Skip to main content
Glama
andras-tkcs

noteker

by andras-tkcs
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

Noteker

Noteker is a macOS MCP server that converts handwritten PDF notes into clean Markdown using Claude Vision. Give it a PDF, get back structured text — no OCR engine, no separate models, no setup beyond an Anthropic API key.

Designed for notes exported from Noteshelf3 on iPad, but works with any handwritten PDF.

How it works

Claude ──MCP stdio──▶ noteker
                          │
               ┌──────────▼──────────┐
               │  PyMuPDF             │
               │  PDF → PNG per page  │
               └──────────┬──────────┘
                          │
               ┌──────────▼──────────┐
               │  Claude Vision API   │
               │  transcribe + format │
               └──────────┬──────────┘
                          │
               clean Markdown ──▶ Claude

Each page is rendered to an image and sent to Claude Vision, which transcribes the handwriting and formats it as Markdown in a single pass. Blank pages are skipped automatically. Pages are processed in batches of at most 5 — requests spanning more pages are automatically split into sequential batches and stitched back into one combined Markdown result.

Both tools are read-only: they never modify the source PDF or any other file.

Related MCP server: pdf2md-mcp

Tools

Tool

Description

noteker_process_pdf(file_path, note_context="", page_start=None, page_end=None)

Transcribe a local PDF of handwritten notes. Returns clean Markdown. note_context is an optional hint (e.g. "team meeting 2025-06-20") that helps Claude resolve ambiguous words. page_start / page_end are 1-based inclusive page bounds — omit both to process the whole document (capped at max_pages). Internally, pages are sent to Claude Vision in batches of at most 5 regardless of range size.

noteker_status()

Return version, config path, and whether the API key is set.

Installation

As a Claude Desktop extension (recommended)

  1. Download the latest noteker-x.y.z.mcpb from the Releases page.

  2. Double-click it (or drag it into Claude Desktop → Settings → Extensions) to install.

  3. When prompted, paste your Anthropic API key — Claude Desktop stores it securely and passes it to Noteker as ANTHROPIC_API_KEY.

That's it — no separate config file or MCP registration step needed. Extra settings (model, max_pages, dpi) are still read from ~/.noteker/config/settings.yaml if you want to override the defaults (see Configuration).

From source

Requirements: Python 3.11+, macOS

git clone https://github.com/andras-tkcs/noteker
cd noteker
python3 -m venv .venv && source .venv/bin/activate
pip install -e .

Copy and edit the config:

cp config/settings.yaml.example config/settings.yaml
# Edit config/settings.yaml — add your Anthropic API key

Register Noteker with Claude (see MCP registration) using the path .venv/bin/noteker.

Configuration

Config file location:

Context

Path

Claude Desktop extension

~/.noteker/config/settings.yaml

From source

config/settings.yaml (next to pyproject.toml)

Override

Set NOTEKER_CONFIG_DIR environment variable

anthropic:
  # API key from console.anthropic.com → API Keys
  # Can also be set via the ANTHROPIC_API_KEY environment variable.
  api_key: sk-ant-api03-...
  # Model used for transcription.
  # claude-sonnet-4-6 is recommended. Use claude-opus-4-8 for very difficult handwriting.
  model: claude-sonnet-4-6

noteker:
  # Maximum pages to process per PDF (safety cap).
  max_pages: 50
  # Rendering resolution. 150 DPI works well for most handwriting.
  # Increase to 200 if the handwriting is very small.
  dpi: 150

logging:
  level: INFO

Anthropic API key

Create a key at console.anthropic.com → API Keys. It looks like sk-ant-api03-....

You can set it in settings.yaml as shown above, or export it as an environment variable — Noteker checks both:

export ANTHROPIC_API_KEY=sk-ant-api03-...

Adding the export to ~/.zshrc means you never need it in the config file.

MCP registration

The Claude Desktop extension registers itself — no manual JSON editing needed.

For Claude Code CLI, add Noteker to the project's .claude/settings.json (the .mcpb format doesn't apply to Claude Code, which always uses a direct command path):

{
  "mcpServers": {
    "noteker": {
      "command": "/absolute/path/to/noteker/.venv/bin/noteker"
    }
  }
}

Or, with the API key passed directly instead of via settings.yaml:

{
  "mcpServers": {
    "noteker": {
      "command": "/absolute/path/to/noteker/.venv/bin/noteker",
      "env": {
        "ANTHROPIC_API_KEY": "sk-ant-api03-..."
      }
    }
  }
}

After saving the config, restart Claude Code (or reload MCP servers) and run noteker_status() to confirm the setup.

Usage

A typical session with both Noteker and Loopline:

# 1. Find the PDF on Google Drive (via loopline)
drive_list_files(query="name contains 'Meeting Notes' and mimeType='application/pdf'")
→ file_id: "1aBcD..."

