Skip to main content
Glama
smcdonnell7

Meeting Chief Lite

by smcdonnell7
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Meeting Chief Lite

Minimal meeting transcript sync and search MCP. Downloads meetings from Otter.ai, stores them in SQLite, and provides semantic search via MCP tools.

Features

  • Otter.ai Sync: Download meeting transcripts automatically

  • Semantic Search: Find relevant transcript chunks using embeddings

  • Keyword Search: Fallback for exact text matching

  • MCP Tools: 3 focused tools for Claude/Cursor integration

Related MCP server: ChatCrystal

Tools

Tool

Description

meetings

List, get, and browse meeting transcripts

search

Semantic and keyword search across transcripts

status

System health, sync status, and management

Quick Start

1. Configure Environment

cp .env.example .env
# Edit .env with your credentials:
# - OTTER_EMAIL
# - OTTER_PASSWORD
# - OPENROUTER_API_KEY

2. Run with Docker

# Build and run
docker compose up -d

# Or run directly
docker run -it \
  -e OTTER_EMAIL=your@email.com \
  -e OTTER_PASSWORD=yourpassword \
  -e OPENROUTER_API_KEY=sk-or-v1-xxx \
  -v meeting-chief-data:/data \
  ghcr.io/smcdonnell7/meeting-chief-lite

3. Configure MCP Client

Cursor (~/.cursor/mcp.json):

{
  "mcpServers": {
    "meeting-chief-lite": {
      "command": "docker",
      "args": ["run", "-i", "--rm",
        "-e", "OTTER_EMAIL",
        "-e", "OTTER_PASSWORD", 
        "-e", "OPENROUTER_API_KEY",
        "-v", "meeting-chief-data:/data",
        "ghcr.io/smcdonnell7/meeting-chief-lite"
      ]
    }
  }
}

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "meeting-chief-lite": {
      "command": "docker",
      "args": ["run", "-i", "--rm",
        "-e", "OTTER_EMAIL=your@email.com",
        "-e", "OTTER_PASSWORD=yourpassword",
        "-e", "OPENROUTER_API_KEY=sk-or-v1-xxx",
        "-v", "meeting-chief-data:/data",
        "ghcr.io/smcdonnell7/meeting-chief-lite"
      ]
    }
  }
}

Usage Examples

# List recent meetings
meetings operation:list limit:10

# Get specific meeting
meetings operation:get id:meeting_123

# Search transcripts
search query:"API migration" mode:semantic

# Search with date filter
search query:"budget" after:2026-01-01

# Check system status
status operation:health

# Sync from Otter.ai
status operation:run_sync sync_days:30

# Generate embeddings for new meetings
status operation:generate_embeddings

Database

SQLite database with 7 tables:

  • meetings - Meeting metadata and transcripts

  • transcript_chunks - Parsed transcript segments

  • transcript_vectors - Embeddings for semantic search

  • embedding_jobs - Embedding generation queue

  • sync_runs - Sync audit log

  • speakers - People roster

  • app_settings - Configuration

Development

# Install dependencies
npm install

# Build
npm run build

# Run locally
npm start

License

MIT

Available Tools

3 tools
meetingsB

Browse and retrieve meeting transcripts from Otter.ai. Operations: list (browse all), get (specific meeting), recent (last N days), stats (database info).

ParametersJSON Schema
NameRequiredDescriptionDefault
operationYesOperation to perform
idNoMeeting ID (required for "get" operation)
limitNoMaximum results to return (default: 20)
offsetNoPagination offset (default: 0)
daysNoNumber of days for "recent" operation (default: 7)

TDQS

B3.1/5.0
Behavior2/5

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. While it lists operations, it doesn't describe important behavioral traits like whether this is a read-only operation, authentication requirements, rate limits, pagination behavior beyond the schema's offset/limit, error handling, or what 'stats' returns. For a tool with 5 parameters and multiple operations, this leaves significant gaps in understanding how it behaves.

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 concise with two sentences that efficiently communicate the tool's purpose and operations. The structure is front-loaded with the core purpose followed by operational details. Every sentence earns its place, though the second sentence 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.

Completeness2/5

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

Given the tool's complexity (5 parameters, 4 distinct operations, no annotations, no output schema), the description is incomplete. It doesn't explain what the tool returns for different operations, how results are structured, error conditions, or behavioral constraints. For a multi-operation tool with no output schema, the description should provide more context about expected outputs and operational boundaries.

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 thoroughly. The description adds minimal value beyond the schema by mentioning the operations that correspond to the 'operation' enum values, but doesn't provide additional semantic context about parameter interactions or usage patterns. This meets the baseline for high schema coverage.

