MCP / Developer tools

DeepWiki MCP

Read public repository wikis and ask codebase questions through DeepWiki. Connect it to Claude, Codex, Cursor or any MCP client through one FlyMy.AI MCP.

No setup step3 actionsDeveloper tools

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use DeepWiki Public MCP in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

Read https://flymy.ai/skill.md and https://flymy.ai/mcp/deepwiki-public.md. Help me connect DeepWiki Public MCP MCP to this assistant. Then help me run this task: Use DeepWiki to list the wiki topics for CognitionAI/deepwiki and suggest where a new contributor should start.

What DeepWiki Public MCP can do

3 actions in the FlyMy.AI catalog, the most used first. Your agent finds them through search_tools and calls the one the task needs.

ActionWhat it does
# ask_wiki_questionAsk DeepWiki an AI question grounded in one public GitHub repository or an ordered list of up to 10 repositories.
# read_wiki_contentsRead documentation contents of the wiki for one public GitHub repository.
# read_wiki_structureRead the topic/page outline of the wiki for one public GitHub repository.

Parameters and results

Open an action for its inputs, result and an illustrative example. Linked result schemas describe optional fields and limits.

read_wiki_structure

List the documentation topics for a single repository.

Use the outline to decide what to read first.

ParameterType, default and meaning
repoNamestring. Required: Yes. Default: None. One public GitHub owner/repo identifier.

Result: The wiki outline appears in the returned text.

Example arguments

{
  "repoName": "facebook/react"
}

Example result

{
  "content": [
    {
      "type": "text",
      "text": "Example topic"
    }
  ],
  "structuredContent": {
    "result": "Example topic"
  }
}

Full method documentation

read_wiki_contents

Read the wiki documentation for a single repository.

The input selects the whole repository wiki. Your assistant can summarize a section from the returned contents.

ParameterType, default and meaning
repoNamestring. Required: Yes. Default: None. One public GitHub owner/repo identifier.

Result: The returned text contains the repository wiki contents.

Example arguments

{
  "repoName": "facebook/react"
}

Example result

{
  "content": [
    {
      "type": "text",
      "text": "Example wiki text"
    }
  ],
  "structuredContent": {
    "result": "Example wiki text"
  }
}

Full method documentation

ask_wiki_question

Ask DeepWiki a question about a codebase.

Supply one repository or an ordered list of up to ten indexed public repositories. For comparisons, ask which repository supports each part of the answer.

ParameterType, default and meaning
repoNamestring or array of strings. Required: Yes. Default: None. One GitHub owner/repo identifier or a list of 1-10 identifiers.
questionstring. Required: Yes. Default: None. The question you want DeepWiki to answer using the selected repositories.

Result: DeepWiki returns its generated answer as text.

Example arguments

{
  "repoName": "facebook/react",
  "question": "Which parts of the repository handle rendering to the DOM?"
}

Example result

{
  "content": [
    {
      "type": "text",
      "text": "Example answer"
    }
  ],
  "structuredContent": {
    "result": "Example answer"
  }
}

Full method documentation

Ask your agent

Requests to paste as they are. Each one runs on the actions named under it. More requests and a walkthrough: Read a GitHub repository wiki with DeepWiki MCP.

“Use DeepWiki to list the wiki topics for CognitionAI/deepwiki and suggest where a new contributor should start.”uses read_wiki_structure
“Read the facebook/react wiki with DeepWiki and write a short reading list for a contributor working on React DOM.”uses read_wiki_contents
“Ask DeepWiki where TanStack/query stores cached results and what happens when a query is invalidated.”uses ask_wiki_question
“Ask DeepWiki to compare facebook/react and TanStack/query. Which project owns UI rendering, and which manages cached server data?”uses ask_wiki_question

Connect DeepWiki Public MCP in a minute

One MCP for every integration. Add it once, then every MCP in the catalog is a request away.

  1. 01

    Add FlyMy.AI

    Add the FlyMy.AI MCP to your assistant with one of the commands below and sign in. No key to copy.

  2. 02

    Select the connector

    Open the DeepWiki Public MCP connection settings and select it for your agent.

  3. 03

    Ask

    Paste a request from this page.

Claude Code
claude mcp add --transport http flymyai https://mcp-agents.flymy.ai/mcp

Then run /mcp in Claude Code and sign in.

Codex
codex mcp add flymy --url https://mcp-agents.flymy.ai/mcp

Then run codex mcp login flymy to sign in.

claude.ai and Claude Desktop
https://mcp-agents.flymy.ai/mcp

Settings, Connectors, Add custom connector: paste this URL.

Connect DeepWiki Public MCP to Hermes Agent

Hermes Agent by Nous Research adds FlyMy.AI with one command, and DeepWiki Public MCP comes with it. Give the browser sign-in up to five minutes. The Hermes Agent MCP guide covers the device code for Hermes on a server.

Hermes Agent
hermes mcp add flymy --url https://mcp-agents.flymy.ai/mcp --auth oauth --connect-timeout 300

Or run hermes mcp login flymy to sign in.

Agent on a server, no browser
X-Api-Key: <your FlyMy.AI API key>

Send it with every request to https://mcp-agents.flymy.ai/mcp, as X-Api-Key or Authorization: Bearer. Your key is on the Developers page.

Provider access

These actions read wikis for indexed public GitHub repositories. DeepWiki requires no provider API key.

Go to the source

From the FlyMy.AI platform catalog of 2026-11-18: name, description, actions and setup as the platform lists them. Examples are requests to paste, not recorded runs.