Where to Find MCP Settings in Cursor (2026): Cursor MCP Guide

Where to find MCP settings in Cursor (2026): open Customize in the Cursor sidebar to add, enable or disable MCP servers, or edit the config file directly — ~/.cursor/mcp.json for every project, .cursor/mcp.json in the project root for one project. Checked against the official Cursor docs in October 2026.

If you searched cursor mcp, you're probably trying to do one of two things: figure out how to wire your first MCP server into Cursor (this post covers the end-to-end recipe), or debug why a server you already added isn't showing up as tools the agent can call. We cover both. The MCP support in Cursor is feature-complete — the same servers that work in Claude Desktop, Claude Code, or any other MCP client work here, no code changes.

Disclosure: we make Human Browser, which ships an MCP server for stealth browser work. We'll cover the OpenClaw + Cursor + Human Browser MCP setup as one of the three recommended first installs.

Contents

1. What MCP is, in one paragraph
2. Cursor IDE MCP settings: where to find them in 2026
3. Cursor MCP support: official docs (2026)
4. The config format
5. Three servers worth installing first
6. Debugging tools that don't show up
7. Pairing Cursor with Human Browser MCP
8. FAQ

What MCP is, in one paragraph

The Model Context Protocol is a standard for giving an LLM agent typed tools. An MCP server is a process that exposes a set of named tools (github.create_issue, filesystem.read_file, browser.navigate). An MCP client — Cursor in our case, but also Claude Code, Claude Desktop, ChatGPT Desktop, Continue.dev — calls those tools generically. The protocol handles handshake, capability discovery, calls, and streaming. The point is that you don't bake in support for every API; you discover tools at runtime.

Cursor and the MCP ecosystem stay separately maintained. Servers improve; your IDE doesn't have to ship to use them.

Cursor IDE MCP settings: where to find them in 2026

Checked Oct 2026 against the official Cursor docs. Current Cursor builds no longer have a separate MCP tab in settings: MCP servers sit on the Customize page together with plugins, skills, rules and hooks.

1. In the app: Customize in the sidebar. Open Customize from the Cursor sidebar. This is where you install MCP servers from the Cursor Marketplace ("Add to Cursor", with OAuth sign-in where the server needs it), see your personal, workspace and team MCP servers, and toggle a server on or off without deleting it.
2. Global config file: ~/.cursor/mcp.json. Create it in your home directory for MCP servers you want available in every project.
3. Project config file: .cursor/mcp.json. Create it in the project root for servers specific to that project. Commit it if you want everyone on the team to get the same servers when they open the repo.
4. Logs: Output panel → MCP Logs. Open the Output panel (Cmd+Shift+U) and pick "MCP Logs" from the dropdown to see server start-up, tool calls and errors.

Older Cursor builds showed MCP under Cursor Settings (labelled "MCP", later "Tools & Integrations"). If you are on one of those, the same two mcp.json files apply — the JSON file is the source of truth either way, and works better for anything non-trivial (env vars, version control).

Cursor MCP support: official docs (2026)

Cursor's official MCP documentation is at cursor.com/docs/mcp (the old docs.cursor.com/context/model-context-protocol link now redirects to cursor.com/docs). The Customize page itself is documented at cursor.com/docs/customize-cursor. As of October 2026 the docs list support for MCP tools and the MCP Apps extension, local STDIO servers (command, args, env) and remote servers (url), variable interpolation such as ${workspaceFolder} in mcp.json, and team-level allowlists for enterprise admins. By default Cursor asks for approval before an agent uses an MCP tool.

The config format

One top-level key, mcpServers. Each entry has command, args, and env:

{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_..."
      }
    },
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/Users/you/code",
        "/Users/you/Documents/notes"
      ]
    },
    "human-browser": {
      "command": "npx",
      "args": ["-y", "@virixlabs/humanbrowser-mcp"],
      "env": {
        "HB_TOKEN": "hb_live_..."
      }
    }
  }
}

That's the entire format. The minor extras:

• disabled: true on an entry skips it without removing the JSON. Useful for "turn off Stripe MCP for this debugging session."
• autoApprove: ["read_file", "list"] (per-server) — array of tool names the agent can call without prompting you. Use for read-only operations. Leave writes off the list so you confirm them.

Restart Cursor after editing the file. To check whether a server started, open the Output panel and pick MCP Logs.

Three servers worth installing first

From the wider MCP ecosystem, three give immediate, durable value in a Cursor setup:

1. GitHub MCP

@modelcontextprotocol/server-github. The agent can list issues, read PR diffs, post review comments, create branches, merge PRs (with permissions). The first "summarise the failing CI on PR #1234" or "find the open issues mentioning 'timeout'" query justifies it.

