ReadMe Connector for AI agents.
10 live capabilities
Give your AI agent direct access to your official API and developer documentation.
Waiting for input…
Why people use ReadMe
ReadMe for Automated API Documentation Audits
This Connector removes that friction. Your agent pulls the content directly from ReadMe. You get accurate answers based on your official docs without ever leaving your current window.
What Vinkius changes
Your AI agent gets instant, accurate access to your official developer documentation.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Auditing old guides
A writer asks the agent to find all pages in a category to check for broken links or outdated info using get_category_docs.
- Real-world use case 02
Drafting new API docs
An engineer asks the agent to summarize a changelog to write a new Getting Started guide using get_changelog.
- Real-world use case 03
Quick API lookups
A dev asks for the specific webhook setup instructions from the docs using search_docs.
Complete set · 10capabilities
The complete ReadMe capability set.
These are the exact actions your AI can choose when you ask it to work with ReadMe.
01—04
4 capabilities in this set.
Part of 10 available through ReadMe.
- 01 Capability
List categories
Lists all documentation categories on ReadMe. Use this to let your agent see the full structure of your portal.
- 02 Capability
Get category
Gets details for a specific documentation category. Use this to understand how a section is organized.
- 03 Capability
Get category docs
Lists all documentation pages under a specific category. This helps your agent see all available guides in one section.
- 04 Capability
Get doc
Retrieves the full content of a documentation page. This lets the agent read the exact Markdown text for a guide.
05—07
3 capabilities in this set.
Part of 10 available through ReadMe.
- 05 Capability
List custom pages
Lists all custom standalone pages. This finds content that isn't part of your main categories.
- 06 Capability
Get custom page
Retrieves the full content of a custom page. This lets your agent read specific standalone content.
- 07 Capability
Get project
Retrieves details about the ReadMe project. This gives your agent a high-level view of your documentation hub.
08—10
3 capabilities in this set.
Part of 10 available through ReadMe.
- 08 Capability
Search docs
Performs a full-text search across all documentation pages. Use this for finding specific instructions quickly.
- 09 Capability
List changelogs
Lists all changelog posts. This provides a history of all official product updates.
- 10 Capability
Get changelog
Retrieves the full content of a specific changelog post. Use this to get the details of a specific release.
Set up in minutes
One URL. Then ask ReadMe to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use ReadMe from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_65dP2ZEWi1ggQrtmq1IKVpZ6MOAhFxi6q98C5XwC/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it ReadMe, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable ReadMe for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_65dP2ZEWi1ggQrtmq1IKVpZ6MOAhFxi6q98C5XwC/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the ReadMe URL.
- Step 03
Save and start
Save the connection and enable ReadMe in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"readme": {
"url": "https://edge.vinkius.com/vk_preview_65dP2ZEWi1ggQrtmq1IKVpZ6MOAhFxi6q98C5XwC/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using ReadMe
Open Agent mode in chat and ask: "Using ReadMe, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"readme": {
"url": "https://edge.vinkius.com/vk_preview_65dP2ZEWi1ggQrtmq1IKVpZ6MOAhFxi6q98C5XwC/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using ReadMe
Ask Copilot: "Using ReadMe, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"readme": {
"url": "https://edge.vinkius.com/vk_preview_65dP2ZEWi1ggQrtmq1IKVpZ6MOAhFxi6q98C5XwC/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using ReadMe
Open Cascade and ask: "Using ReadMe, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"readme": {
"url": "https://edge.vinkius.com/vk_preview_65dP2ZEWi1ggQrtmq1IKVpZ6MOAhFxi6q98C5XwC/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using ReadMe
Ask Cline: "Using ReadMe, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add readme --transport http "https://edge.vinkius.com/vk_preview_65dP2ZEWi1ggQrtmq1IKVpZ6MOAhFxi6q98C5XwC/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using ReadMe
Ask Claude: "Using ReadMe, show me...". 10 tools are ready
Where the request belongs
Work ReadMe can move forward.
This is for people who spend their days updating, auditing, or consuming technical documentation and need to stop manual copy-pasting.
Developer Advocate
Verifies guide accuracy and drafts new content based on existing structures.
Technical Writer
Audits documentation for outdated references without switching windows.
Software Engineer
Pulls official API docs into the IDE to ensure code matches published standards.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsArchbee
Manage documentation spaces, sync OpenAPI specs, and organize technical knowledge directly from your AI agent.
DevDocs
Search and read developer documentation via DevDocs.io. list libraries, find specific API pages, and retrieve Markdown docs directly from any AI agent.
Slab
Manage your team's knowledge base. query wiki articles, create new documentation, and explore topics directly using AI agents.
GitBook
Manage technical documentation via GitBook. list organizations and spaces, handle document pages, search content, and audit collections directly from any AI agent.
DeveloperHub
Equip your AI agent to manage documentation projects, track pages, and monitor changelogs via the DeveloperHub API.
Tettra
Search, read, and create internal wiki pages on your Tettra knowledge base directly from your AI agent.
Bring your own AI
Change the model, client or framework. Keep ReadMe connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about ReadMe.
The practical details behind the request, access and result.
Can the ReadMe MCP help me write better API guides?
Yes. It helps your AI agent stay consistent with your existing style and structure by giving it direct access to your current guides.
How does this help with changelog tracking?
It lets your AI agent pull official updates automatically so you can summarize what changed without manual searching.
Can my agent search specific categories?
Yes. Your agent can list and fetch docs by category to find information in specific sections of your portal.
Is this for my private docs?
It works with your ReadMe project based on your personal API key, keeping your connection secure.
Does it support custom pages?
Yes. It can list and retrieve standalone pages that aren't part of your main documentation categories.
How do I give the agent access?
You just need to provide your ReadMe API key in your Connector settings to connect your project.
Where do I obtain my ReadMe API Key?
Log into your ReadMe dashboard. Navigate to your specific project, then open 'Configuration' and click on 'API Key'. You will use this key as the authentication parameter (our integration handles it natively as a Basic Auth username).
Does the server allow me to write or edit documentation?
Currently, the Connector is focused on read-only operations. It can query, retrieve, and search changelogs, custom pages, and standard documentation categories, bringing context to the AI securely without risking accidental overwrites.
In what format is the document content returned?
All text and page content uses native Markdown format directly fetched from ReadMe's engine. This makes it perfect for the AI to interpret, syntax-highlight, and display naturally within chat or code comments.
One connection away
Give your agent a direct line to ReadMe.
Connect ReadMe once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available