feat: replace custom mcp-types crate with equivalents from rmcp (#10349)

We started working with MCP in Codex before
https://crates.io/crates/rmcp was mature, so we had our own crate for
MCP types that was generated from the MCP schema:


https://github.com/openai/codex/blob/8b95d3e082376f4cb23e92641705a22afb28a9da/codex-rs/mcp-types/README.md

Now that `rmcp` is more mature, it makes more sense to use their MCP
types in Rust, as they handle details (like the `_meta` field) that our
custom version ignored. Though one advantage that our custom types had
is that our generated types implemented `JsonSchema` and `ts_rs::TS`,
whereas the types in `rmcp` do not. As such, part of the work of this PR
is leveraging the adapters between `rmcp` types and the serializable
types that are API for us (app server and MCP) introduced in #10356.

Note this PR results in a number of changes to
`codex-rs/app-server-protocol/schema`, which merit special attention
during review. We must ensure that these changes are still
backwards-compatible, which is possible because we have:

```diff
- export type CallToolResult = { content: Array<ContentBlock>, isError?: boolean, structuredContent?: JsonValue, };
+ export type CallToolResult = { content: Array<JsonValue>, structuredContent?: JsonValue, isError?: boolean, _meta?: JsonValue, };
```

so `ContentBlock` has been replaced with the more general `JsonValue`.
Note that `ContentBlock` was defined as:

```typescript
export type ContentBlock = TextContent | ImageContent | AudioContent | ResourceLink | EmbeddedResource;
```

so the deletion of those individual variants should not be a cause of
great concern.

Similarly, we have the following change in
`codex-rs/app-server-protocol/schema/typescript/Tool.ts`:

```
- export type Tool = { annotations?: ToolAnnotations, description?: string, inputSchema: ToolInputSchema, name: string, outputSchema?: ToolOutputSchema, title?: string, };
+ export type Tool = { name: string, title?: string, description?: string, inputSchema: JsonValue, outputSchema?: JsonValue, annotations?: JsonValue, icons?: Array<JsonValue>, _meta?: JsonValue, };
```

so:

- `annotations?: ToolAnnotations` ➡️ `JsonValue`
- `inputSchema: ToolInputSchema` ➡️ `JsonValue`
- `outputSchema?: ToolOutputSchema` ➡️ `JsonValue`

and two new fields: `icons?: Array<JsonValue>, _meta?: JsonValue`

---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with [ReviewStack](https://reviewstack.dev/openai/codex/pull/10349).
* #10357
* __->__ #10349
* #10356

codex-rs/protocol/src/approvals.rs

@@ -1,9 +1,9 @@
 use std::collections::HashMap;
 use std::path::PathBuf;
 
+use crate::mcp::RequestId;
 use crate::parse_command::ParsedCommand;
 use crate::protocol::FileChange;
-use mcp_types::RequestId;
 use schemars::JsonSchema;
 use serde::Deserialize;
 use serde::Serialize;
@@ -62,6 +62,7 @@ pub struct ExecApprovalRequestEvent {
 #[derive(Debug, Clone, Deserialize, Serialize, JsonSchema, TS)]
 pub struct ElicitationRequestEvent {
     pub server_name: String,
+    #[ts(type = "string | number")]
     pub id: RequestId,
     pub message: String,
     // TODO: MCP servers can request we fill out a schema for the elicitation. We don't support

codex-rs/protocol/src/mcp.rs

@@ -1,14 +1,14 @@
+//! Types used when representing Model Context Protocol (MCP) values inside the
+//! Codex protocol.
+//!
+//! We intentionally keep these types TS/JSON-schema friendly (via `ts-rs` and
+//! `schemars`) so they can be embedded in Codex's own protocol structures.
 use schemars::JsonSchema;
 use serde::Deserialize;
 use serde::Serialize;
 use ts_rs::TS;
 
-/// Types used when representing Model Context Protocol (MCP) values inside the
-/// Codex protocol.
-///
-/// We intentionally keep these types TS/JSON-schema friendly (via `ts-rs` and
-/// `schemars`) so they can be embedded in Codex's own protocol structures.
-
+/// ID of a request, which can be either a string or an integer.
 #[derive(Debug, Clone, PartialEq, Eq, Hash, Serialize, Deserialize, JsonSchema, TS)]
 #[serde(untagged)]
 pub enum RequestId {
@@ -26,6 +26,7 @@ impl std::fmt::Display for RequestId {
     }
 }
 
+/// Definition for a tool the client can call.
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize, JsonSchema, TS)]
 #[serde(rename_all = "camelCase")]
 pub struct Tool {
@@ -51,6 +52,7 @@ pub struct Tool {
     pub meta: Option<serde_json::Value>,
 }
 
