Skip to main content
Glama
199-mcp

Limitless MCP Server

by 199-mcp

limitless_get_detailed_analysis

Extract precise technical specifications, exact measurements, and scientific details from conversation recordings. Focus on financial data, research findings, or decision analysis while maintaining numerical accuracy.

Instructions

Deep analysis focused on technical details, exact figures, scientific terminology, and specific information. Preserves precision without generalization - ideal for extracting exact specifications, measurements, and technical discussions.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
time_expressionNoNatural time expression like 'today', 'this week' (defaults to 'today').
timezoneNoIANA timezone for date calculations.
focus_areaNoFocus analysis on specific areas: technical (scientific/medical terms, specifications), financial (numbers, costs, budgets), decisions (choices made, conclusions), research (findings, data, studies), or all.all
preserve_precisionNoMaintain exact numbers, measurements, and technical specifications without rounding or generalization.

Implementation Reference

  • Primary handler function for the 'limitless_get_detailed_analysis' tool. Fetches lifelogs for the given time range using pagination, extracts detailed structured transcripts with metadata (technical terms, numbers/figures, key phrases), then filters and analyzes content based on focus_area (technical, financial, decisions, research, or all). Returns structured analysis preserving exact details and precision.
    async (args, _extra) => {
        try {
            const timeExpression = args.time_expression || 'today';
            const parser = new NaturalTimeParser({ timezone: args.timezone });
            const timeRange = parser.parseTimeExpression(timeExpression);
            
            // Fetch all logs with pagination
            const allLogs: Lifelog[] = [];
            let cursor: string | undefined = undefined;
            
            while (true) {
                const result = await getLifelogsWithPagination(limitlessApiKey, {
                    start: timeRange.start,
                    end: timeRange.end,
                    timezone: timeRange.timezone,
                    includeMarkdown: true,
                    includeHeadings: true,
                    limit: MAX_API_LIMIT,
                    direction: 'asc',
                    cursor: cursor
                });
                
                allLogs.push(...result.lifelogs);
                
                if (!result.pagination.nextCursor || result.lifelogs.length < MAX_API_LIMIT) {
                    break;
                }
                cursor = result.pagination.nextCursor;
            }
            
            const logs = allLogs;
            
            if (logs.length === 0) {
                return { content: [{ type: "text", text: `No detailed information found for "${timeExpression}".` }] };
            }
            
            // Extract detailed transcripts with maximum context preservation
            const transcriptOptions: TranscriptOptions = {
                format: "structured",
                includeTimestamps: true,
                includeSpeakers: true,
                includeContext: true,
                preserveFormatting: true
            };
            
            const detailedAnalysis = {
                timeRange: `${timeRange.start} to ${timeRange.end}`,
                totalLifelogs: logs.length,
                focusArea: args.focus_area,
                preservePrecision: args.preserve_precision,
                analysis: [] as any[]
            };
            
            for (const lifelog of logs) {
                const transcript = TranscriptExtractor.extractRawTranscript(lifelog, transcriptOptions);
                
                // Focus analysis based on requested area
                let focusedContent: any = {};
                
                switch (args.focus_area) {
                    case "technical":
                        focusedContent = {
                            technicalTerms: transcript.metadata.technicalTermsFound,
                            specifications: transcript.segments.filter(s => 
                                /\b(?:specification|spec|requirement|parameter|protocol|algorithm|implementation|architecture|design|version|model|standard)\b/i.test(s.content)
                            ),
                            measurements: transcript.metadata.numbersAndFigures.filter(f => 
                                /\b\d+(?:\.\d+)?\s*(?:mg|kg|ml|cm|mm|km|hz|ghz|mb|gb|tb|fps|rpm|°[CF]|pH|ppm|mol|atm|bar|pascal|joule|watt|volt|amp|ohm)\b/i.test(f)
                            )
                        };
                        break;
                        
                    case "financial":
                        focusedContent = {
                            monetaryFigures: transcript.metadata.numbersAndFigures.filter(f => 
                                /\$|budget|cost|price|revenue|profit|expense|dollar|EUR|GBP|million|billion/i.test(f)
                            ),
                            percentages: transcript.metadata.numbersAndFigures.filter(f => f.includes('%')),
                            financialTerms: transcript.segments.filter(s => 
                                /\b(?:budget|cost|price|revenue|profit|loss|expense|investment|ROI|funding|valuation|equity|debt|cash flow|EBITDA|margin)\b/i.test(s.content)
                            )
                        };
                        break;
                        
