A
licenseB
qualityF
maintenanceA Model Context Protocol server that enables AI assistants to interact with Feishu project management systems, allowing retrieval of project views and work items.
6
12
MIT
FeedbackBasket MCP Server
by deifos
FeedbackBasket MCP server lets an AI assistant query your FeedbackBasket projects, feedback, and bug reports — this schema exposes 4 read-only tools (the README documents 42 operations for the CLI/HTTP transports).
list_projects— list all projects your API key can access, with summary statistics.get_feedback— retrieve feedback filtered by project, status (PENDING/REVIEWED/DONE), category (BUG/FEATURE/REVIEW), sentiment, or text search; optionally include internal notes; up to 100 results.get_bug_reports— pull bug reports with computed severity (negative=high, neutral=medium, positive=low), status, text search, and optional notes.search_feedback— text search across all accessible projects, filterable by category and project (requiresquery, up to 50 results).All four tools are read-only, require an authenticated API key (
fb_key_…) with access to at least one project, and need no confirmation.Write and high-impact operations described in the README (create/update/delete feedback, notes, replies, team, widget, mobile, GitHub, exports) are not present in this schema and would require a full-access key with
confirm: truewhere applicable.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@FeedbackBasket MCP Server show me high severity bug reports from the last week"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
FeedbackBasket MCP Server
Model Context Protocol (MCP) server for FeedbackBasket. Version 3.5.1 provides the same 42 product operations as the FeedbackBasket CLI and live Streamable HTTP server.
Use a read key for queries. Use a full key for approved writes. A project-restricted key can access only its allowed projects. Project creation and team operations need an unrestricted full key. Each high-impact operation needs confirm: true.
Use this STDIO package with an MCP key for local processes, CI, servers, and unattended automation. For remote Streamable HTTP, add https://feedbackbasket.com/.well-known/mcp to the host, save it, and select Authenticate. Sign in, select an organization, select Read or Full access, select Selected projects or All projects, and select Allow. Browser OAuth is the recommended remote setup. It is not used by STDIO.
Read is selected by default. Full needs an explicit choice and an owner or administrator role. Selected projects limits access to the approved projects. All projects includes current and future projects and is required for project creation and team operations. Existing unrestricted MCP keys remain compatible. New browser grants never receive All-projects access silently. Never put an access token, refresh token, MCP key, or CLI token in source, prompts, logs, generated configuration, or final output.
Installation & Setup
1. Generate API Key
Log into feedbackbasket.com
Go to Settings (sidebar)
Scroll to MCP API Keys section
Click New API Key
Name your key (e.g., "Claude Code", "Cursor", "Windsurf")
Select projects to grant access to (or leave empty for all projects)
Copy the generated key. It is shown only once. Keep it out of source, logs, prompts, and command history.
2. Configure Your Editor
Claude Code (CLI)
Set FEEDBACKBASKET_API_KEY in the environment that starts Claude Code. Then
add the server without putting the key in the command or shell history:
claude mcp add feedbackbasket -- npx -y feedbackbasket-mcp-server@3.5.1On native Windows, use cmd /c npx as the command because Claude Code cannot
start npx directly there.
Claude Desktop
Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"feedbackbasket": {
"command": "npx",
"args": ["-y", "feedbackbasket-mcp-server@3.5.1"],
"env": { "FEEDBACKBASKET_API_KEY": "${FEEDBACKBASKET_API_KEY}" }
}
}
}Cursor / Windsurf
Add to your MCP config (.cursor/mcp.json or equivalent):
{
"mcpServers": {
"feedbackbasket": {
"command": "npx",
"args": ["-y", "feedbackbasket-mcp-server@3.5.1"],
"env": { "FEEDBACKBASKET_API_KEY": "${FEEDBACKBASKET_API_KEY}" }
}
}
}Environment Variable
Use an environment variable instead of the --api-key argument. This keeps
the key out of process listings and saved command history.
{
"mcpServers": {
"feedbackbasket": {
"command": "npx",
"args": ["-y", "feedbackbasket-mcp-server@3.5.1"],
"env": {
"FEEDBACKBASKET_API_KEY": "${FEEDBACKBASKET_API_KEY}"
}
}
}
}Related MCP server: Sentry MCP Server
Usage Examples
Once configured, ask your AI assistant:
Project Overview
"Show me all my FeedbackBasket projects"
"How much feedback does each project have?"
Bug Reports
"Show me all open bug reports"
"Get high severity bugs that haven't been addressed"
"Find bugs related to authentication"
Feedback Analysis
"Show me negative feedback from my project"
"Get all feature requests"
"What are users asking for the most?"
