server URL: https://api.retriever.run/mcp
7. Authentication:
   • OAuth 2.1 (Instant & Recommended): ChatGPT will automatically query Retriever's .well-known discovery endpoints. A pop-up window from app.retriever.run will ask you to log in and authorize the connection. Click Allow.
   • Manual Bearer Token: If your organization requires static credentials, choose Bearer authentication and paste your Retriever API key.
8. Click Save.

Using Retriever in ChatGPT

1. Start a new chat in ChatGPT.
2. In the message composer, click the + (plus) button on the left.
3. Select Retriever from the list of available apps.
4. You can now prompt ChatGPT to run live market lookups and company research directly in the conversation.

---

The Retriever tools reference

Once connected, your AI assistant has access to four core capability families:

Host Agent (Cursor / Claude / ChatGPT)
  │
  ├── 1. Atomic Services ───────> service_discover / service_inspect / service_execute
  │                              (Emails, Direct Phones, Ads, Tech Stack, Jobs)
  │
  ├── 2. Autonomous Research ───> retriever_research_start / retriever_research_get
  │                              (Live web crawling, evidence synthesis, dossier)
  │
  ├── 3. List Building & ICP ───> retriever_build_list_start / table_get_rows
  │                              (Calibrate sources, evaluate fit score 0–100)
  │
  └── 4. Cold Outreach ─────────> sequence_create / sequence_enroll_leads / inbox_list
                                 (Multi-step LinkedIn & Email campaigns)

1. Atomic Services (service_*)

Retriever packages dozens of B2B data providers and live crawlers into standardized atomic capabilities called Services. The agent follows a disciplined 3-step loop:

1. service_discover: The agent describes its intent (e.g. "find work email", "meta ads", "french company siren"). Retriever returns the matching canonical service name.
2. service_inspect: The agent reads the exact schema, required parameters, and credit cost.
3. service_execute: The agent executes the service and receives clean JSON with source evidence.

2. Autonomous Research (retriever_research_*)

For questions that require checking multiple sources across the web (e.g. analyzing a competitor's pricing tiers or investigating whether a company has a dedicated security team), retriever_research_start spins up an autonomous research sub-agent. The agent crawls sites, verifies claims, and returns a cited dossier.

3. Lead Qualification & Tables (retriever_build_list_* & table_*)

Instead of dumping raw lists into the chat, the agent can create structured tables in your Retriever workspace. Each lead is evaluated against your custom Ideal Customer Profile (ICP), receiving a fit score between 0 and 100 along with explicit reasoning.

4. Outreach Sequences (sequence_* & inbox_*)

Your agent can draft multi-channel outreach campaigns (combining automated LinkedIn profile visits, connection requests, and personalized emails), enroll leads from tables, and monitor incoming replies from the shared inbox.

---

4 Real-world workflows to try

Here are four prompts you can paste directly into Cursor, Claude Desktop, or ChatGPT once your MCP is connected.

Workflow 1: Account discovery with precise ICP filtering

Prompt:
"Using Retriever, find 5 B2B SaaS companies headquartered in France that have raised Series A or B, use Stripe or Chargebee for billing, and are currently hiring software engineers. For each, give me their domain, ICP score, and the proof."

What happens:

1. The model calls service_discover for company search signals.
2. It queries Retriever's company database filtering by country, funding stage, and tech stack.
3. It validates recent job postings to confirm active engineering hiring.
4. It outputs a clean comparison table with links to original sources.

---

Workflow 2: Finding verified decision-maker contacts

Prompt:
"I need to reach out to Pennylane about their automated accounting integration. Use Retriever to find their Head of Sales or VP Sales, and return their verified work email, direct mobile phone number, and LinkedIn URL."

What happens:

1. The model calls service_execute with findPersonAtCompany specifying the company domain (pennylane.com) and target seniority (VP / Head of).
2. It executes findWorkEmail and findMobilePhone on the identified contact.
3. It returns the contact's direct details along with verification status (e.g., SMTP deliverability check).

---

Workflow 3: Generating an account briefing dossier before a sales call

Prompt:
"I have a discovery call in 30 minutes with Dataiku. Use Retriever to pull a full intelligence dossier: recent funding rounds, open roles in their revenue team, tech stack detected on their marketing site, and active Meta ad copy."

What happens:

1. The model invokes retriever_research_start and service_execute for ad signals.
2. It collects active advertising creative angles, recent leadership hires, and technographic signatures.
3. It produces an executive 1-page pre-call brief highlighting pain points you can address during the call.

---

Workflow 4: Autonomous list building and sequence drafting

Prompt:
"Start a list-building mission on Retriever called 'FinTech Growth 2026'. Target 20 European FinTech scale-ups that hired a new CMO in the last 90 days. Once the table is ready, draft a 3-step outreach sequence tailored to each company's recent announcements."

What happens:

1. The model calls retriever_build_list_start.
2. Retriever provisions a persistent table in your workspace and streams qualified leads into it.
3. The model calls sequence_create to set up a personalized 3-step cadence (Day 1: LinkedIn connection with custom context; Day 3: Email referencing CMO hire; Day 7: Follow-up case study).

---

Troubleshooting & FAQ

401 Unauthorized or invalid_token

• Cause: The API key is missing, expired, or contains whitespace.
• Fix: Check that your key starts with ret_sk_. In claude_desktop_config.json, verify that RETRIEVER_API_TOKEN matches the exact string. If using Cursor, check that the header is formatted as Authorization: Bearer ret_sk_....

402 Payment Required or insufficient_credits

• Cause: Your account balance has reached 0 credits.
• Fix: Run the credits tool in your agent to inspect your wallet balance. You can add credits anytime from app.retriever.run/settings.

The hammer icon (🔨) does not appear in Claude Desktop

• Cause: Claude Desktop failed to start the background process.
• Fix:
  1. Verify that Node.js (v18 or newer) is installed on your computer by running node -v in your terminal.
  2. Ensure you didn't leave a trailing comma or syntax error in claude_desktop_config.json.
  3. Ensure you completely quit Claude (Cmd + Q on macOS) rather than simply minimizing the window.

ChatGPT connector fails to authenticate

• Cause: Browser cookie blocking or stale redirect.
• Fix: Ensure third-party cookies are allowed for retriever.run. If the pop-up consent window fails to complete, select Bearer Token authentication in ChatGPT settings and paste your ret_sk_ key directly.

---

Summary & Next Steps

Connecting Retriever via MCP transforms your AI assistants from text generators into autonomous revenue team members:

• Cursor becomes an automated lead-generation terminal.
• Claude Desktop acts as an on-demand market intelligence analyst.
• ChatGPT allows your entire sales and marketing team to query real B2B data on the fly.

To get started, generate your key at app.retriever.run and copy the configuration snippet for your assistant.