generated: '2026-08-02' method: searched source: https://registry.npmjs.org/@cequenceai/mcp-cli (README) + https://docs.aigateway.cequence.ai/docs/getstarted name: Cequence MCP CLI binary: cequence-mcp package: '@cequenceai/mcp-cli' version: 1.5.0 license: MIT official: true description: >- "A command-line tool by Cequence Security for easily setting up Cequence MCP (Model Context Protocol) servers with AI clients like Cursor IDE, Claude AI, and Windsurf IDE." install: - method: npx command: npx @cequenceai/mcp-cli@latest --help - method: npm global command: npm install -g @cequenceai/mcp-cli requirements: node: '>=18.0.0' platforms: [macOS, Windows, Linux] commands: - name: cursor group: client-setup summary: Write a Cequence MCP server entry into the Cursor IDE MCP config. example: npx @cequenceai/mcp-cli@latest cursor --url "https://your-cequence-gateway.com/mcp" --name "Cequence API Gateway" flags: ['--url', '--name', '--api-key'] - name: claude group: client-setup summary: Write a Cequence MCP server entry into the Claude AI MCP config. example: npx @cequenceai/mcp-cli@latest claude --url "https://your-cequence-gateway.com/mcp" --name "Cequence API Gateway" flags: ['--url', '--name', '--api-key'] - name: windsurf group: client-setup summary: Write a Cequence MCP server entry into the Windsurf IDE MCP config. example: npx @cequenceai/mcp-cli@latest windsurf --url "https://your-cequence-gateway.com/mcp" --name "Cequence API Gateway" flags: ['--url', '--name', '--api-key'] - name: list group: client-setup summary: List configured MCP servers. example: npx @cequenceai/mcp-cli@latest list - name: introspect group: onboarding summary: >- Act as an MCP client against an internally-hosted MCP server the Cequence control plane cannot reach, perform the MCP handshake, list every tool, and write an upload bundle so the server registers with its tools intact instead of 0 tools. example: npx @cequenceai/mcp-cli@latest introspect --url "https://internal-mcp.corp.local/mcp" --auth oauth --scope "read" flags: - {flag: '--url, -u', required: true, description: remote MCP server URL} - {flag: '--transport, -t', description: 'streamable-http (default) or sse'} - {flag: '--auth, -a', description: 'none (default), bearer, api-key, basic, or oauth'} - {flag: '--token', description: bearer token (with --auth bearer)} - {flag: '--api-key / --header-name', description: 'API key and the header to carry it (default Authorization)'} - {flag: '--basic-user / --basic-pass', description: credentials (with --auth basic)} - {flag: '--scope / --callback-port', description: 'OAuth scope(s) and local redirect port (default 8765)'} - {flag: '--header', description: 'extra "Name: Value" header, repeatable'} - {flag: '--name, -n / --description, -d', description: catalog display name and description} - {flag: '--primary-category / --family / --secondary', description: catalog categorization} - {flag: '--out, -o', description: 'directory to write output into (default: current directory)'} - {flag: '--format, -f', description: 'tgz (default, single .tar.gz bundle) or dir (loose files)'} - {flag: '--timeout', description: per-request timeout in seconds} - {flag: '--push', description: also upload the spec to the Cequence control plane} - {flag: '--api-url / --tenant / --api-token', description: control-plane target, tenant and bearer token for --push} - {flag: '--spec-id', description: re-introspect and refresh an existing catalog spec's tools in place} outputs: default: '/.tar.gz — upload in the AI Gateway UI (add remote MCP server -> "Upload a spec (CLI)")' contents: [create-spec.json, tools.json, manifest.json] alt_format: '--format dir writes the three files loose into //' caveats: >- "introspect removes the tool-discovery blocker only. For cloud-hosted Cequence gateways, the dataplane must still be able to reach the internal endpoint at runtime (network route / IP allow-list)." related: packages: packages/cequence-security-packages.yml mcp: mcp/cequence-security-mcp.yml x-evidence: fetched: '2026-08-02' urls: - url: https://registry.npmjs.org/@cequenceai/mcp-cli http_status: 200 - url: https://docs.aigateway.cequence.ai/docs/getstarted http_status: 200