Limitless MCP Server

limitless_get_full_transcript

Retrieve complete conversation transcripts from Limitless Pendant recordings for specific dates or time ranges, handling large datasets automatically to bypass token limits.

Instructions

Fetches complete transcript data for a date/range with automatic pagination. Handles large datasets by fetching all pages internally. Use this when you need complete transcript data without worrying about token limits.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`date`	No	Specific date (YYYY-MM-DD format)
`start`	No	Start datetime (YYYY-MM-DD or YYYY-MM-DD HH:mm:SS)
`end`	No	End datetime (YYYY-MM-DD or YYYY-MM-DD HH:mm:SS)
`timezone`	No	IANA timezone
`isStarred`	No	Filter for starred lifelogs only
`format`	No	Output format: summary (key info only), full (all data), transcript_only (just text)	summary

Implementation Reference

src/server.ts:1141-1272 (registration)

Registration of the 'limitless_get_full_transcript' MCP tool, including description, Zod input schema, and inline async handler function that implements the full logic.

server.tool("limitless_get_full_transcript",
    "Fetches complete transcript data for a date/range with automatic pagination. Handles large datasets by fetching all pages internally. Use this when you need complete transcript data without worrying about token limits.",
    {
        date: z.string().optional().describe("Specific date (YYYY-MM-DD format)"),
        start: z.string().optional().describe("Start datetime (YYYY-MM-DD or YYYY-MM-DD HH:mm:SS)"),
        end: z.string().optional().describe("End datetime (YYYY-MM-DD or YYYY-MM-DD HH:mm:SS)"),
        timezone: z.string().optional().describe("IANA timezone"),
        isStarred: z.boolean().optional().describe("Filter for starred lifelogs only"),
        format: z.enum(["summary", "full", "transcript_only"]).optional().default("summary").describe("Output format: summary (key info only), full (all data), transcript_only (just text)")
    },
    async (args, _extra) => {
        try {
            // Validate date format
            if (args.date && !/^\d{4}-\d{2}-\d{2}$/.test(args.date)) {
                return { content: [{ type: "text", text: `❌ Date format error: '${args.date}' must be YYYY-MM-DD` }], isError: true };
            }
            
            const allLifelogs: Lifelog[] = [];
            let cursor: string | undefined = undefined;
            let pageCount = 0;
            
            // Fetch all pages
            while (true) {
                pageCount++;
                const result = await getLifelogsWithPagination(limitlessApiKey, {
                    date: args.date,
                    start: args.start,
                    end: args.end,
                    timezone: args.timezone,
                    isStarred: args.isStarred,
                    includeMarkdown: true,
                    includeHeadings: true,
                    limit: MAX_API_LIMIT,
                    cursor: cursor,
                    direction: 'asc'
                });
                
                allLifelogs.push(...result.lifelogs);
                
                if (!result.pagination.nextCursor || result.lifelogs.length < MAX_API_LIMIT) {
                    break;
                }
                cursor = result.pagination.nextCursor;
            }
            
            if (allLifelogs.length === 0) {
                return { content: [{ type: "text", text: "No lifelogs found for the specified criteria." }] };
            }
            
            // Format based on requested output
            let output: any;
            let description: string;
            
            switch (args.format) {
                case "transcript_only":
                    // Extract just the transcript text
                    const transcripts = allLifelogs.map(log => ({
                        id: log.id,
                        date: log.startTime.split('T')[0],
                        transcript: log.markdown || "[No transcript available]"
                    }));
                    output = transcripts;
                    description = `Complete transcripts for ${allLifelogs.length} lifelogs (${pageCount} pages fetched)`;
                    break;
                    
                case "full":
                    // Return all data
                    output = allLifelogs;
                    description = `Complete data for ${allLifelogs.length} lifelogs (${pageCount} pages fetched)`;
                    break;
                    
                case "summary":
                default:
                    // Return summary with key information
                    const summaries = allLifelogs.map(log => ({
                        id: log.id,
                        title: log.title || "[Untitled]",
                        date: log.startTime.split('T')[0],
                        time: `${log.startTime.split('T')[1]?.split('.')[0]} - ${log.endTime.split('T')[1]?.split('.')[0]}`,
                        duration: calculateDuration(log.startTime, log.endTime),
                        starred: log.isStarred || false,
                        wordCount: log.markdown ? log.markdown.split(/\s+/).length : 0
                    }));
                    output = {
                        total: allLifelogs.length,
                        pages_fetched: pageCount,
                        date_range: {
                            start: allLifelogs[0].startTime,
                            end: allLifelogs[allLifelogs.length - 1].endTime
                        },
                        lifelogs: summaries
                    };
                    description = `Summary of ${allLifelogs.length} lifelogs`;
                    break;
            }
            
            // Check size and handle appropriately
            const estimatedSize = estimateTokens(JSON.stringify(output));
            if (estimatedSize > MAX_RESPONSE_TOKENS) {
                // Save to a structured format that can be processed in chunks
                return {
                    content: [{
                        type: "text",
                        text: `⚠️ Data too large for single response (${Math.ceil(estimatedSize / 1000)}k tokens)

Successfully fetched ${allLifelogs.length} lifelogs across ${pageCount} pages.