"Show me high priority feedback"
Search
"Search for feedback about 'payment issues'"
"Find feedback mentioning 'mobile'"
Agentic Workflows
"Look at my bug reports and suggest which ones to fix first"
"Summarize this week's feedback trends"
"Are users happy with the new checkout flow?"
Agent capability contract
Agent surface version: 3.10.0. The CLI and both MCP transports implement the same 61 product operations.
Product operation | CLI command | MCP tool | Required access | Confirm |
|
|
|
| No |
|
|
|
| Yes |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| Yes |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| Yes |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| Yes |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| Yes |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| Yes |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| Yes |
|
|
|
| Yes |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| Yes |
|
|
|
| No |
|
|
|
| Yes |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| Yes |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| Yes |
|
|
|
| Yes |
|
|
|
| Yes |
|
|
|
| Yes |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| No |
|
|
|
| Yes |
|
|
|
| No |
|
|
|
| Yes |
|
|
|
| No |
|
|
|
| Yes |
Security & Privacy
Explicit access — Read keys query data. Full keys can use approved write operations.
Project-level permissions — Restricted keys can access only selected projects.
Confirmation — High-impact operations do not run without explicit confirmation.
API key authentication — Secure token-based authentication
Usage tracking — Monitor API key usage from your Settings page
Revokable access — Deactivate or delete API keys instantly
Troubleshooting
"Invalid or missing API key"
Check that your API key starts with
fb_key_Ensure the key is still active in Settings > MCP API Keys
Verify the key has access to at least one project
"No projects found"
Make sure your API key has been granted access to projects
Check that you have projects in your FeedbackBasket account
Connection Issues
Ensure Node.js 18+ is installed
Try clearing npx cache:
npx clear-npx-cacheFor local development, add
--base-url http://localhost:3000
API Key Management
Visit feedbackbasket.com/dashboard/settings to:
Generate new API keys
Manage project access
View usage statistics
Activate/deactivate keys
Delete keys
Links
Remote ChatGPT events
Agent surface 3.5.1 adds feedback.created on the remote HTTP MCP endpoint. Event subscriptions are an explicit transport parity exemption. CLI and STDIO retain the same 42 product operations. Use ChatGPT Work or a dot with the remote plugin to subscribe; use get_feedback_item to fetch details from an event.
Available Tools
4 toolsget_bug_reportsC
Get bug reports specifically from your FeedbackBasket projects
Inputs: projectId, status, severity, search, +2 more.
get_feedbackC
Get feedback from your FeedbackBasket projects with filtering options
Inputs: projectId, category, status, sentiment, +3 more.
list_projectsB
List all FeedbackBasket projects accessible by your API key with summary statistics
Inputs: no named parameters.
search_feedbackB
Search for feedback across all accessible projects using text search
Inputs: query (required), projectId, category, limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
B3.3/5.0
Scored across 4 tools
Disambiguation4/5
The tools are mostly distinct in purpose, with clear separation between listing projects, getting bug reports, getting general feedback, and searching feedback. However, there is some potential overlap between 'get_feedback' and 'search_feedback'—both involve retrieving feedback, which could cause mild confusion if an agent needs to choose between them based on vague criteria.
Naming Consistency5/5
All tool names follow a consistent verb_noun pattern (e.g., get_bug_reports, get_feedback, list_projects, search_feedback). The naming is uniform and predictable, using snake_case throughout without any deviations in style or structure.
Tool Count4/5
With 4 tools, the count is reasonable for a feedback management server, covering core operations like listing projects and retrieving feedback. It is slightly lean but well-scoped, as each tool serves a distinct function without obvious bloat or redundancy.
Completeness3/5
The tool set covers read operations well (list, get, search) but lacks any write or update capabilities, such as creating, updating, or deleting feedback or projects. This creates notable gaps for agents needing to perform full CRUD operations, limiting the server to query-only workflows.
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
Model Context Protocol server for Studex tools, notifications, and profile integrations
Model Context Protocol server for todo.vu task management and time tracking.
Related MCP Servers
Sentry MCP Serverofficial
AlicenseBqualityDmaintenanceA Model Context Protocol server that lets AI assistants interact with the Sentry API to retrieve and analyze error data, manage projects, and monitor application performance.1112ISC- FlicenseNot gradedqualityNot gradedmaintenanceModel Context Protocol server that enables interaction with GitHub repositories, issues, pull requests, and search functionality through natural language.1-
- FlicenseBqualityDmaintenanceA Model Context Protocol server providing access to WeWork project management data, enabling project search, task analysis, and statistics retrieval through Claude and other LLM clients.6-