Skip to main content
Glama
anortham

COA Goldfish MCP

by anortham

timeline

Track work sessions and project activities using checkpoints grouped by date and workspace. Supports filtering by time range, scope, and workspace for standups or task reviews.

Instructions

Show timeline of work sessions. Perfect for standups and understanding recent activity across projects. Shows checkpoints grouped by date and workspace.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
scopeNoTimeline scope: current workspace or all workspaces
sinceNoTime range to show (default: "7d")
workspaceNoSpecific workspace (optional)

Implementation Reference

  • The primary handler function for the 'timeline' MCP tool. It fetches recent checkpoints using SearchEngine, groups them chronologically by local date and workspace, generates a formatted text summary with highlights, supports VS Code visualization, and returns structured data.
    async timeline(args: {
      since?: string;
      workspace?: string;
      scope?: 'current' | 'all';
      format?: OutputMode;
    }) {
      const {
        since = '7d',
        workspace,
        scope = 'current',
        format
      } = args;
    
      try {
        const memories = await this.searchEngine.searchMemories({
          since,
          workspace: scope === 'all' ? undefined : workspace,
          scope,
          type: 'checkpoint',
          limit: 200
        });
    
        if (memories.length === 0) {
          const formatted = `📅 No work sessions found in the last ${since}\n\nTry extending the time range or checking other workspaces.`;
          const data = {
            scope,
            since,
            workspace,
            totalItems: 0,
            workspacesFound: 0,
            checkpointsFound: 0,
            byDate: {},
            byWorkspace: {}
          } as const;
          return buildToolContent('timeline', formatted, data as any, format);
        }
    
        // Group by date and workspace
        const timelineMap = new Map<string, Map<string, { count: number; highlights: string[] }>>();
        
        for (const memory of memories) {
          // Extract local date key for user-intuitive timeline grouping
          const date = getLocalDateKey(memory.timestamp);
          const ws = memory.workspace || 'unknown';
          
          if (!timelineMap.has(date)) {
            timelineMap.set(date, new Map());
          }
          
          const dayMap = timelineMap.get(date);
          if (!dayMap) continue;
          
          if (!dayMap.has(ws)) {
            dayMap.set(ws, { count: 0, highlights: [] });
          }
          
          const wsData = dayMap.get(ws)!;
          wsData.count++;
          
          // Extract highlights
          if (typeof memory.content === 'object' && memory.content && 'highlights' in memory.content) {
            const contentObj = memory.content as { highlights?: string[] };
            if (Array.isArray(contentObj.highlights)) {
              wsData.highlights.push(...contentObj.highlights);
            }
          }
        }
    
        // Build formatted output
        const output = [`📅 Work Timeline (${since})`];
        
        const sortedDates = Array.from(timelineMap.keys()).sort().reverse();
        
        for (const date of sortedDates) {
          const dayData = timelineMap.get(date)!;
          // Use centralized date formatting utility for consistent Today/Yesterday logic
          const dayName = formatDateName(date);
          
          output.push(`\n**${dayName}** (${date})`);
          
          for (const [ws, data] of dayData.entries()) {
            const wsDisplay = ws; // Always show actual workspace name
            output.push(`  📁 ${wsDisplay}: ${data.count} checkpoints`);
            
            // Show unique highlights
            const uniqueHighlights = [...new Set(data.highlights)];
            if (uniqueHighlights.length > 0) {
              uniqueHighlights.slice(0, 3).forEach(highlight => {
                output.push(`     ✨ ${highlight}`);
              });
              if (uniqueHighlights.length > 3) {
                output.push(`     ... and ${uniqueHighlights.length - 3} more`);
              }
            }
          }
        }
    
