Skip to main content
Glama
deifos

FeedbackBasket MCP Server

by deifos

get_feedback

Retrieve and filter project feedback from FeedbackBasket by category, status, sentiment, or search terms to analyze bug reports, feature requests, and reviews.

Instructions

Get feedback from your FeedbackBasket projects with filtering options

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
projectIdNoFilter by specific project ID
categoryNoFilter by feedback category
statusNoFilter by feedback status
sentimentNoFilter by sentiment analysis result
searchNoSearch feedback content for specific text
limitNoMaximum number of results to return (default: 20, max: 100)
includeNotesNoInclude internal notes in the response (default: false)

Implementation Reference

  • The primary handler function implementing the 'get_feedback' tool logic. It makes an authenticated API request to the FeedbackBasket '/feedback' endpoint with optional filters, formats the results into a structured markdown report including project info, categories, sentiments, and handles empty results or errors.
    async getFeedback(params: {
      projectId?: string;
      category?: 'BUG' | 'FEATURE' | 'REVIEW';
      status?: 'PENDING' | 'REVIEWED' | 'DONE';
      sentiment?: 'POSITIVE' | 'NEGATIVE' | 'NEUTRAL';
      limit?: number;
      search?: string;
      includeNotes?: boolean;
    } = {}): Promise<{ content: Array<{ type: string; text: string }> }> {
      try {
        const response = await this.api.post<FeedbackResponse>('/feedback', {
          limit: 20,
          includeNotes: false,
          ...params,
        });
    
        const feedback = response.data.feedback;
        if (feedback.length === 0) {
          const filters = Object.entries(params)
            .filter(([_, value]) => value !== undefined)
            .map(([key, value]) => `${key}: ${value}`)
            .join(', ');
          
          return {
            content: [{
              type: 'text',
              text: `No feedback found${filters ? ` with filters: ${filters}` : ''}.`
            }]
          };
        }
    
        const feedbackList = feedback.map(item => {
          const category = item.category || 'UNCATEGORIZED';
          const sentiment = item.sentiment || 'UNKNOWN';
          const confidenceText = item.categoryConfidence 
            ? ` (${Math.round(item.categoryConfidence * 100)}% confidence)`
            : '';
    
          return [
            `**${category}${confidenceText} | ${sentiment} | ${item.status}**`,
            `Project: ${item.project.name}`,
            `Content: ${item.content.length > 100 ? item.content.substring(0, 100) + '...' : item.content}`,
            item.email ? `Email: ${item.email}` : '',
            item.notes && params.includeNotes ? `Notes: ${item.notes}` : '',
            `Created: ${new Date(item.createdAt).toLocaleDateString()}`,
            ''
          ].filter(Boolean).join('\n');
        }).join('\n');
    
        const summary = [
          `# Feedback Results (${feedback.length} of ${response.data.pagination.totalCount})\n`,
          feedbackList,
          response.data.pagination.hasMore ? `\n*Showing first ${feedback.length} results. Use offset parameter to get more.*` : '',
          `\n*API Key: ${response.data.apiKeyInfo.name}*`
        ].join('\n');
    
        return {
          content: [{
            type: 'text',
            text: summary
          }]
        };
      } catch (error) {
        throw this.handleError('Failed to fetch feedback', error);
      }
    }
  • src/index.ts:74-115 (registration)
    Tool registration in the MCP ListTools response, defining the 'get_feedback' tool's name, description, and complete input schema for validation.
      name: 'get_feedback',
      description: 'Get feedback from your FeedbackBasket projects with filtering options',
      inputSchema: {
        type: 'object',
        properties: {
          projectId: {
            type: 'string',
            description: 'Filter by specific project ID',
          },
          category: {
            type: 'string',
            enum: ['BUG', 'FEATURE', 'REVIEW'],
            description: 'Filter by feedback category',
          },
          status: {
            type: 'string',
            enum: ['PENDING', 'REVIEWED', 'DONE'],
            description: 'Filter by feedback status',
          },
          sentiment: {
            type: 'string',
            enum: ['POSITIVE', 'NEGATIVE', 'NEUTRAL'],
            description: 'Filter by sentiment analysis result',
          },
          search: {
            type: 'string',
            description: 'Search feedback content for specific text',
          },
          limit: {
            type: 'number',
            description: 'Maximum number of results to return (default: 20, max: 100)',
            minimum: 1,
            maximum: 100,
          },
          includeNotes: {
            type: 'boolean',
            description: 'Include internal notes in the response (default: false)',
          },
        },
        additionalProperties: false,
      },
    },
  • MCP server handler for CallToolRequest that delegates 'get_feedback' calls to the FeedbackBasketClient.getFeedback method.
    case 'get_feedback':
      return await client.getFeedback(args || {});
  • Type definitions used by the getFeedback handler for typing the API response, including feedback items, pagination, and filters.
    export interface FeedbackResponse {
      feedback: Feedback[];
      pagination: {
        totalCount: number;
        limit: number;
        offset: number;
        hasMore: boolean;
        nextOffset: number | null;
      };
      filters: {
        projectId?: string;
        category?: string;
        status?: string;
        sentiment?: string;
        search?: string;
      };
      apiKeyInfo: {
        name: string;
        usageCount: number;
      };
    }
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It only mentions 'filtering options' without explaining important behaviors like whether this is a read-only operation, how results are ordered, pagination details, rate limits, or authentication requirements. For a tool with 7 parameters and no annotation coverage, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that gets straight to the point without unnecessary words. It's appropriately sized for the tool's complexity and front-loads the core functionality.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 7 parameters, no annotations, and no output schema, the description is inadequate. It doesn't explain what the tool returns, how results are structured, or provide behavioral context needed for proper usage. The description should do more to compensate for the lack of structured metadata.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description mentions 'filtering options' which aligns with the schema's filtering parameters, but adds no specific semantic information beyond what the 100% schema coverage already provides. The schema descriptions fully document each parameter's purpose, enums, and defaults, so the description doesn't add meaningful value here.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Get feedback') and resource ('from your FeedbackBasket projects'), making the purpose understandable. However, it doesn't distinguish this tool from its sibling 'search_feedback' which appears to serve a similar filtering/search function, preventing a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'search_feedback' or 'get_bug_reports'. It mentions 'filtering options' but doesn't specify when these filters are appropriate or what scenarios warrant using this tool over siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/deifos/feedbackbasket-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server