How to Connect Mintlify Docs Remote MCP to Gemini CLI
Add Mintlify's remote MCP server to Gemini CLI in about a minute.
Step-by-step
- Edit ~/.gemini/settings.jsonAdd the
mcpServersentry shown above β Gemini CLI useshttpUrlfor Streamable HTTP endpoints andurlfor legacy SSE. - AuthorizeNo authentication needed β Mintlify Docs MCP is public.
- VerifyRestart
gemini, then run/mcp listinside the CLI. Verify in the browser: pastehttps://www.mintlify.com/docs/mcpinto remotemcp.net/inspector and run initialize + tools/list.
Troubleshooting OAuth / 401
- A
401 Unauthorizedon first connect is normal β the endpoint is OAuth-protected; let Gemini CLI finish the browser consent flow. - If the consent window never opens, remove and re-add the server, then retry.
- Check the exact challenge at our OAuth debugger.
- Run the live endpoint through the online inspector to see the raw JSON-RPC exchange.
Or add to ~/.cursor/mcp.json:
{
"mcpServers": {
"mintlify-docs": {
"url": "https://www.mintlify.com/docs/mcp"
}
}
}claude mcp add --transport http mintlify-docs https://www.mintlify.com/docs/mcp
Or add to .vscode/mcp.json:
{
"servers": {
"mintlify-docs": {
"type": "http",
"url": "https://www.mintlify.com/docs/mcp"
}
}
}- Open Settings β Connectors (Integrations) β Add Custom Connector.
- Paste the endpoint URL:
https://www.mintlify.com/docs/mcp - No authentication needed β tools are available immediately.
Bridge the remote endpoint into stdio with mcp-remote in claude_desktop_config.json:
{
"mcpServers": {
"mintlify-docs": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://www.mintlify.com/docs/mcp"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"mintlify-docs": {
"serverUrl": "https://www.mintlify.com/docs/mcp"
}
}
}Add to ~/.kiro/settings/mcp.json (or .kiro/settings/mcp.json in your workspace), then reopen Kiro's Agent panel to pick up the server:
{
"mcpServers": {
"mintlify-docs": {
"url": "https://www.mintlify.com/docs/mcp"
}
}
}Add to ~/.codex/config.toml β Codex reads remote HTTP servers from [mcp_servers.*] tables:
[mcp_servers.mintlify-docs] url = "https://www.mintlify.com/docs/mcp"
Add to cline_mcp_settings.json (Cline β MCP Servers β Configure), or paste it via Cline's MCP marketplace file:
{
"mcpServers": {
"mintlify-docs": {
"type": "streamableHttp",
"url": "https://www.mintlify.com/docs/mcp"
}
}
}Add to ~/.gemini/settings.json under mcpServers β httpUrl for Streamable HTTP, url for legacy SSE:
{
"mcpServers": {
"mintlify-docs": {
"httpUrl": "https://www.mintlify.com/docs/mcp"
}
}
}Tools exposed by Mintlify Docs MCP (3)
| Tool | Safety | Description | Parameters |
|---|---|---|---|
| search_mintlify ~229 tok | π’ Readidempotent | Search across the Mintlify knowledge base to find relevant information, code examples, API references, and guides. Use this tool when you need to answer questions about Mintlify, find specific documentation, understand how features work, or locate implementation details. The search returns contextual content with titles and direct links to the documentation pages. If you need the full content of a specific page, use the query_docs_filesystem tool to `head` or `cat` the page path (append `.mdx` to the path returned from search β e.g. a result at `/some/page` is read with `head -200 /some/page.mdx`). | query*: stringlanguage: string |
| query_docs_filesystem_mintlify ~867 tok | π’ Readidempotent | Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the Mintlify documentation pages and OpenAPI specs. This is NOT a shell on any real machine β nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its `.mdx` path to `head` or `cat` β a page at the URL path `/some/page` lives at `/some/page.mdx`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Paths are specific to this site β never guess them.** Discover real paths with `tree / -L 2`, `ls /`, or the search tool before reading. If a path does not exist, that only means the guess was wrong; it does NOT mean the topic is undocumented β use `rg -il "keyword" /` to find where it is covered. **Workflow:** Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path. Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage. Each call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /some-directory && ls` or `ls /some-directory`). Do NOT assume that `cd` in one call affects the next call. Examples (replace the placeholder paths with real ones from `tree` or search): - `tree / -L 2` β see the top-level directory layout - `rg -il "rate limit" /` β find all files mentioning "rate limit" - `rg -C 3 "apiKey" /some-directory/` β show matches with 3 lines of context around each hit - `head -80 /some/page.mdx` β read the top 80 lines of a specific page - `head -80 /page-one.mdx /page-two.mdx /section/page-three.mdx` β read multiple pages in one call - `cat /some/page.mdx` β read a full page when you need everything - `cat /openapi/zh/discovery-openapi.json | jq '.paths | keys'` β list OpenAPI endpoints OpenAPI specs for this site are mounted under `/openapi`; run `find /openapi -type f` to list them. Use them to answer questions about endpoints, request/response schemas, parameters, and authentication. Output is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 "pattern" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible. When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/some/page.mdx` becomes `/some/page`. | command*: string |
| submit_feedback ~203 tok | π Writeopen-world | Report a problem with this documentation site so the docs team can fix it. Use when a documentation page is incorrect, outdated, confusing, incomplete, or has a broken example. This is for feedback about the documentation content itself β not for product support requests or feedback about this tool or assistant. | path*: stringfeedback*: string |
Connect Mintlify Docs MCP to another client
Other servers for Gemini CLI
GitHub's official remote MCP server hosted at api.githubcopilot.com. Gives AI agents first-party access to repositories, issues, pull requests and code search.
Notion's official hosted MCP server. Agents can search your workspace, read and create pages, and query databases over Streamable HTTP or SSE.
Linear's official remote MCP server. Agents can search, create and update issues and query your team's workflow over Streamable HTTP or SSE.
Figma's official remote MCP server. Agents can pull design context, variables, Code Connect mappings and screenshots from your Figma files.
AWS Knowledge's hosted remote MCP server. AWS's fully-managed public knowledge MCP gives agents access to the latest AWS documentation, API references, What's New posts and architectural guidance across all AWS services. It is public and unauthenticated β connect and call tools immediately.
Stripe's official remote MCP server at mcp.stripe.com. Agents can query customers, payment intents and subscriptions and invoke Stripe API operations with OAuth.