To access this data:
1. Use the regular list tools with cursor pagination
2. Request specific lifelogs by ID
3. Use the search or analytics tools for specific queries

Summary:
- Total lifelogs: ${allLifelogs.length}
- Date range: ${allLifelogs[0].startTime.split('T')[0]} to ${allLifelogs[allLifelogs.length - 1].endTime.split('T')[0]}
- Total word count: ${allLifelogs.reduce((sum, log) => sum + (log.markdown ? log.markdown.split(/\s+/).length : 0), 0).toLocaleString()}
- Starred items: ${allLifelogs.filter(log => log.isStarred).length}

First few IDs for reference:
${allLifelogs.slice(0, 5).map(log => `- ${log.id}: ${log.title || '[Untitled]'}`).join('\n')}`
                    }]
                };
            }
            
            return { content: [{ type: "text", text: `${description}:\n\n${JSON.stringify(output, null, 2)}` }] };
            
        } catch (error) {
            return handleToolApiCall(() => Promise.reject(error));
        }
    }
);

src/server.ts:1151-1271 (handler)

Core handler logic: Loops to fetch ALL paginated lifelogs using getLifelogsWithPagination, aggregates them, then formats output as summary/full/transcript_only, calculates durations, and handles token limit truncation with warnings.

    async (args, _extra) => {
        try {
            // Validate date format
            if (args.date && !/^\d{4}-\d{2}-\d{2}$/.test(args.date)) {
                return { content: [{ type: "text", text: `❌ Date format error: '${args.date}' must be YYYY-MM-DD` }], isError: true };
            }
            
            const allLifelogs: Lifelog[] = [];
            let cursor: string | undefined = undefined;
            let pageCount = 0;
            
            // Fetch all pages
            while (true) {
                pageCount++;
                const result = await getLifelogsWithPagination(limitlessApiKey, {
                    date: args.date,
                    start: args.start,
                    end: args.end,
                    timezone: args.timezone,
                    isStarred: args.isStarred,
                    includeMarkdown: true,
                    includeHeadings: true,
                    limit: MAX_API_LIMIT,
                    cursor: cursor,
                    direction: 'asc'
                });
                
                allLifelogs.push(...result.lifelogs);
                
                if (!result.pagination.nextCursor || result.lifelogs.length < MAX_API_LIMIT) {
                    break;
                }
                cursor = result.pagination.nextCursor;
            }
            
            if (allLifelogs.length === 0) {
                return { content: [{ type: "text", text: "No lifelogs found for the specified criteria." }] };
            }
            
            // Format based on requested output
            let output: any;
            let description: string;
            
            switch (args.format) {
                case "transcript_only":
                    // Extract just the transcript text
                    const transcripts = allLifelogs.map(log => ({
                        id: log.id,
                        date: log.startTime.split('T')[0],
                        transcript: log.markdown || "[No transcript available]"
                    }));
                    output = transcripts;
                    description = `Complete transcripts for ${allLifelogs.length} lifelogs (${pageCount} pages fetched)`;
                    break;
                    
                case "full":
                    // Return all data
                    output = allLifelogs;
                    description = `Complete data for ${allLifelogs.length} lifelogs (${pageCount} pages fetched)`;
                    break;
                    
                case "summary":
                default:
                    // Return summary with key information
                    const summaries = allLifelogs.map(log => ({
                        id: log.id,
                        title: log.title || "[Untitled]",
                        date: log.startTime.split('T')[0],
                        time: `${log.startTime.split('T')[1]?.split('.')[0]} - ${log.endTime.split('T')[1]?.split('.')[0]}`,
                        duration: calculateDuration(log.startTime, log.endTime),
                        starred: log.isStarred || false,
                        wordCount: log.markdown ? log.markdown.split(/\s+/).length : 0
                    }));
                    output = {
                        total: allLifelogs.length,
                        pages_fetched: pageCount,
                        date_range: {
                            start: allLifelogs[0].startTime,
                            end: allLifelogs[allLifelogs.length - 1].endTime
                        },
                        lifelogs: summaries
                    };
                    description = `Summary of ${allLifelogs.length} lifelogs`;
                    break;
            }
            
            // Check size and handle appropriately
            const estimatedSize = estimateTokens(JSON.stringify(output));
            if (estimatedSize > MAX_RESPONSE_TOKENS) {
                // Save to a structured format that can be processed in chunks
                return {
                    content: [{
                        type: "text",
                        text: `⚠️ Data too large for single response (${Math.ceil(estimatedSize / 1000)}k tokens)

Successfully fetched ${allLifelogs.length} lifelogs across ${pageCount} pages.

