Super-MCP-OCR-Deepseek
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Super-MCP-OCR-DeepseekExtract text from this image and analyze it"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
๐ฆ Super MCP OCR for DeepSeek (teks-only LLM) 
Memberi "mata" ke model AI yang tidak punya vision (mis. DeepSeek v4 Flash, DeepSeek R1, atau LLM teks-only lain) โ semua gambar & dokumen dibaca jadi teks murni yang bisa langsung dianalisa.
Gambar / PDF / Word / Excel / PPT
โ
โผ
[ MCP OCR Server ] โโโบ teks murni โโโบ LLM bisa baca & jawabโจ Fitur
Format | Cara baca |
๐ผ๏ธ Gambar โ png, jpg/jpeg, webp, bmp, gif, tif/tiff | OCR (RapidOCR + pre-process) |
๐ PDF | teks asli diekstrak; halaman scan otomatis di-OCR per halaman (max 25 hal) |
๐ Office โ docx, xlsx/xlsm, pptx, rtf | ekstrak paragraf, tabel, slide |
๐ Teks โ txt, md, csv, json, xml, log, yaml, toml, html | baca langsung |
Tidak didukung: .doc / .xls versi lama โ simpan ulang sebagai .docx / .xlsx.
Tool yang tersedia:
read_document(file_path, mode, enhance)โ nama penuh (teks)ocr_image(image_path, mode, enhance)โ alias kompatibel (teks)read_colors(file_path, top_n=8, merge=true)โ ๐จ ekstrak warna dominan dari gambar
Related MCP server: docling-mcp
๐จ Baca Warna dari Gambar (read_colors)
Model teks-only juga tidak bisa melihat warna. read_colors terjemahkan warna gambar jadi teks berstruktur โ hex, rgb, nama, shade, persentase area, dan posisi region. Cocok buat: copy-paste screenshot halaman web, mau ganti warna desain, cari nilai hex yang dipakai.
read_colors(file_path="web-design.png")
read_colors(file_path="ui.png", top_n=12) # lebih banyak warna
read_colors(file_path="ui.png", merge=false) # tanpa gabung shade dekatParam | Nilai | Fungsi |
| path gambar lokal / URL | wajib |
|
| jumlah warna teratas |
|
| gabung warna nyaris-sama (<30 delta) |
Contoh output:
[COLORS] web-design.png โ 1280x800px โ top 6 warna dominan
1. #FFFFFF rgb(255, 255, 255) ~white (light) 53.1% posisi: background
2. #1F2937 rgb(31, 41, 55) ~custom (dark) 19.8% posisi: header/navbar
3. #3B82F6 rgb(59, 130, 246) ~custom (dark) 6.5% posisi: accent/panelRegion label: background, header/navbar, footer, sidebar, panel/card, accent/button/text, band. Nilai hex sudah siap tempel ke CSS/Tailwind. Warna tanpa nama umum (Tailwind dll) dilabel ~custom โ pakai hex/rgb-nya.
Flow copas web: gambar di-paste di chat โ
extract-pasted-image.pyโread_colors(...)โ dapat hex โ edit warna.
๐ฏ Kenapa ini penting?
Banyak LLM yang murah/cepat hanya teks-only โ mereka menolak gambar (Cannot read image / model does not support image input). Padahal pengguna sering paste screenshot error, stack trace, scan dokumen, proposal PDF.
Skill ini menjembatani: file โ OCR โ teks โ LLM, tanpa perlu model vision yang mahal.
๐ Cara Setup
1. Install dependensi
cd mcp-ocr
# pakai uv (disarankan)
uv sync
# atau pakai pip langsung
pip install -r pyproject.tomlButuh Python 3.10 โ 3.13. Dependensi utama:
mcp, rapidocr-onnxruntime, Pillow, numpy, pypdfium2, python-docx, openpyxl, python-pptx, striprtf.
Model OCR RapidOCR (ONNX) di-download otomatis saat pertama kali dipakai.
2. Daftarkan sebagai MCP server
Tambahkan ke config MCP klien kamu (opencode, Claude Code, dst):
{
"mcpServers": {
"ocr": {
"command": "python",
"args": ["/path/ke/server.py"],
"env": { "PYTHONIOENCODING": "utf-8" }
}
}
}3. Selftest (tanpa MCP)
python server.py --selftest # buat sample gambar lalu OCR
python server.py --selftest "folder/file" # test file atau folder๐ Cara Pakai
Panggil tool dari LLM:
read_document(file_path="C:/Users/.../test-failed-1.png")
read_document(file_path="proposal.pdf")
read_document(file_path="laporan-bug.docx", mode="text", enhance=true)Param | Nilai | Fungsi |
| path lokal / URL http(s) / file:// | wajib |
|
| urutan baris OCR ( |
|
| autocontrast + upscale teks kecil |
Hasilnya teks murni + metadata singkat, contoh:
[OCR] pasted-XXXX.png โ 1658x605px โ 21 baris โ avg confidence 0.98 โ 18.5s
----------------------------------------------------
Models
# Model Provider Source Input Output ...
1 cx/gpt-5.5 9router Codex 16.5M 685K ...