        // Send to VS Code if available
        if (this.displayHandler?.isAvailable) {
          try {
            await this.displayHandler.displayTimeline(memories, `Work Timeline (${since})`);
            console.error('📊 Timeline sent to VS Code');
          } catch (error) {
            console.error('⚠️ Failed to send timeline to VS Code:', error);
          }
        }
    
        const formatted = output.join('\n');
        const data = {
          scope,
          since,
          workspace,
          totalItems: memories.length,
          workspacesFound: new Set(memories.map(m => m.workspace || 'unknown')).size,
          checkpointsFound: memories.filter(m => m.type === 'checkpoint').length,
          byDate: Object.fromEntries(Array.from(timelineMap.entries()).map(([date, wsMap]) => [
            date,
            Object.fromEntries(wsMap.entries())
          ])),
          byWorkspace: {}
        } as const;
    
        return buildToolContent('timeline', formatted, data as any, format);
      } catch (error) {
        return {
          content: [
            {
              type: 'text',
              text: `❌ Timeline failed: ${error instanceof Error ? error.message : String(error)}`
            }
          ]
        };
      }
  • Defines the input schema and metadata for the 'timeline' tool, including optional parameters for time range, workspace filtering, scope, and output format.
      name: 'timeline',
      description: 'Review work progress chronologically. Use when user asks "what did I do" or needs timeline view for reporting.',
      inputSchema: {
        type: 'object',
        properties: {
          since: {
            type: 'string',
            description: 'Time range to show (default: "7d")',
            default: '7d'
          },
          workspace: {
            type: 'string',
            description: 'Workspace name or path (e.g., "coa-goldfish-mcp" or "C:\\source\\COA Goldfish MCP"). Will be normalized automatically.'
          },
          scope: {
            type: 'string',
            enum: ['current', 'all'],
            description: 'Timeline scope: current workspace or all workspaces',
            default: 'current'
          },
          format: {
            type: 'string',
            enum: ['plain', 'emoji', 'json', 'dual'],
            description: 'Output format override (defaults to env GOLDFISH_OUTPUT_MODE or dual)'
          }
        }
      }
    },
  • Registers the runtime handler dispatch for the 'timeline' tool in the main tool call switch statement, invoking SearchTools.timeline.
    case 'timeline':
      return await this.searchTools.timeline(args || {});
  • Registers the 'timeline' tool schema by including SearchTools.getToolSchemas() in the list of available tools returned by ListToolsRequestHandler.
    // Search and timeline tools
    ...SearchTools.getToolSchemas(),
Behavior2/5

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

No annotations are provided, so the description carries the full burden. It mentions grouping behavior ('grouped by date and workspace') but doesn't disclose other traits like pagination, rate limits, authentication needs, or what 'work sessions' entail. For a read-only tool with no annotations, this leaves significant behavioral gaps.

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

Conciseness4/5

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

The description is appropriately sized with three concise sentences. It's front-loaded with the core purpose, followed by usage context and output details. No wasted words, though it could be slightly more structured for clarity.

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

Completeness3/5

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

Given no annotations and no output schema, the description is moderately complete for a read-only tool with good schema coverage. It covers purpose and usage but lacks details on return format, error handling, or behavioral constraints. It's adequate but has clear gaps in transparency.

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?

Schema description coverage is 100%, so the schema already documents all parameters well. The description adds minimal value beyond the schema by implying the output structure ('grouped by date and workspace'), but doesn't explain parameter interactions (e.g., how 'workspace' interacts with 'scope'). Baseline 3 is appropriate as the schema does the heavy lifting.

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 tool's purpose: 'Show timeline of work sessions' with specific context about what it displays ('checkpoints grouped by date and workspace'). It distinguishes from siblings like 'checkpoint' (individual) and 'search_history' (search-focused), though not explicitly named. However, it doesn't fully differentiate from 'summarize_session' which might overlap in showing activity.

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

Usage Guidelines3/5

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

The description provides implied usage guidelines: 'Perfect for standups and understanding recent activity across projects' suggests when to use it. However, it lacks explicit alternatives (e.g., vs. 'search_history' for filtering or 'summarize_session' for summaries) and doesn't specify when not to use it, leaving some ambiguity.

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

Related 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/anortham/coa-goldfish-mcp'

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