Merge pull request modelcontextprotocol#320 from koic/feature_pagination

Support pagination per MCP specification

Author: koic

README.md

@@ -40,6 +40,7 @@ It implements the Model Context Protocol specification, handling model context r
 - Supports notifications for list changes (tools, prompts, resources)
 - Supports roots (server-to-client filesystem boundary queries)
 - Supports sampling (server-to-client LLM completion requests)
+- Supports cursor-based pagination for list operations
 
 ### Supported Methods
 
@@ -1365,6 +1366,90 @@ When configured, sessions that receive no HTTP requests for this duration are au
 transport = MCP::Server::Transports::StreamableHTTPTransport.new(server, session_idle_timeout: 1800)
 ```
 
+### Pagination
+
+The MCP Ruby SDK supports [pagination](https://modelcontextprotocol.io/specification/2025-11-25/server/utilities/pagination)
+for list operations that may return large result sets. Pagination uses string cursor tokens carrying a zero-based offset,
+treated as opaque by clients: the server decides page size, and the client follows `nextCursor` until the server omits it.
+
+Pagination applies to `tools/list`, `prompts/list`, `resources/list`, and `resources/templates/list`.
+
+#### Server-Side: Enabling Pagination
+
+Pass `page_size:` to `MCP::Server.new` to split list responses into pages. When `page_size` is omitted (the default),
+list responses contain all items in a single response, preserving the pre-pagination behavior.
+
+```ruby
+server = MCP::Server.new(
+  name: "my_server",
+  tools: tools,
+  page_size: 50,
+)
+```
+
+When `page_size` is set, list responses include a `nextCursor` field whenever more pages are available:
+
+```json
+{
+  "jsonrpc": "2.0",
+  "id": 1,
+  "result": {
+    "tools": [
+      { "name": "example_tool" }
+    ],
+    "nextCursor": "50"
+  }
+}
+```
+
+Invalid cursors (e.g. non-numeric, negative, or out-of-range) are rejected with JSON-RPC error code `-32602 (Invalid params)` per the MCP specification.
+
+#### Client-Side: Iterating Pages
+
+`MCP::Client` exposes `list_tools`, `list_prompts`, `list_resources`, and `list_resource_templates`.
+**Each call issues exactly one `*/list` JSON-RPC request and returns exactly one page** — not the full collection.
+The returned result object (`MCP::Client::ListToolsResult` etc.) exposes the page items and the next cursor as method accessors:
+
+```ruby
+client = MCP::Client.new(transport: transport)
+
+cursor = nil
+loop do
+  page = client.list_tools(cursor: cursor)
+  page.tools.each { |tool| process(tool) }
+  cursor = page.next_cursor
+  break unless cursor
+end
+```
+
+The same pattern applies to `list_prompts` (`page.prompts`), `list_resources` (`page.resources`), and
+`list_resource_templates` (`page.resource_templates`). `next_cursor` is `nil` on the final page.
+
+Because a single call returns a single page, how many items come back depends on the server's `page_size` configuration:
+
+| Server `page_size` | `client.list_tools(cursor: nil)`                                    |
+|--------------------|---------------------------------------------------------------------|
+| Not set (default)  | Returns every item in one response. `next_cursor` is `nil`.         |
+| Set to `N`         | Returns the first `N` items. `next_cursor` is set for continuation. |
+
+If your application needs the complete collection regardless of how the server is configured, either loop on
+`next_cursor` as shown above, or use the whole-collection methods described below.
+
+#### Fetching the Complete Collection
+
+`client.tools`, `client.resources`, `client.resource_templates`, and `client.prompts` auto-iterate
+through all pages and return a plain array of items, guaranteeing the full collection regardless
+of the server's `page_size` setting. When a server paginates, they issue multiple JSON-RPC round
+trips per call and break out of the pagination loop if the server returns the same `nextCursor`
+twice in a row as a safety measure.
+
+```ruby
+tools = client.tools # => Array<MCP::Client::Tool> of every tool on the server.
+```
+
+Use these when you want the complete list; use `list_tools(cursor:)` etc. when you need
+fine-grained iteration (e.g. to stream-process pages without loading everything into memory).
+
 ### Advanced
 
 #### Custom Methods

lib/mcp/client.rb

@@ -2,6 +2,7 @@
 
 require_relative "client/stdio"
 require_relative "client/http"
+require_relative "client/paginated_result"