2. Filesystem MCP (scoped)

@modelcontextprotocol/server-filesystem with the allowed roots restricted to the directories the agent should touch. The agent can grep, summarise, and edit files outside the open editor without you pasting them. Pair with a permission model that requires confirmation for writes — or use autoApprove on the read-only tools only.

3. A browser MCP

Two natural picks:

• Chrome MCP (@modelcontextprotocol/server-puppeteer or the official Chrome MCP extension) — attaches to your real signed-in Chrome. Great for Gmail summarisation, Calendar triage, internal dashboards where you're already logged in.
• Human Browser MCP (@virixlabs/humanbrowser-mcp) — covered below. Stealth Chromium on a residential IP for sites that fight bots.

You can install both — they expose different tool names (chrome.* vs human-browser.*) so the agent picks the right one based on context.

Debugging tools that don't show up

Single most common Cursor MCP question we get: "I added a server but the agent doesn't know about it." The diagnostic flowchart:

1. Did the server start? Open the Output panel (Cmd+Shift+U) and pick MCP Logs. A launch error shows there. 90% of the time: missing env var, wrong path in args, or the package name is misspelled.
2. Did Cursor pick up the config? Edit the JSON, save, and restart Cursor. If the new server doesn't appear in Customize, the JSON is malformed — paste it into jq . in your terminal to validate.
3. Is the server advertising tools? Some MCP servers launch successfully but advertise no tools until they have credentials. Check MCP Logs — a server with no tools usually means the server is up but auth failed.
4. Are you using the right tool name in your prompt? The agent picks tools by name + description. If two tools have similar names (list_issues in GitHub MCP and Linear MCP), the description matters. Mention the server name in your prompt: "use the github server to list issues".

Pairing Cursor with Human Browser MCP

The browser-MCP slot is where the choice matters. The Chrome MCP is fine for "use my real session." It fails the moment your target is Cloudflare-, DataDome-, or PerimeterX-protected — the same data-center-IP and CDP-fingerprint walls every stock Chromium hits.

Human Browser ships an MCP server (@virixlabs/humanbrowser-mcp) that exposes the same browser-shaped tool surface (navigate, click, type, screenshot, evaluate) but the browser on the other end is a stealth-patched Chromium running on a residential IP, with a CAPTCHA solver and human-paced input baked in. From Cursor's side, it's just another MCP entry:

{
  "mcpServers": {
    "human-browser": {
      "command": "npx",
      "args": ["-y", "@virixlabs/humanbrowser-mcp"],
      "env": {
        "HB_TOKEN": "hb_live_...",   // from /install on humanbrowser.cloud
        "HB_DEFAULT_COUNTRY": "us"    // optional: residential-IP country
      }
    }
  }
}

Add this entry next to your GitHub + filesystem servers, reload, and Composer can drive a stealth browser whenever your task needs one. The agent picks human-browser.* when the target is protected and a regular browser MCP otherwise.

Try the Human Browser MCP — $1 for about 4 typical tasks

Pay-as-you-go: $0.10/hr browser time, $4/GB residential proxy, $0.005/captcha, $0.02 per agent step with the AI included. No subscription, unused balance never expires. humanbrowser.cloud.

FAQ

Does Cursor support MCP?

Yes. Manage servers from Customize in the sidebar; official docs at cursor.com/docs/mcp. Same server ecosystem as Claude Desktop / Claude Code.

Where is the config file?

Global: ~/.cursor/mcp.json. Project-scoped: .cursor/mcp.json in the project root.

What's the config format?

JSON with mcpServers top-level key. Each entry has command, args, env. Optional disabled and autoApprove.

Which servers should I install first?

GitHub, scoped filesystem, and a browser MCP (Chrome MCP for daily-driver Chrome, Human Browser MCP for protected sites).

Why don't my tools show up?

Open the Output panel and pick MCP Logs. Usual causes: missing env var, bad command, or failed auth. Restart Cursor after config changes, and check the server is toggled on in Customize.

Can I share an MCP config between Cursor and Claude Code?

Yes — same format and ecosystem. Keep one canonical file and reference it from both clients to avoid drift.

Related Articles

• Cursor vs Claude Code (2026) — Comparison
• Cursor Browser (2026): Built-in vs MCP vs Remote-CDP — AI Agents
• Browser MCP: Connect Claude / Cursor to a Real Browser — MCP
• OpenClaw and MCP (2026) — AI Agents