chore: implement MCP client

[appflowy]

Feature Preview

---

PR Checklist

• My code adheres to AppFlowy's Conventions
• I've listed at least one issue that this PR fixes in the description above.
• I've added a test(s) to validate changes in this PR, or this PR only contains semantic changes.
• All existing tests are passing.

Summary by Sourcery

Implement MCP (Multi-Component Protocol) client for managing AI tool interactions

New Features:

• Add MCP client manager to handle connections with AI tool servers
• Introduce ability to connect, remove, and list tools from MCP servers

Enhancements:

• Add new error code for MCP-related errors
• Update logging filters to match new dependency names

Chores:

• Rename dependencies from 'appflowy-local-ai' and 'appflowy-plugin' to 'af-local-ai' and 'af-plugin' respectively
• Update dependency references across multiple Cargo.toml files

[appflowy]

We need to merge before finishing the MCP client feature because some changes were made and the main branch depends on them.

[sourcery-ai]

Reviewer's Guide by Sourcery

This pull request implements the MCP client by adding a new module for managing MCP clients, updating dependencies, and modifying existing code to integrate the new functionality.

Entity relationship diagram for MCP module

erDiagram
    MCPClientManager {
        STRING server_cmd
    }
    MCPClient {
        STRING server_cmd
    }
    ToolsList {
    }
    MCPClientManager ||--o{ MCPClient : manages
    MCPClient ||--o{ ToolsList : lists
    MCPClientManager ||--o{ ToolsList : accesses

Loading

Class diagram for MCPClientManager

classDiagram
    class MCPClientManager {
        +Arc<DashMap<String, MCPClient>> stdio_clients
        +MCPClientManager new()
        +connect_server(MCPServerConfig) Result<(), FlowyError>
        +remove_server(MCPServerConfig) Result<(), FlowyError>
        +tool_list(server_cmd: &str) Option<ToolsList>
    }
    class MCPClient {
        +new_stdio(MCPServerConfig) MCPClient
        +initialize() Result<(), FlowyError>
        +stop() Result<(), FlowyError>
        +list_tools() Result<ToolsList, FlowyError>
    }
    class MCPServerConfig {
        +String server_cmd
    }
    class ToolsList
    MCPClientManager --> "1" DashMap
    MCPClientManager --> "*" MCPClient
    MCPClientManager --> "1" MCPServerConfig
    MCPClientManager --> "*" ToolsList
    MCPClient --> "1" MCPServerConfig
    MCPClient --> "*" ToolsList

Loading

File-Level Changes

Change	Details	Files
Added MCP client management functionality.	Introduced MCPClientManager struct for managing MCP clients. Implemented methods to connect, remove, and list tools from MCP servers.	frontend/rust-lib/flowy-ai/src/mcp/manager.rs frontend/rust-lib/flowy-ai/src/mcp/mod.rs
Updated dependencies to include af-mcp and renamed existing dependencies.	Added af-mcp dependency to Cargo.toml files. Renamed appflowy-local-ai to af-local-ai and appflowy-plugin to af-plugin in Cargo.toml files.	frontend/rust-lib/flowy-ai/Cargo.toml frontend/rust-lib/Cargo.toml frontend/scripts/tool/update_local_ai_rev.sh
Modified log filter to accommodate renamed dependencies.	Updated log filter entries to use new dependency names af_local_ai and af_plugin.	frontend/rust-lib/flowy-core/src/log_filter.rs
Added new error code for MCP errors.	Introduced MCPError in the ErrorCode enum.	frontend/rust-lib/flowy-error/src/code.rs

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!
• Generate a plan of action for an issue: Comment @sourcery-ai plan on
  an issue to generate a plan of action for it.

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey @appflowy - I've reviewed your changes - here's some feedback:

Overall Comments:

• Consider adding a feature flag to gate the MCP client functionality, allowing for easier experimentation and rollback if needed.
• It looks like you've commented out the mcp module in flowy-ai/src/lib.rs; make sure this is intentional and won't cause issues.

Here's what I looked at during the review

• 🟢 General issues: all looks good
• 🟢 Security: all looks good
• 🟢 Testing: all looks good
• 🟢 Complexity: all looks good
• 🟢 Documentation: all looks good

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}