 require_relative "client/tool"
 
 module MCP
@@ -43,8 +44,41 @@ def initialize(transport:)
     # So keeping it public
     attr_reader :transport
 
-    # Returns the list of tools available from the server.
-    # Each call will make a new request – the result is not cached.
+    # Returns a single page of tools from the server.
+    #
+    # @param cursor [String, nil] Cursor from a previous page response.
+    # @return [MCP::Client::ListToolsResult] Result with `tools` (Array<MCP::Client::Tool>)
+    #   and `next_cursor` (String or nil).
+    #
+    # @example Iterate all pages
+    #   cursor = nil
+    #   loop do
+    #     page = client.list_tools(cursor: cursor)
+    #     page.tools.each { |tool| puts tool.name }
+    #     cursor = page.next_cursor
+    #     break unless cursor
+    #   end
+    def list_tools(cursor: nil)
+      params = cursor ? { cursor: cursor } : nil
+      response = request(method: "tools/list", params: params)
+      result = response["result"] || {}
+
+      tools = (result["tools"] || []).map do |tool|
+        Tool.new(
+          name: tool["name"],
+          description: tool["description"],
+          input_schema: tool["inputSchema"],
+        )
+      end
+
+      ListToolsResult.new(tools: tools, next_cursor: result["nextCursor"], meta: result["_meta"])
+    end
+
+    # Returns every tool available on the server. Iterates through all pages automatically
+    # when the server paginates, so the full collection is returned regardless of the server's `page_size` setting.
+    # Use {#list_tools} when you need fine-grained cursor control.
+    #
+    # Each call will make a new request - the result is not cached.
     #
     # @return [Array<MCP::Client::Tool>] An array of available tools.
     #
@@ -54,45 +88,151 @@ def initialize(transport:)
     #     puts tool.name
     #   end
     def tools
-      response = request(method: "tools/list")
+      # TODO: consider renaming to `list_all_tools`.
+      all_tools = []
+      seen = Set.new
+      cursor = nil
 
-      response.dig("result", "tools")&.map do |tool|
-        Tool.new(
-          name: tool["name"],
-          description: tool["description"],
-          input_schema: tool["inputSchema"],
-        )
-      end || []
+      loop do
+        page = list_tools(cursor: cursor)
+        all_tools.concat(page.tools)
+        next_cursor = page.next_cursor
+        break if next_cursor.nil? || seen.include?(next_cursor)
+
+        seen << next_cursor
+        cursor = next_cursor
+      end
+
+      all_tools
+    end
+
+    # Returns a single page of resources from the server.
+    #
+    # @param cursor [String, nil] Cursor from a previous page response.
+    # @return [MCP::Client::ListResourcesResult] Result with `resources` (Array<Hash>)
+    #   and `next_cursor` (String or nil).
+    def list_resources(cursor: nil)
+      params = cursor ? { cursor: cursor } : nil
+      response = request(method: "resources/list", params: params)
+      result = response["result"] || {}
+
+      ListResourcesResult.new(
+        resources: result["resources"] || [],
+        next_cursor: result["nextCursor"],
+        meta: result["_meta"],
+      )
     end
 
-    # Returns the list of resources available from the server.
-    # Each call will make a new request – the result is not cached.
+    # Returns every resource available on the server. Iterates through all pages automatically
+    # when the server paginates, so the full collection is returned regardless of the server's `page_size` setting.
+    # Use {#list_resources} when you need fine-grained cursor control.
+    #
+    # Each call will make a new request - the result is not cached.
     #
     # @return [Array<Hash>] An array of available resources.
     def resources
-      response = request(method: "resources/list")
+      # TODO: consider renaming to `list_all_resources`.
+      all_resources = []
+      seen = Set.new
+      cursor = nil
+
+      loop do
+        page = list_resources(cursor: cursor)
+        all_resources.concat(page.resources)
+        next_cursor = page.next_cursor
+        break if next_cursor.nil? || seen.include?(next_cursor)
+
+        seen << next_cursor
+        cursor = next_cursor
+      end
+
+      all_resources
+    end
 
-      response.dig("result", "resources") || []
+    # Returns a single page of resource templates from the server.
+    #