                    case "decisions":
                        focusedContent = {
                            decisions: transcript.segments.filter(s => 
                                /\b(?:decided|decision|agreed|concluded|determined|chose|selected|approved|rejected|final|consensus)\b/i.test(s.content)
                            ),
                            keyChoices: transcript.metadata.keyPhrases.filter(p => 
                                /\b(?:decide|determine|choose|select|go with|option|alternative)\b/i.test(p)
                            )
                        };
                        break;
                        
                    case "research":
                        focusedContent = {
                            findings: transcript.segments.filter(s => 
                                /\b(?:study|research|data|analysis|results|findings|evidence|statistics|survey|experiment|trial|test)\b/i.test(s.content)
                            ),
                            citations: transcript.segments.filter(s => 
                                /\b(?:according to|source|reference|cited|published|journal|paper|article|report)\b/i.test(s.content)
                            ),
                            methodology: transcript.segments.filter(s => 
                                /\b(?:method|methodology|approach|technique|process|procedure|protocol|framework)\b/i.test(s.content)
                            )
                        };
                        break;
                        
                    default: // "all"
                        focusedContent = {
                            technicalTerms: transcript.metadata.technicalTermsFound,
                            numbersAndFigures: transcript.metadata.numbersAndFigures,
                            keyPhrases: transcript.metadata.keyPhrases,
                            decisions: transcript.segments.filter(s => 
                                /\b(?:decided|decision|agreed|concluded)\b/i.test(s.content)
                            ),
                            specificDetails: transcript.segments.filter(s => 
                                s.content.length > 50 && // Longer, more detailed segments
                                (/\b(?:\d+(?:\.\d+)?|\$|%|version|model|specification|exactly|precisely|specifically)\b/i.test(s.content))
                            )
                        };
                }
                
                detailedAnalysis.analysis.push({
                    lifelogId: lifelog.id,
                    title: transcript.title,
                    duration: `${Math.round(transcript.totalDuration / 60000)} minutes`,
                    participants: transcript.metadata.uniqueSpeakers,
                    wordCount: transcript.metadata.wordCount,
                    focusedContent,
                    fullTranscript: args.preserve_precision ? transcript.formattedTranscript : transcript.rawText
                });
            }
            
            return createSafeResponse(
                detailedAnalysis,
                `Detailed analysis for "${timeExpression}" (Focus: ${args.focus_area})`
            );
            
        } catch (error) {
            const errorMessage = error instanceof Error ? error.message : String(error);
            return { content: [{ type: "text", text: `Error generating detailed analysis: ${errorMessage}` }], isError: true };
        }
    }
  • Input schema validation using Zod for the tool's arguments: time_expression, timezone, focus_area, preserve_precision.
    const DetailedAnalysisArgsSchema = {
        time_expression: z.string().optional().describe("Natural time expression like 'today', 'this week' (defaults to 'today')."),
        timezone: z.string().optional().describe("IANA timezone for date calculations."),
        focus_area: z.enum(["technical", "financial", "decisions", "research", "all"]).optional().default("all").describe("Focus analysis on specific areas: technical (scientific/medical terms, specifications), financial (numbers, costs, budgets), decisions (choices made, conclusions), research (findings, data, studies), or all."),
        preserve_precision: z.boolean().optional().default(true).describe("Maintain exact numbers, measurements, and technical specifications without rounding or generalization."),
    };
  • src/server.ts:989-992 (registration)
    MCP server registration of the 'limitless_get_detailed_analysis' tool with description, schema, and handler reference.
    server.tool("limitless_get_detailed_analysis",
        "Deep analysis focused on technical details, exact figures, scientific terminology, and specific information. Preserves precision without generalization - ideal for extracting exact specifications, measurements, and technical discussions.",
        DetailedAnalysisArgsSchema,
        async (args, _extra) => {
  • Key helper function TranscriptExtractor.extractRawTranscript used by the handler to process each lifelog into detailed transcript with segments, metadata (technicalTermsFound, numbersAndFigures, keyPhrases), which drives the focused analysis.
    static extractRawTranscript(lifelog: Lifelog, options: TranscriptOptions = { format: "structured" }): DetailedTranscript {
        const {
            format = "structured",
            includeTimestamps = true,
            includeSpeakers = true,
            includeContext = true,
            preserveFormatting = false,
            timeFormat = "absolute",
            speakerFormat = "names"
        } = options;
    
        if (!lifelog.contents || lifelog.contents.length === 0) {
            return this.createEmptyTranscript(lifelog);
        }
    