+/// A known resource that the server is capable of reading.
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize, JsonSchema, TS)]
 #[serde(rename_all = "camelCase")]
 pub struct Resource {
@@ -80,6 +82,7 @@ pub struct Resource {
     pub meta: Option<serde_json::Value>,
 }
 
+/// A template description for resources available on the server.
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize, JsonSchema, TS)]
 #[serde(rename_all = "camelCase")]
 pub struct ResourceTemplate {
@@ -99,6 +102,7 @@ pub struct ResourceTemplate {
     pub mime_type: Option<String>,
 }
 
+/// The server's response to a tool call.
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize, JsonSchema, TS)]
 #[serde(rename_all = "camelCase")]
 pub struct CallToolResult {

codex-rs/protocol/src/models.rs

@@ -2,8 +2,6 @@ use std::collections::HashMap;
 use std::path::Path;
 
 use codex_utils_image::load_and_resize_to_fit;
-use mcp_types::CallToolResult;
-use mcp_types::ContentBlock;
 use serde::Deserialize;
 use serde::Deserializer;
 use serde::Serialize;
@@ -24,6 +22,8 @@ use codex_git::GhostCommit;
 use codex_utils_image::error::ImageProcessingError;
 use schemars::JsonSchema;
 
+use crate::mcp::CallToolResult;
+
 /// Controls whether a command should use the session sandbox or bypass it.
 #[derive(
     Debug, Clone, Copy, Default, Eq, Hash, PartialEq, Serialize, Deserialize, JsonSchema, TS,
@@ -833,6 +833,7 @@ impl From<&CallToolResult> for FunctionCallOutputPayload {
             content,
             structured_content,
             is_error,
+            meta: _,
         } = call_tool_result;
 
         let is_success = is_error != &Some(true);
@@ -869,7 +870,7 @@ impl From<&CallToolResult> for FunctionCallOutputPayload {
             }
         };
 
-        let content_items = convert_content_blocks_to_items(content);
+        let content_items = convert_mcp_content_to_items(content);
 
         FunctionCallOutputPayload {
             content: serialized_content,
@@ -879,32 +880,45 @@ impl From<&CallToolResult> for FunctionCallOutputPayload {
     }
 }
 
-fn convert_content_blocks_to_items(
-    blocks: &[ContentBlock],
+fn convert_mcp_content_to_items(
+    contents: &[serde_json::Value],
 ) -> Option<Vec<FunctionCallOutputContentItem>> {
+    #[derive(serde::Deserialize)]
+    #[serde(tag = "type")]
+    enum McpContent {
+        #[serde(rename = "text")]
+        Text { text: String },
+        #[serde(rename = "image")]
+        Image {
+            data: String,
+            #[serde(rename = "mimeType", alias = "mime_type")]
+            mime_type: Option<String>,
+        },
+        #[serde(other)]
+        Unknown,
+    }
+
     let mut saw_image = false;
-    let mut items = Vec::with_capacity(blocks.len());
-    tracing::warn!("Blocks: {:?}", blocks);
-    for block in blocks {
-        match block {
-            ContentBlock::TextContent(text) => {
-                items.push(FunctionCallOutputContentItem::InputText {
-                    text: text.text.clone(),
-                });
-            }
-            ContentBlock::ImageContent(image) => {
+    let mut items = Vec::with_capacity(contents.len());
+
+    for content in contents {
+        let item = match serde_json::from_value::<McpContent>(content.clone()) {
+            Ok(McpContent::Text { text }) => FunctionCallOutputContentItem::InputText { text },
+            Ok(McpContent::Image { data, mime_type }) => {
                 saw_image = true;
-                // Just in case the content doesn't include a data URL, add it.
-                let image_url = if image.data.starts_with("data:") {
-                    image.data.clone()
+                let image_url = if data.starts_with("data:") {
+                    data
                 } else {
-                    format!("data:{};base64,{}", image.mime_type, image.data)
+                    let mime_type = mime_type.unwrap_or_else(|| "application/octet-stream".into());
+                    format!("data:{mime_type};base64,{data}")
                 };
-                items.push(FunctionCallOutputContentItem::InputImage { image_url });
+                FunctionCallOutputContentItem::InputImage { image_url }
             }
-            // TODO: render audio, resource, and embedded resource content to the model.
-            _ => return None,
-        }
+            Ok(McpContent::Unknown) | Err(_) => FunctionCallOutputContentItem::InputText {
+                text: serde_json::to_string(content).unwrap_or_else(|_| "<content>".to_string()),
+            },
+        };
+        items.push(item);
     }
 
     if saw_image { Some(items) } else { None }
@@ -936,12 +950,54 @@ mod tests {
     use crate::protocol::AskForApproval;
     use anyhow::Result;
     use codex_execpolicy::Policy;
-    use mcp_types::ImageContent;
-    use mcp_types::TextContent;
     use pretty_assertions::assert_eq;
     use std::path::PathBuf;
     use tempfile::tempdir;
 
