Skip to main content
Glama
CestcaVision

FlowNoter MCP Server

by CestcaVision
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Local

FlowNoter MCP Server

A Model Context Protocol (MCP) server for saving conversation notes as markdown files.

Features

  • 📝 Save agent conversation history as markdown notes

  • 🗂️ Automatically organizes notes in a notes folder

  • 🧹 Filters out thinking process and tool execution details

  • ⏰ Adds timestamps to each note

  • 🎯 Extracts clean responses from assistant messages

  • 🔧 Configurable number of conversation turns to save

Related MCP server: AI Conversation Logger

Installation

Via npm

# Install globally
npm install -g @tricrepe/flownoter

# Or use with npx (no installation needed)
npx @tricrepe/flownoter

Local Development

git clone https://github.com/tricrepe/flownoter.git
cd flownoter
npm install
npm run build

Configuration

Add this to your MCP settings configuration file:

Option 1: Using npx (Recommended)

{
  "mcpServers": {
    "flownoter": {
      "command": "npx",
      "args": ["-y", "@tricrepe/flownoter"]
    }
  }
}

Option 2: Global installation

npm install -g @tricrepe/flownoter
{
  "mcpServers": {
    "flownoter": {
      "command": "flownoter"
    }
  }
}

Option 3: Local development

{
  "mcpServers": {
    "flownoter": {
      "command": "node",
      "args": ["/path/to/flownoter/dist/index.js"]
    }
  }
}

Available Tools

save_conversation_note

Saves recent conversation messages as a markdown note.

Parameters:

  • messages (required): Array of conversation messages

    • Each message should have:

      • role: Either "user" or "assistant"

      • content: The message content

  • user_question (required): The user's question to use as the note title

  • num_messages (optional): Number of recent conversation turns to include (default: all messages)

Example:

{
  "messages": [
    {
      "role": "user",
      "content": "How do I create an MCP server?"
    },
    {
      "role": "assistant",
      "content": "To create an MCP server, you need to..."
    }
  ],
  "user_question": "Creating an MCP server",
  "num_messages": 1
}

Output Format

Notes are saved in the notes/ folder with the following format:

# [User Question]

**Created:** [ISO 8601 Timestamp]

---

## Question

[User's question]

## Answer

[Assistant's clean response without thinking process or tool calls]

File Naming

Note files are named using:

  • Sanitized version of the user's question (alphanumeric characters and Chinese characters only)

  • Timestamp for uniqueness

  • .md extension

Example: Creating_an_MCP_server_1696348800000.md

Development

Build

npm run build

Run Locally

npm start

License

ISC

Available Tools

1 tool
save_conversation_noteA

Save recent conversation messages as a markdown note. The note will be saved in the 'notes' folder with a filename based on the user's question. Automatically filters out tool calls and intermediate processing steps, keeping only user questions and final assistant responses. You can specify how many recent messages to include.

ParametersJSON Schema
NameRequiredDescriptionDefault
messagesYesArray of conversation messages to save. Tool calls and intermediate steps will be automatically filtered out.
user_questionYesThe user's question to use as the note title and filename
num_messagesNoNumber of recent messages to include (default: all provided messages)

TDQS

A3.8/5.0
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 effectively describes key behaviors: automatic filtering of tool calls/intermediate steps, markdown formatting, and file naming/saving location. However, it omits details like error handling, permissions, or rate limits, which are relevant for a write operation. The description doesn't contradict any annotations (none exist).

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 front-loaded with the core purpose in the first sentence, followed by essential details in a logical flow. Every sentence adds value: saving location, filtering behavior, and parameter guidance. It avoids redundancy and is appropriately sized for the tool's complexity, making it efficient to parse.

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

Completeness4/5

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

Given the tool's moderate complexity (3 parameters, write operation) and lack of annotations/output schema, the description provides a solid foundation by covering purpose, behavior, and basic usage. It compensates well for missing structured data, though it could be more complete by addressing potential errors or output details. No sibling tools reduce contextual demands.

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 'how many recent messages to include' (hinting at num_messages usage) and reinforcing the filtering behavior for messages. This meets the baseline for high schema coverage without significant enhancement.

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

Purpose5/5

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

The description clearly states the specific action ('save recent conversation messages as a markdown note'), resource ('notes folder'), and scope ('automatically filters out tool calls and intermediate processing steps'). It distinguishes this tool's purpose with precise details about what content is preserved and where it's saved, making it immediately actionable without ambiguity.

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 context ('recent conversation messages') and provides some guidance on parameter usage ('specify how many recent messages to include'), but it lacks explicit when-to-use directives, prerequisites, or comparisons to alternatives. Since no sibling tools are listed, the absence of differentiation is acceptable, but overall guidance remains basic.

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

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0
Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool has a single, clear purpose: saving conversation messages as markdown notes.

Naming Consistency5/5

Since there is only one tool, naming consistency is inherently perfect. The tool name 'save_conversation_note' follows a clear verb_noun pattern, but with no other tools to compare to, it cannot be inconsistent.

Tool Count2/5

A single tool is too few for a server named 'FlowNoter MCP Server', which suggests a broader note-taking or conversation management domain. While the tool is useful, the server lacks basic operations like listing, retrieving, updating, or deleting notes, making it feel incomplete and under-scoped.

Completeness2/5

The server is severely incomplete for a note-taking domain. It only provides a 'save' operation, missing essential CRUD functionality such as listing existing notes, retrieving note content, updating notes, or deleting notes. This creates significant gaps that will hinder agent workflows.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • MCP Chat Logger

    AlexiFeng
    A
    license
    B
    quality
    C
    maintenance
    A tool that preserves chat history as Markdown files, automatically adding timestamps and supporting conversation identification through session IDs.
    1
    5
    MIT

  • IDE Chat Summarizer

    RalphLi213
    F
    license
    A
    quality
    D
    maintenance
    Transforms chat conversations with AI into structured markdown summaries and automatically saves them to organized files in your notes directory. Supports different summary styles, handles large conversations through chunking, and provides tools to manage your saved summaries.
    2
    4

  • OpenClaw Memory

    liuhao6741
    A
    license
    A
    quality
    D
    maintenance
    Automatically records AI conversation turns and code changes to local Markdown files to provide persistent context across chat sessions. It enables AI agents to search history through MCP tools and provides a web viewer for browsing past discussions.
    3
    4
    Apache 2.0

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/CestcaVision/flownoter'

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