        // Extract all conversation segments with full context
        const segments = this.extractSegments(lifelog.contents, {
            includeTimestamps,
            includeSpeakers,
            includeContext,
            timeFormat,
            speakerFormat
        });
    
        // Analyze content for technical terms, figures, and key phrases
        const metadata = this.analyzeContent(segments);
    
        // Generate different format outputs
        const rawText = this.generateRawText(segments, preserveFormatting);
        const formattedTranscript = this.generateFormattedTranscript(segments, format, options);
    
        const totalDuration = new Date(lifelog.endTime).getTime() - new Date(lifelog.startTime).getTime();
    
        return {
            lifelogId: lifelog.id,
            title: lifelog.title || "Untitled Conversation",
            startTime: lifelog.startTime,
            endTime: lifelog.endTime,
            totalDuration,
            segments,
            metadata,
            rawText,
            formattedTranscript
        };
    }
  • NaturalTimeParser.parseTimeExpression helper used in handler to convert natural language time_expression to precise time range for fetching lifelogs.
    parseTimeExpression(expression: string): TimeRange {
        const normalized = expression.toLowerCase().trim();
        
        // Get current time in target timezone
        const now = new Date(this.referenceTime);
        const currentDate = new Date(now.toLocaleString("en-US", { timeZone: this.timezone }));
        
        // Basic day references
        switch (normalized) {
            case "today":
                return this.getDayRange(currentDate);
            
            case "yesterday":
                const yesterday = new Date(currentDate);
                yesterday.setDate(yesterday.getDate() - 1);
                return this.getDayRange(yesterday);
            
            case "tomorrow":
                const tomorrow = new Date(currentDate);
                tomorrow.setDate(tomorrow.getDate() + 1);
                return this.getDayRange(tomorrow);
            
            // Time of day - today
            case "this morning":
            case "morning":
                return this.getTimeOfDayRange(currentDate, 6, 12);
            
            case "this afternoon":
            case "afternoon":
                return this.getTimeOfDayRange(currentDate, 12, 18);
            
            case "this evening":
            case "evening":
                return this.getTimeOfDayRange(currentDate, 18, 22);
            
            case "tonight":
            case "this night":
                return this.getTimeOfDayRange(currentDate, 20, 23, 59);
            
            case "earlier today":
            case "earlier":
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. While it mentions the tool 'preserves precision without generalization', it doesn't describe what the analysis returns, how results are structured, whether it processes transcripts or other data sources, or any performance characteristics. Significant behavioral aspects remain undocumented.

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 efficiently structured in two sentences with zero wasted words. The first sentence defines the analysis focus, and the second specifies ideal use cases. Every phrase adds value without redundancy.

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 4-parameter analysis tool with no annotations and no output schema, the description is incomplete. It doesn't explain what data source is analyzed (transcripts? lifelogs?), what format the analysis returns, or how results are presented. The technical focus is clear, but operational context is missing.

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%, providing complete parameter documentation. The description adds minimal value beyond the schema, mentioning 'technical details' and 'exact figures' which loosely relate to the 'focus_area' and 'preserve_precision' parameters but without additional semantic context. Baseline 3 is appropriate given the comprehensive schema.

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 performs 'deep analysis focused on technical details, exact figures, scientific terminology, and specific information' with a verb+resource pattern. It distinguishes itself from siblings by emphasizing precision and technical focus, though it doesn't explicitly name alternative tools for different analysis types.

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 context ('ideal for extracting exact specifications, measurements, and technical discussions') but doesn't explicitly state when to use this tool versus alternatives like 'limitless_get_daily_summary' or 'limitless_get_full_transcript'. No explicit exclusions or comparisons to sibling tools are provided.

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/199-mcp/mcp-limitless'

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