...๐ Bonus: Baca gambar yang DI-PASTE langsung di chat
Ada satu masalah unik di opencode: gambar yang di-paste di kolom chat tidak disimpan sebagai file โ opencode menyimpannya di database SQLite (opencode.db, tabel part) sebagai base64 data-URL. Model teks-only tidak bisa melihat bytes-nya.
Helper extract-pasted-image.py menjembatani ini:
User paste gambar di chat
โ
โผ
[extract-pasted-image.py] โโโบ ambil gambar terbaru dari opencode.db
โ (base64 โ file temp)
โผ
[read_document] โโโบ OCR โโโบ teks โโโบ LLM jawabPakai
python extract-pasted-image.py
# โ {"paths": ["C:/.../pasted-XXXX.png"], "count": 1}Lalu OCR hasilnya:
read_document(file_path="C:/.../pasted-XXXX.png")Opsi:
Flag | Fungsi |
| ekstrak N gambar terakhir (default 1) |
| filter session tertentu |
| folder output (default temp) |
| lokasi |
Butuh Python + stdlib saja (sqlite3, base64, json). Lokasi DB auto-detect dari
~/.local/share/opencode/lalu~/.config/opencode/.
Alur kerja agent (otomatis)
User paste gambar โ model dapat error
Cannot read image.Agent jalankan
extract-pasted-image.pyโ ambil file temp.Agent panggil
read_document(file_path=<hasil>)โ teks.Agent analisa & jawab. Tanpa minta user simpan manual.
๐งฉ Struktur Project
Super-MCP-OCR-Deepseek/
โโโ README.md โ dokumentasi ini
โโโ SKILL.md โ skill instruction (untuk agent)
โโโ server.py โ MCP OCR server (inti + read_colors)
โโโ extract-pasted-image.py โ helper gambar tempelan opencode
โโโ pyproject.toml โ dependensi
โโโ .python-version โ versi Python๐ง Alur Kerja Teknis (server.py)
_resolve_pathโ terima path lokal / URL http(s) / file:// โ file lokal.Routing per ekstensi โ gambar โ OCR; pdf โ ekstrak+OCR; office โ ekstrak; teks โ baca.
_ocr_pil(gambar) โ pre-process (grayscale + autocontrast + upscale teks kecil) โ RapidOCR ONNX โ susun hasil jadi baris visual (urutylalux)._extract_palette/_read_colors(gambar) โ flatten RGBAโRGB โ downscale โ kuantisasi median-cut (PIL) โ cluster warna dominan โ gabung shade dekat โ hitung % area + region.Confidence filter โ buang hasil OCR dengan skor < 0.35.
Output โ header metadata + teks murni, siap dianalisa LLM.
Kenapa preprocessing?
Teks kecil (< 900px) di-upscale 2โ3ร agar OCR akurat.
Gambar raksasa (> 3200px) di-cap agar tidak boros memory.
Autocontrast meningkatkan kontras teks di screenshot gelap/terang.
๐ง Troubleshooting
Masalah | Solusi |
| Masalah kuota gateway model, bukan MCP OCR. Top up saldo, lalu ulangi. |
Tool tidak muncul di klien | Restart sesi / |
OCR hasil jelek | Pakai |
| Simpan ulang sebagai |
๐ Lisensi
MIT โ bebas dipakai, diubah, disebarluaskan.
Dibuat untuk mengaktifkan DeepSeek & LLM teks-only lainnya di ekosistem MCP (opencode, Claude Code, dll).
This server cannot be installed
Maintenance
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
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Document-to-Markdown MCP server โ convert PDF, Office and HTML into LLM-ready Markdown.
Hosted MCP server: convert PDFs to clean, LLM-ready Markdown with tables, formulas and OCR.
MCP server for agentverse documentation, generated by doc2mcp.
Related MCP Servers
- AlicenseBqualityDmaintenanceAn MCP server that lets AI assistants read and visually analyze local documents โ PDFs, Excel spreadsheets, CSV files, Word documents, PowerPoint presentations, and images.466MIT
- AlicenseAqualityCmaintenanceMCP server wrapping Docling to give text-only LLMs document vision via tools for converting PDFs, images, and Office files to Markdown, extracting tables, OCR, and RAG chunking.41MIT
- AlicenseAqualityBmaintenanceMCP server that analyzes images, reads code and ZIP archives, and provides text context for non-vision models.3172MIT
- FlicenseNot gradedqualityBmaintenanceA lightweight MCP server that provides vision capabilities to text-only models like Claude Code and Codex by forwarding images to an OpenAI-compatible multimodal model, offering tools for image analysis and OCR.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/slamsmart/Super-MCP-OCR-Deepseek'
If you have feedback or need assistance with the MCP directory API, please join our Discord server