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 as 'Browse and retrieve meeting transcripts from Otter.ai' with specific operations listed (list, get, recent, stats). It distinguishes itself from the 'search' sibling tool by focusing on browsing/retrieving rather than searching, though the distinction could be more explicit. The verb+resource combination is specific and actionable.

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 implies usage through the listed operations but doesn't explicitly state when to use this tool versus the 'search' sibling tool. It provides operational context (list for all, get for specific, recent for last N days, stats for database info) but lacks clear guidance on tool selection criteria or exclusion scenarios. The implied usage is helpful but not comprehensive.

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

statusC

System health, sync status, and management operations. Use health to check system state, sync to see last sync info, stats for database statistics, generate_embeddings to process pending jobs, run_sync to sync from Otter.ai.

ParametersJSON Schema
NameRequiredDescriptionDefault
operationYesOperation to perform
sync_daysNoDays of history to sync (default: 90)

TDQS

C2.9/5.0
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 mentions operations but doesn't clarify whether these are read-only or mutating operations (e.g., 'generate_embeddings' and 'run_sync' sound like mutating operations). No information about permissions, side effects, rate limits, or what happens when operations fail is provided.

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

Conciseness3/5

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

The description is reasonably concise but could be better structured. It starts with a vague phrase 'System health, sync status, and management operations' then lists operations. The information is front-loaded but the initial phrase doesn't clearly communicate the tool's purpose. Some sentences could be more efficiently worded.

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 5 distinct operations (some potentially mutating), no annotations, and no output schema, the description is insufficient. It doesn't explain what each operation returns, what 'sync from Otter.ai' entails, what 'pending jobs' means for generate_embeddings, or any error conditions. The description leaves too many behavioral questions unanswered.

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 both parameters thoroughly. The description doesn't add meaningful parameter semantics beyond what's in the schema - it lists operation names but doesn't explain them further. 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.

Purpose3/5

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

The description lists multiple operations (health, sync, stats, generate_embeddings, run_sync) but doesn't clearly state a unified purpose. It reads more like a menu of options rather than a coherent tool purpose. While it distinguishes from sibling tools 'meetings' and 'search' by focusing on system operations, it lacks a clear overarching verb+resource statement.

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 explicit guidance on when to use each operation: 'Use health to check system state, sync to see last sync info, stats for database statistics, generate_embeddings to process pending jobs, run_sync to sync from Otter.ai.' This gives clear context for each option, though it doesn't explicitly state when NOT to use this tool versus alternatives.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv1.0.0
    • First observedmeetings
    • First observedsearch
    • First observedstatus
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: 'meetings' handles browsing and retrieving transcripts, 'search' focuses on finding content within transcripts, and 'status' manages system health and operations. The descriptions clearly differentiate these domains, eliminating any ambiguity for agent selection.

Naming Consistency5/5

All tool names follow a consistent, simple noun-based pattern ('meetings', 'search', 'status') that is readable and predictable. There are no deviations in style or convention, making the set easy to navigate and understand.

Tool Count4/5

With 3 tools, the count is slightly low but reasonable for a 'lite' server focused on meeting transcripts. It covers core operations (browse, search, status), though it might benefit from additional tools for actions like updating or deleting data, but it's well-scoped for its apparent purpose.

Completeness4/5

The tool set provides good coverage for browsing, searching, and managing meeting transcripts, with no obvious dead ends. Minor gaps exist, such as lack of explicit update or delete operations for transcripts, but agents can likely work around this given the server's focus on retrieval and search.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • cursor-history-mcp

    S2thend
    A
    license
    A
    quality
    A
    maintenance
    MCP server for browsing, searching, exporting, and backing up your Cursor AI chat history directly into Claude via natural language.
    8
    144 npm
    32
    MIT

  • ChatCrystal

    ZengLiangYi
    A
    license
    A
    quality
    A
    maintenance
    Local-first AI PKM memory server for coding conversations. Imports Claude Code, Cursor, Codex CLI, Trae, and GitHub Copilot chats into notes, semantic search, tag graphs, Markdown exports, and MCP memory tools.
    7
    121 npm
    58
    Apache 2.0
  • LoreConvo by labyrinth-analytics

    LoreConvoofficial

    labyrinth-analytics
    A
    license
    A
    quality
    A
    maintenance
    Persistent memory layer for MCP-compatible AI agents. Implements save/recall/search over a local SQLite session store via 14 MCP tools. Auto-loads relevant context at session start. No cloud dependency. Works with Claude, Cursor, Codex, Hermes Agent. Free (50 sessions) / Pro ($8/mo).
    33
    62 PyPI
    10
    Business Source 1.1