+    #[test]
+    fn convert_mcp_content_to_items_preserves_data_urls() {
+        let contents = vec![serde_json::json!({
+            "type": "image",
+            "data": "data:image/png;base64,Zm9v",
+            "mimeType": "image/png",
+        })];
+
+        let items = convert_mcp_content_to_items(&contents).expect("expected image items");
+        assert_eq!(
+            items,
+            vec![FunctionCallOutputContentItem::InputImage {
+                image_url: "data:image/png;base64,Zm9v".to_string(),
+            }]
+        );
+    }
+
+    #[test]
+    fn convert_mcp_content_to_items_builds_data_urls_when_missing_prefix() {
+        let contents = vec![serde_json::json!({
+            "type": "image",
+            "data": "Zm9v",
+            "mimeType": "image/png",
+        })];
+
+        let items = convert_mcp_content_to_items(&contents).expect("expected image items");
+        assert_eq!(
+            items,
+            vec![FunctionCallOutputContentItem::InputImage {
+                image_url: "data:image/png;base64,Zm9v".to_string(),
+            }]
+        );
+    }
+
+    #[test]
+    fn convert_mcp_content_to_items_returns_none_without_images() {
+        let contents = vec![serde_json::json!({
+            "type": "text",
+            "text": "hello",
+        })];
+
+        assert_eq!(convert_mcp_content_to_items(&contents), None);
+    }
+
     #[test]
     fn converts_sandbox_mode_into_developer_instructions() {
         let workspace_write: DeveloperInstructions = SandboxMode::WorkspaceWrite.into();
@@ -1124,20 +1180,12 @@ mod tests {
     fn serializes_image_outputs_as_array() -> Result<()> {
         let call_tool_result = CallToolResult {
             content: vec![
-                ContentBlock::TextContent(TextContent {
-                    annotations: None,
-                    text: "caption".into(),
-                    r#type: "text".into(),
-                }),
-                ContentBlock::ImageContent(ImageContent {
-                    annotations: None,
-                    data: "BASE64".into(),
-                    mime_type: "image/png".into(),
-                    r#type: "image".into(),
-                }),
+                serde_json::json!({"type":"text","text":"caption"}),
+                serde_json::json!({"type":"image","data":"BASE64","mimeType":"image/png"}),
             ],
-            is_error: None,
             structured_content: None,
+            is_error: Some(false),
+            meta: None,
         };
 
         let payload = FunctionCallOutputPayload::from(&call_tool_result);
@@ -1169,6 +1217,33 @@ mod tests {
         Ok(())
     }
 
+    #[test]
+    fn preserves_existing_image_data_urls() -> Result<()> {
+        let call_tool_result = CallToolResult {
+            content: vec![serde_json::json!({
+                "type": "image",
+                "data": "data:image/png;base64,BASE64",
+                "mimeType": "image/png"
+            })],
+            structured_content: None,
+            is_error: Some(false),
+            meta: None,
+        };
+
+        let payload = FunctionCallOutputPayload::from(&call_tool_result);
+        let Some(items) = payload.content_items else {
+            panic!("expected content items");
+        };
+        assert_eq!(
+            items,
+            vec![FunctionCallOutputContentItem::InputImage {
+                image_url: "data:image/png;base64,BASE64".into(),
+            }]
+        );
+
+        Ok(())
+    }
+
     #[test]
     fn deserializes_array_payload_into_items() -> Result<()> {
         let json = r#"[

codex-rs/protocol/src/protocol.rs

@@ -23,6 +23,11 @@ use crate::dynamic_tools::DynamicToolCallRequest;
 use crate::dynamic_tools::DynamicToolResponse;
 use crate::dynamic_tools::DynamicToolSpec;
 use crate::items::TurnItem;
+use crate::mcp::CallToolResult;
+use crate::mcp::RequestId;
+use crate::mcp::Resource as McpResource;
+use crate::mcp::ResourceTemplate as McpResourceTemplate;
+use crate::mcp::Tool as McpTool;
 use crate::message_history::HistoryEntry;
 use crate::models::BaseInstructions;
 use crate::models::ContentItem;
@@ -35,11 +40,6 @@ use crate::plan_tool::UpdatePlanArgs;
 use crate::request_user_input::RequestUserInputResponse;
 use crate::user_input::UserInput;
 use codex_utils_absolute_path::AbsolutePathBuf;
-use mcp_types::CallToolResult;
-use mcp_types::RequestId;
-use mcp_types::Resource as McpResource;
-use mcp_types::ResourceTemplate as McpResourceTemplate;
-use mcp_types::Tool as McpTool;
 use schemars::JsonSchema;
 use serde::Deserialize;
 use serde::Serialize;