+    # @param cursor [String, nil] Cursor from a previous page response.
+    # @return [MCP::Client::ListResourceTemplatesResult] Result with `resource_templates`
+    #   (Array<Hash>) and `next_cursor` (String or nil).
+    def list_resource_templates(cursor: nil)
+      params = cursor ? { cursor: cursor } : nil
+      response = request(method: "resources/templates/list", params: params)
+      result = response["result"] || {}
+
+      ListResourceTemplatesResult.new(
+        resource_templates: result["resourceTemplates"] || [],
+        next_cursor: result["nextCursor"],
+        meta: result["_meta"],
+      )
     end
 
-    # Returns the list of resource templates available from the server.
-    # Each call will make a new request – the result is not cached.
+    # Returns every resource template available on the server. Iterates through all pages automatically
+    # when the server paginates, so the full collection is returned regardless of the server's `page_size` setting.
+    # Use {#list_resource_templates} when you need fine-grained cursor control.
+    #
+    # Each call will make a new request - the result is not cached.
     #
     # @return [Array<Hash>] An array of available resource templates.
     def resource_templates
-      response = request(method: "resources/templates/list")
+      # TODO: consider renaming to `list_all_resource_templates`.
+      all_templates = []
+      seen = Set.new
+      cursor = nil
 
-      response.dig("result", "resourceTemplates") || []
+      loop do
+        page = list_resource_templates(cursor: cursor)
+        all_templates.concat(page.resource_templates)
+        next_cursor = page.next_cursor
+        break if next_cursor.nil? || seen.include?(next_cursor)
+
+        seen << next_cursor
+        cursor = next_cursor
+      end
+
+      all_templates
     end
 
-    # Returns the list of prompts available from the server.
-    # Each call will make a new request – the result is not cached.
+    # Returns a single page of prompts from the server.
+    #
+    # @param cursor [String, nil] Cursor from a previous page response.
+    # @return [MCP::Client::ListPromptsResult] Result with `prompts` (Array<Hash>)
+    #   and `next_cursor` (String or nil).
+    def list_prompts(cursor: nil)
+      params = cursor ? { cursor: cursor } : nil
+      response = request(method: "prompts/list", params: params)
+      result = response["result"] || {}
+
+      ListPromptsResult.new(
+        prompts: result["prompts"] || [],
+        next_cursor: result["nextCursor"],
+        meta: result["_meta"],
+      )
+    end
+
+    # Returns every prompt available on the server. Iterates through all pages automatically
+    # when the server paginates, so the full collection is returned regardless of the server's `page_size` setting.
+    # Use {#list_prompts} when you need fine-grained cursor control.
+    #
+    # Each call will make a new request - the result is not cached.
     #
     # @return [Array<Hash>] An array of available prompts.
     def prompts
-      response = request(method: "prompts/list")
+      # TODO: consider renaming to `list_all_prompts`.
+      all_prompts = []
+      seen = Set.new
+      cursor = nil
+
+      loop do
+        page = list_prompts(cursor: cursor)
+        all_prompts.concat(page.prompts)
+        next_cursor = page.next_cursor
+        break if next_cursor.nil? || seen.include?(next_cursor)
+
+        seen << next_cursor
+        cursor = next_cursor
+      end
 
-      response.dig("result", "prompts") || []
+      all_prompts
     end
 
     # Calls a tool via the transport layer and returns the full response from the server.

lib/mcp/client/paginated_result.rb

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+
+module MCP
+  class Client
+    # Result objects returned by `list_tools`, `list_prompts`, `list_resources`, and `list_resource_templates`.
+    # Each carries the page items, an optional opaque `next_cursor` string for continuing pagination,
+    # and an optional `meta` hash mirroring the MCP `_meta` response field.
+    ListToolsResult = Struct.new(:tools, :next_cursor, :meta, keyword_init: true)
+    ListPromptsResult = Struct.new(:prompts, :next_cursor, :meta, keyword_init: true)
+    ListResourcesResult = Struct.new(:resources, :next_cursor, :meta, keyword_init: true)
+    ListResourceTemplatesResult = Struct.new(:resource_templates, :next_cursor, :meta, keyword_init: true)
+  end
+end