Fider MCP Server
Enables interaction with Fider customer feedback platforms, supporting post management, commenting, tagging, and status updates through natural language commands.
README
MCP Server for Fider
A Model Context Protocol (MCP) server that provides tools to interact with Fider - an open-source customer feedback tool.
Features
This MCP server provides the following tools:
Posts:
- list_posts - List posts with filtering options (search, view, limit, tags)
- get_post - Retrieve a specific post by number
- create_post - Create new posts (requires authentication)
- edit_post - Edit existing posts (requires collaborator/admin role)
- delete_post - Delete posts (requires admin role)
- respond_to_post - Change post status (open, planned, started, completed, declined, duplicate)
Comments:
- list_comments - List comments for a specific post
- add_comment - Add a comment to a post (requires authentication)
- update_comment - Update a comment (requires authentication and ownership)
- delete_comment - Delete a comment (requires authentication and ownership/admin)
Tags:
- list_tags - List all available tags
- create_tag - Create a new tag (requires admin role)
- update_tag - Update an existing tag (requires admin role)
- delete_tag - Delete a tag (requires admin role)
- assign_tag - Assign a tag to a post (requires collaborator/admin role)
- unassign_tag - Unassign a tag from a post (requires collaborator/admin role)
Installation
Using uvx (recommended - no installation needed!)
# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh
# Run directly from PyPI (once published)
uvx --from mcp-fider==2025.06.27.170000 --refresh-package mcp-fider mcp-fider
# Or run from GitHub directly
uvx --from git+https://github.com/ringostat/fider-mcp.git mcp-fider
Using pip (if you prefer traditional method)
# Clone the repository
git clone https://github.com/ringostat/fider-mcp.git
cd fider-mcp
# Create a virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install the package
pip install -e .
Configuration
The server requires the following environment variables:
FIDER_BASE_URLorFIDER_URL- Your Fider instance URL (e.g.,https://feedback.example.com)FIDER_API_KEY- Optional API key for authentication (required for creating, editing, and deleting posts)
Getting a Fider API Key
- Log in to your Fider instance as an administrator
- Go to Settings → API
- Generate a new API key
- Copy the key and set it as the
FIDER_API_KEYenvironment variable
Usage
With Claude Desktop
-
Add the server to your Claude Desktop configuration file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json -
Add the following configuration:
{
"mcpServers": {
"fider": {
"command": "uvx",
"args": ["--from", "mcp-fider==2025.06.27.170000",
"--refresh-package", "mcp-fider", "mcp-fider"],
"env": {
"FIDER_BASE_URL": "https://your-fider-instance.com",
"FIDER_API_KEY": "your-api-key-here"
}
}
}
}
- Restart Claude Desktop
Running Directly
You can also run the server directly for testing:
# Set environment variables
export FIDER_BASE_URL="https://your-fider-instance.com"
export FIDER_API_KEY="your-api-key-here"
# Run from PyPI (once published)
uvx --from mcp-fider==2025.06.27.170000 --refresh-package mcp-fider mcp-fider
# Or run from GitHub directly
uvx --from git+https://github.com/ringostat/fider-mcp.git mcp-fider
Development
Running Tests
uv run pytest
Code Formatting
uv run black .
uv run ruff check .
Publishing to PyPI
# Build the package
uv build
# Publish to PyPI
uv publish
Tool Descriptions
list_posts
List posts from Fider with optional filtering.
Parameters:
query(string) - Search keywordsview(string) - Filter and order options: all, recent, my-votes, most-wanted, most-discussed, planned, started, completed, declined, trendinglimit(integer) - Number of entries to return (1-100, default: 30)tags(string) - Comma-separated list of tags to filter by
get_post
Get a specific post by its number.
Parameters:
number(integer, required) - The post number to retrieve
create_post
Create a new post (requires authentication).
Parameters:
title(string, required) - The title of the postdescription(string) - The description of the post
edit_post
Edit an existing post (requires collaborator/admin role).
Parameters:
number(integer, required) - The post number to edittitle(string, required) - The new title of the postdescription(string) - The new description of the post
delete_post
Delete a post (requires admin role).
Parameters:
number(integer, required) - The post number to deletereason(string) - Reason for deletion
respond_to_post
Respond to a post by changing its status (requires collaborator/admin role).
Parameters:
number(integer, required) - The post number to respond tostatus(string, required) - The new status: open, planned, started, completed, declined, duplicatetext(string) - Optional description of the status changeoriginalNumber(integer) - Required when status is 'duplicate' - the post number to merge into
Comment Tools
list_comments
List comments for a specific post.
Parameters:
number(integer, required) - The post number to get comments for
add_comment
Add a comment to a post (requires authentication).
Parameters:
number(integer, required) - The post number to comment oncontent(string, required) - The comment content
update_comment
Update a comment (requires authentication and ownership).
Parameters:
post_number(integer, required) - The post numbercomment_id(integer, required) - The comment ID to updatecontent(string, required) - The new comment content
delete_comment
Delete a comment (requires authentication and ownership/admin).
Parameters:
post_number(integer, required) - The post numbercomment_id(integer, required) - The comment ID to delete
Tag Tools
list_tags
List all available tags.
Parameters: None
create_tag
Create a new tag (requires admin role).
Parameters:
name(string, required) - The tag namecolor(string, required) - The tag color (hex format, e.g., #FF0000)isPublic(boolean) - Whether the tag is public (default: true)
update_tag
Update an existing tag (requires admin role).
Parameters:
slug(string, required) - The tag slug to updatename(string, required) - The new tag namecolor(string, required) - The new tag color (hex format, e.g., #FF0000)isPublic(boolean) - Whether the tag is public
delete_tag
Delete a tag (requires admin role).
Parameters:
slug(string, required) - The tag slug to delete
assign_tag
Assign a tag to a post (requires collaborator/admin role).
Parameters:
post_number(integer, required) - The post numberslug(string, required) - The tag slug to assign
unassign_tag
Unassign a tag from a post (requires collaborator/admin role).
Parameters:
post_number(integer, required) - The post numberslug(string, required) - The tag slug to unassign
Troubleshooting
Connection Issues
- Ensure your Fider instance is accessible from your network
- Check that the
FIDER_BASE_URLis correct and doesn't have a trailing slash - Verify your API key is valid if you're getting authentication errors
Permission Errors
- Creating, editing, and deleting posts requires proper authentication
- Ensure your API key has the necessary permissions for the operations you're trying to perform
License
MIT License - see LICENSE file for details
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。