# 2. Download it locally (via loopline — drive_save_to_path)
drive_save_to_path(file_id="1aBcD...")
→ /Users/you/Downloads/Meeting Notes 2025-06-20.pdf

# 3. Transcribe the handwriting (via noteker)
noteker_process_pdf(
  file_path="/Users/you/Downloads/Meeting Notes 2025-06-20.pdf",
  note_context="product team standup"
)
→ ## Page 1
  ### Action items
  - Follow up with design on the onboarding flow
  ...

Noteker is source-agnostic — any local PDF works, regardless of how it got there.

Building the .mcpb

./scripts/build_mcpb.sh

Output: noteker-<version>.mcpb. The build script creates a virtual environment at server/venv with all dependencies installed, so the extension has no runtime dependency on uv or pip. It still links against the Python 3.13 framework install used to build it, and PyMuPDF ships arch-specific wheels — build on the same OS/CPU architecture (arm64 macOS) you're targeting.

License

Apache 2.0 — see LICENSE.

Available Tools

2 tools
noteker_process_pdfA
Read-only

Convert a local PDF of handwritten notes into clean Markdown using Claude Vision.

file_path: absolute path to a PDF file on the local filesystem. note_context: optional hint about the content (e.g. 'team meeting 2025-06-20'). Helps Claude resolve ambiguous words. page_start: first page to process (1-based, inclusive). Omit to start from page 1. page_end: last page to process (1-based, inclusive). Omit to process to the last page (capped at max_pages when no range is given).

Pages are sent to Claude Vision in batches of at most 5. Requests spanning more pages are processed as several sequential batches and stitched into one result — the caller always gets back a single combined Markdown document.

ParametersJSON Schema
NameRequiredDescriptionDefault
page_endNo
file_pathYes
page_startNo
note_contextNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.6/5.0
Behavior4/5

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

The description discloses key behavioral traits: batching (max 5 pages per batch), sequential processing across batches, single combined Markdown output, and the optional 'note_context' parameter to aid resolution. The 'readOnlyHint' annotation is not contradicted as the tool does not modify input files. Slightly more detail on the max_pages cap could improve, but it's well-covered.

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 concise and well-structured, using bullet points for parameters and separate sentences for behavior. It delivers all necessary information without fluff, earning its space with every sentence.

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

Completeness5/5

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

Given the tool's complexity (4 parameters, batching logic, output schema exists), the description covers all input aspects and processing behavior clearly. The presence of an output schema reduces the need to describe return values, and the description mentions the final result is a single combined Markdown document, making it complete for an agent to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite 0% schema description coverage, the description provides thorough explanations for all four parameters: file_path (absolute path), note_context (hint for ambiguous words), page_start (1-based inclusive, default 1), and page_end (inclusive, default last page with cap). It also explains batching behavior, adding significant meaning beyond the schema.

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 tool name 'noteker_process_pdf' and description clearly state its function: converting local PDFs of handwritten notes into Markdown using Claude Vision. The verb 'Convert' and resource 'local PDF' are specific, and it implicitly distinguishes itself from the sibling 'noteker_status' which presumably checks status.

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 explains when to use it (for converting handwritten note PDFs) and provides contextual details like batching behavior and page range handling. It does not explicitly state when not to use it, but the sibling tool 'noteker_status' suggests a clear divide, making usage context adequate.

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

noteker_statusA
Read-only

Return Noteker version and configuration status.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

A4.1/5.0
Behavior4/5

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

Annotations declare readOnlyHint=true, consistent with a read operation. The description adds detail on what is returned (version and configuration status), enhancing transparency beyond the annotation.

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?

Single, front-loaded sentence with no waste. Every word is necessary.

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

Completeness5/5

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

Given zero parameters, an output schema, and clear read-only annotations, the description is fully adequate for selecting and invoking this simple tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, so baseline is 4. The description adds nothing about parameters, but none are needed.

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 tool returns 'Noteker version and configuration status,' a specific verb-resource combination. It distinguishes from the sibling 'noteker_process_pdf' which processes PDFs, not status.

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

Usage Guidelines2/5

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

No guidance on when to use this tool vs others. The description implies usage for status checks but lacks explicit context or alternatives.

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

A4.4/5.0
Disambiguation5/5

Only two tools with clearly distinct purposes: one processes PDFs into Markdown, the other returns server status. No overlap whatsoever.

Naming Consistency5/5

Both tools use the same prefix 'noteker_' and follow a verb_noun pattern ('process_pdf', 'status'), making naming predictable and consistent.

Tool Count4/5

With only two tools, the server is minimal but well-scoped for its stated purpose of converting handwritten notes from PDFs. Slightly low but reasonable.

Completeness4/5

The core functionality (PDF conversion) is fully covered, and a status tool is provided. Minor gaps like batch processing or format options are absent but not essential.

Maintenance

ActivitySlowing
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

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/andras-tkcs/noteker'

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