To access this data:
1. Use the regular list tools with cursor pagination
2. Request specific lifelogs by ID
3. Use the search or analytics tools for specific queries

Summary:
- Total lifelogs: ${allLifelogs.length}
- Date range: ${allLifelogs[0].startTime.split('T')[0]} to ${allLifelogs[allLifelogs.length - 1].endTime.split('T')[0]}
- Total word count: ${allLifelogs.reduce((sum, log) => sum + (log.markdown ? log.markdown.split(/\s+/).length : 0), 0).toLocaleString()}
- Starred items: ${allLifelogs.filter(log => log.isStarred).length}

First few IDs for reference:
${allLifelogs.slice(0, 5).map(log => `- ${log.id}: ${log.title || '[Untitled]'}`).join('\n')}`
                    }]
                };
            }
            
            return { content: [{ type: "text", text: `${description}:\n\n${JSON.stringify(output, null, 2)}` }] };
            
        } catch (error) {
            return handleToolApiCall(() => Promise.reject(error));
        }
    }
);

src/server.ts:1143-1150 (schema)

Zod schema defining input parameters for the tool: date/range filters, timezone, starred filter, and output format.

{
    date: z.string().optional().describe("Specific date (YYYY-MM-DD format)"),
    start: z.string().optional().describe("Start datetime (YYYY-MM-DD or YYYY-MM-DD HH:mm:SS)"),
    end: z.string().optional().describe("End datetime (YYYY-MM-DD or YYYY-MM-DD HH:mm:SS)"),
    timezone: z.string().optional().describe("IANA timezone"),
    isStarred: z.boolean().optional().describe("Filter for starred lifelogs only"),
    format: z.enum(["summary", "full", "transcript_only"]).optional().default("summary").describe("Output format: summary (key info only), full (all data), transcript_only (just text)")
},

src/server.ts:1274-1282 (helper)

Utility function to format duration from start/end ISO timestamps into human-readable 'Xh Ym' or 'Zm', used in summary output.

function calculateDuration(start: string, end: string): string {
    const startTime = new Date(start).getTime();
    const endTime = new Date(end).getTime();
    const durationMs = endTime - startTime;
    const minutes = Math.floor(durationMs / 60000);
    const hours = Math.floor(minutes / 60);
    const mins = minutes % 60;
    return hours > 0 ? `${hours}h ${mins}m` : `${minutes}m`;
}

src/limitless-client.ts:267-302 (helper)

Key helper function called by the handler to fetch a single page of lifelogs with pagination metadata from Limitless API. Handler loops this to get full dataset.

export async function getLifelogsWithPagination(apiKey: string, options: LifelogParams = {}): Promise<LifelogsWithPagination> {
    const defaultTimezone = getDefaultTimezone();
    const batchSize = options.limit || 10; // Use requested limit as batch size

    const params: Record<string, string | number | boolean | undefined> = {
        limit: batchSize,
        includeMarkdown: options.includeMarkdown ?? true,
        includeHeadings: options.includeHeadings ?? true,
        date: options.date,
        start: options.start,
        end: options.end,
        direction: options.direction ?? 'desc',
        timezone: options.timezone ?? defaultTimezone,
        cursor: options.cursor,
        isStarred: options.isStarred,
    };

    // Clean up undefined values
    Object.keys(params).forEach(key => {
        if (params[key] === undefined) delete params[key];
    });

    const response = await makeApiRequest<LifelogsResponse>(apiKey, "v1/lifelogs", params);
    const lifelogs = response.data?.lifelogs ?? [];
    const nextCursor = response.meta?.lifelogs?.nextCursor;
    const count = response.meta?.lifelogs?.count ?? lifelogs.length;

    return {
        lifelogs,
        pagination: {
            nextCursor,
            hasMore: !!nextCursor,
            count
        }
    };
}

Tool Definition Quality

A3.7/5.0

Behavior3/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds valuable context about 'automatic pagination' and handling 'large datasets by fetching all pages internally', which goes beyond what the input schema provides. However, it doesn't mention potential rate limits, authentication requirements, error conditions, or what the return format looks like (though there's no output schema).

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 perfectly concise with two sentences that each earn their place. The first sentence explains what the tool does and its key features. The second sentence provides clear usage guidance. There's zero wasted language or redundancy.

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 the complexity (6 parameters, no annotations, no output schema), the description provides adequate but incomplete context. It explains the core functionality and when to use it, but doesn't describe the return format or potential limitations. For a data-fetching tool with no output schema, the description should ideally mention what kind of data structure to expect.

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 6 parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema. It mentions 'date/range' which aligns with the date/start/end parameters, but provides no additional syntax or format details. The baseline of 3 is appropriate when 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 'fetches complete transcript data for a date/range with automatic pagination', which is a specific verb+resource combination. However, it doesn't explicitly differentiate from sibling tools like 'limitless_get_raw_transcript' or 'limitless_list_lifelogs_by_range', which might have overlapping functionality. The purpose is clear but lacks sibling differentiation.

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

Usage Guidelines4/5

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

The description provides clear context for when to use this tool: 'Use this when you need complete transcript data without worrying about token limits.' This gives explicit guidance on the primary use case. However, it doesn't mention when NOT to use it or name specific alternatives among the many sibling tools, which would be needed for a perfect score.

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

Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
open source
OpenAI
Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security

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