Redocly

com.redoclyPublished by redocly.comOfficial publisherv1.0.1Updated Nov 3, 2026

Search and read the Redocly product docs, guides and blog on redocly.com, and report a wrong page.

VerifiedStreamable HTTPWeb executableKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Remote Redocly server that lets an assistant search and read Redocly docs and OpenAPI references, and report a wrong page.

What you can do
  • Search and read documentation: search the docs, list the navigation, read pages as Markdown, and grep for lines containing text.
  • Explore APIs: list available APIs, their endpoints, endpoint details, security schemes and full OpenAPI descriptions.
  • Run sandboxed scripts: execute JavaScript that calls those functions on a global site object, with no fetch, console or Node.js APIs.
  • Inspect signatures: discover returns the exact TypeScript signatures of the sandbox functions before scripting.
  • Report problems: submit feedback about a documentation page that is wrong or incomplete.
When to use it
Useful when an assistant needs current Redocly product documentation, CLI and configuration guidance, or OpenAPI reference details while answering questions or writing lint rules and docs setups. Also handy for passing a documentation problem back to the Redocly docs team.
Requirements
A remote MCP endpoint over Streamable HTTP at redocly.com/mcp; no package, account or API key is declared. The client sends an X-Redocly-MCP-Source header. Network access to redocly.com is required.
Before you install
The execute tool runs JavaScript in a sandbox against the site, so scripts are limited to the documented site functions. submit-feedback sends a report to the Redocly documentation team. Redocly receives tool calls and keeps usage statistics such as tool name, duration, client name and plugin version, though not the conversation.

Installation

In SourceWeft

  1. Open Redocly in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.redocly%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "redocly": {
      "type": "http",
      "url": "https://redocly.com/mcp"
    }
  }
}

README

Redocly plugin

The Redocly plugin gives your AI coding agent the Redocly skills and live access to the Redocly documentation through the Redocly MCP server. It works in Claude Code, Codex and Cursor.

Install

Claude Code:

bash
claude plugin marketplace add Redocly/redocly-pluginclaude plugin install redocly@redocly

Codex:

bash
codex plugin marketplace add Redocly/redocly-plugincodex plugin add redocly@redocly

Cursor: import this repository as a team marketplace (Teams and Enterprise plans), or copy plugins/redocly into ~/.cursor/plugins/local.

Skills only, in any client that reads Agent Skills:

bash
npx skills add Redocly/redocly-plugin

MCP server only, in any MCP client: add https://redocly.com/mcp as a remote server over Streamable HTTP, or install com.redocly/mcp from the MCP Registry. The Redocly MCP server docs have the steps for each client.

What you get

  • Skills that the agent loads when your request matches one: Redocly CLI commands, redocly.yaml configuration, custom lint rules, Markdown linting with redocly recheck, and Redocly docs projects (setup, pages, and API reference docs). The Redocly skills index lists them.
  • The Redocly MCP server at https://redocly.com/mcp. It searches and reads the current Redocly documentation, and it reports a wrong or incomplete page to the Redocly documentation team.

Example prompts:

  • "Lint my OpenAPI description with Redocly CLI and explain each problem."
  • "Write a Redocly lint rule that requires an operationId on every operation."
  • "Set up a Redocly docs site for my OpenAPI description."

Data and privacy

The plugin itself runs no code on your machine: the skills are Markdown files, and the plugin adds only the Redocly MCP server. Some skills tell the agent to run Redocly CLI commands, which the agent runs like any other command. Redocly receives the tool calls that your agent sends, not your conversation, and keeps usage statistics such as the tool name, the duration, the name of your client and the plugin version. No tool changes your Redocly account or your projects. The Redocly Privacy Notice covers requests to the server.

Support

Open an issue for a problem with the plugin. We do not accept pull requests from outside Redocly. To report a security vulnerability, follow SECURITY.md. For anything else, contact Redocly.

License

MIT

Source: README.md at commit 5ec18b2

Tools

3

execute

Query the docs with code

Run JavaScript in a sandbox against the documentation at https://redocly.com. The script calls the sandbox functions on the global `site` object. The only extra global is `site` - there is no `fetch`, `console`, `setTimeout`, `require`, or Node.js API; all I/O goes through `site`. Workflow - minimize round-trips; one `discover` call plus one `execute` call covers most requests: 1. Analyze the request and decide which sandbox functions it needs. 2. Call `discover` with those names to get their exact TypeScript signatures - inputs, result shapes, and a worked example. NEVER call `execute` with guessed function names, parameter names, enum values, or result field names: read fields off the declared return types, not from assumptions. 3. Batch everything into a SINGLE script: chain function calls, pass one call's output into the next, process results in plain JavaScript, and `return` only what the request needs. Functions for `execute` scripts (signatures come from `discover`): - listApis — List the available APIs. - getEndpoints — Get all endpoints for an API. - getEndpointInfo — Get the details of an endpoint. - getSecuritySchemes — Get the security schemes for an API. - getFullApiDescription — Get the complete OpenAPI description. - search — Search the documentation. - listPages — List the docs navigation, one level per call. - getPage — Read a docs page as Markdown, in line windows. - grepPages — Find the docs lines that contain a text.

Parameterscoderequireddescriptionrequired

discover

Get docs function signatures

Get the exact TypeScript signatures of the sandbox functions that `execute` scripts can call. Analyze the user request first, then pass `names` with only the functions the request needs (every name is listed in this input schema / description); omit `names` only when you cannot tell which functions apply. Always call this before your first `execute` and never guess signatures. Request every function the task may need in ONE call instead of calling this repeatedly.

Parametersnames

submit-feedback

Submit feedback

Report a documentation page that is wrong or incomplete. Use it when the user reports a problem with a page on this site, or agrees to report a problem that you found. Do not use it for product bugs or support questions.

ParameterspathrequireddetailssummaryrequiredtargetFeature

Version history

2
  1. v1.0.1LatestOct 26, 2026
  2. v1.0.0Oct 20, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts