MCP tools: query docs filesystem and skills (#5333)

* add info on skills as MCP resources

* update MCP resources/tools

* remove get_page

Author: ethanpalm

ai/model-context-protocol.mdx

@@ -21,17 +21,23 @@ When an AI application connects to your documentation MCP server, it can search
 - Each tool call happens during the generation process, so the AI application uses up-to-date information from your documentation to generate its response.
 
 <Tip>
-  Some AI tools like Claude support both MCP and Skills. MCP gives the AI access to your documentation content, while Skills instruct the AI how to use that content effectively. They're complementary. MCP provides the data and Skills provide the instructions.
+  Some AI tools like Claude support both MCP and skills. MCP gives access to your documentation content, while skills instruct agents how to use that content effectively. They're complementary and connecting your MCP server gives agents access to both.
 </Tip>
 
 ### MCP tools
 
-Your MCP server provides two tools that AI applications can use:
+Your MCP server provides two tools that agents can use:
 
-- **Search**: Searches across your documentation to find relevant content, returning snippets with titles and links. Use this when you need to discover information or find pages matching a query.
-- **Get page**: Retrieves the full content of a specific documentation page by its path. Use this when you already know the page path, such as from search results, and need the complete content rather than a snippet.
+- **Search**: Searches across your documentation to find relevant content, returning snippets with titles and links. Use this to discover information or find pages matching a query.
+- **Query docs filesystem**: Reads and navigates your documentation's virtual filesystem using shell-style commands. Use this to retrieve page content, browse the docs structure, or extract specific sections—including batch reads across multiple pages in a single call.
 
-AI applications determine when to use each tool based on the context of the conversation. For example, an AI application might first search your documentation to find relevant pages, then use the get page tool to retrieve the full content of the most relevant result.
+Agents determine when to use each tool based on the context of the conversation. For example, an agent might first search your documentation to find relevant pages, then use the query docs filesystem tool to read the full content of the most relevant results.
+
+### MCP resources
+
+Your MCP server also exposes your [skill.md files](/ai/skillmd) as MCP resources. Agents connected to your MCP server can discover and access your skill files without installing them separately.
+
+`Skill.md` resources appear in the MCP server's resource list and contain the capability descriptions Mintlify generates or that you define in your [custom skill files](/ai/skillmd#custom-skill-files).
 
 ### Search parameters
 
@@ -44,12 +50,6 @@ The MCP search tool supports optional parameters that AI applications use to con
 
 AI applications determine when to apply these parameters based on the context of the user's query. For example, if a user asks about a specific API version, the AI application may automatically apply the appropriate filter to provide more relevant results.
 
-### Get page parameters
-
-The get page tool accepts one required parameter:
-
-- **`page`**: The page path to retrieve, such as `'api-reference/create-customer'`. Use page paths returned from search results.
-
 ### MCP compared to web search
 
 AI tools can search the web, but MCP provides distinct advantages for documentation.
@@ -196,9 +196,9 @@ To protect availability, Mintlify applies rate limits to MCP servers.
 | :---- | :---- | :---------- |
 | Per user (IP address) | 5,000 requests per hour | Limits how frequently a single user can query your MCP server configuration. |
 | Search per documentation site (domain) | 10,000 requests per hour | Limits total search tool calls across all users of your MCP server. |
-| Get page per documentation site (domain) | 10,000 requests per hour | Limits total get page tool calls across all users of your MCP server. |
+| Query docs filesystem per documentation site (domain) | 10,000 requests per hour | Limits total query docs filesystem tool calls across all users of your MCP server. |
 | Authenticated search per documentation site (domain) | 5,000 requests per hour | Limits total authenticated search tool calls across all users of your MCP server. |
-| Authenticated get page per documentation site (domain) | 5,000 requests per hour | Limits total authenticated get page tool calls across all users of your MCP server. |
+| Authenticated query docs filesystem per documentation site (domain) | 5,000 requests per hour | Limits total authenticated query docs filesystem tool calls across all users of your MCP server. |
 
 ## Content filtering and indexing
 

ai/skillmd.mdx

@@ -28,12 +28,12 @@ View your `skill.md` by appending `/skill.md` to your documentation site's URL.
 ## Use `skill.md` files with agents
 
 <Note>
-  If you use a [reverse proxy](/deploy/reverse-proxy), configure it to forward
-  `/skill.md`, `/.well-known/skills/*`, and `/.well-known/agent-skills/*` paths
-  to your Mintlify subdomain.
+  If you use a [reverse proxy](/deploy/reverse-proxy), configure it to forward `/skill.md`, `/.well-known/skills/*`, and `/.well-known/agent-skills/*` paths to your Mintlify subdomain.
 </Note>
 
-Agents can process your `skill.md` with the [skills CLI](https://www.npmjs.com/package/skills).
+When users connect to your MCP server, their agents can discover and use your `skill.md` files as [MCP resources](/ai/model-context-protocol#mcp-resources) without installing the skills separately.
+
+To add your skills to an agent's context manually, use the [skills CLI](https://www.npmjs.com/package/skills).
 
 ```bash
 npx skills add https://your-docs-domain.com
@@ -42,8 +42,7 @@ npx skills add https://your-docs-domain.com
 This adds your product's capabilities to the agent's context so it can take actions on behalf of users.
 
 <Tip>
-  Teach your users how to use `skill.md` files with agents so that they have
-  better results using your product with their AI tools.
+  Teach your users how to use `skill.md` files with agents so that they have better results using your product with their AI tools.
 </Tip>
 
 ## `skill.md` structure