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., "@mega-mcp List top-level files in my MEGA folder."
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.
Browse · Search · Read files & PDFs · Video metadata · Optional transcription — all from a public mega.nz link, no account required.
⭐ If this saves you time, please star the repo — it really helps others find it.
mega-mcp is a Model Context Protocol (MCP) server that exposes a public MEGA folder or file link as a queryable knowledge base. Point it at a share link and your AI assistant — Claude Code, Claude Desktop, or any MCP-compatible client — can browse the tree, search filenames, read text files and extract text from PDFs, inspect video/audio metadata, and optionally transcribe media to text.
No MEGA login. No re-uploading your files somewhere else. Just a link.
Great for course libraries, research archives, documentation dumps, datasets, meeting recordings — any pile of files already living on MEGA that you want an LLM to actually use.
Related MCP server: MCP-RAG
Tool | What it does | |
📁 |
| List a folder link — top level, a subfolder, or the entire tree. |
🔎 |
| Find files/folders by name across the whole share (substring or regex). |
📄 |
| Return a file's text. PDFs are auto-extracted to text. Other binaries are rejected. |
🧠 |
| Full-text search inside text files and PDFs, with line-level snippets. |
🎬 |
| Video/audio metadata (duration, resolution, codecs, fps, bitrate) — streams only the header, no full download. |
🎙️ |
| (opt-in) Transcribe speech to text via a pluggable backend (OpenAI-compatible API or any local CLI like whisper.cpp). |
🔓 Public links only — folder links and single-file links, zero credentials.
📦 Batteries included — ffmpeg/ffprobe ship via npm; PDF extraction uses a bundled pdf.js. No system installs.
🧩 Pluggable transcription — bring OpenAI Whisper, a local model, or any command. Off by default.
⏱️ Long-job friendly — emits MCP progress so big transcriptions don't hit client timeouts.
🛡️ Safe by default — size caps, binary detection, and friendly errors for dead/blocked/expired links.
git clone https://github.com/Anicodeth/mega-mcp.git
cd mega-mcp
npm install
npm run buildThat's it — dist/index.js is your MCP server. Wire it into a client below.
claude mcp add mega \
-e MEGA_LINK="https://mega.nz/folder/XXXX#YYYY" \
-- node "/absolute/path/to/mega-mcp/dist/index.js"Then just ask: "Browse my MEGA folder and summarize what's in the Strategy section."
On Windows, use the full path, e.g.
node "C:\\path\\to\\mega-mcp\\dist\\index.js".
Add to claude_desktop_config.json:
{
"mcpServers": {
"mega": {
"command": "node",
"args": ["/absolute/path/to/mega-mcp/dist/index.js"],
"env": {
"MEGA_LINK": "https://mega.nz/folder/XXXX#YYYY"
}
}
}
}Without MEGA_LINK, pass a link argument to each tool call instead — handy for working with many links.
All environment variables are optional.
Var | Purpose | Default |
| Default public link so tools work without repeating it. Per-call | — |
| Max bytes to download for a text-file read / content search. |
|
| Max bytes to download for a PDF before extracting text. |
|
mega_transcribe is off by default. Turn it on by choosing a backend.
Var | Value |
|
|
| your key (required) |
| optional, default |
| optional, default |
Works with any OpenAI-compatible endpoint (Groq, local servers, etc.) via OPENAI_BASE_URL.
Var | Value |
|
|
| a shell command where |
A ready-to-use faster-whisper wrapper is included at scripts/whisper_cli.py:
pip install faster-whisper# macOS/Linux
export MEGA_TRANSCRIBE=command
export MEGA_TRANSCRIBE_CMD='python /path/to/mega-mcp/scripts/whisper_cli.py {input}'
export WHISPER_MODEL=base # tiny | base | small | medium | large-v3The wrapper runs fully locally on CPU — no API key, no data leaving your machine.
How it works: the media file is downloaded to a temp dir, ffmpeg (bundled) extracts mono 16 kHz audio and splits it into ~10-minute segments, each segment goes to your backend, and results are concatenated. Use the maxMinutes argument to transcribe just the start of a long file.
Once connected, you can drive everything in natural language:
You say… | Tool used |
"What folders are in my MEGA share?" |
|
"Find every file with 'invoice' in the name." |
|
"Read |
|
"Open the Patreon case study PDF and pull the key takeaways." |
|
"Search all the PDFs for 'activation metric' and show me where." |
|
"How long is |
|
"Transcribe the first 10 minutes of |
|
mega_browse — link?, path? (subfolder), recursive? (default false)
mega_search — query, link?, regex?, filesOnly?
mega_read_file — path? or file link, maxBytes?
mega_search_content — query, link?, regex?, includePdf? (default true), maxFiles?, maxMatchesPerFile?
mega_video_info — path? or file link, raw?
mega_transcribe — path? or file link, maxMinutes?, language?, segmentMinutes?
Every tool falls back to MEGA_LINK when link is omitted.
public MEGA link
│
┌──────────▼───────────┐
│ megajs (no login) │ load link → walk tree → resolve path → download
└──────────┬───────────┘
│
┌───────────────┼───────────────────────────┐
▼ ▼ ▼ ▼
browse / read_file / video_info transcribe (opt-in)
search search_content (ffprobe, (download → ffmpeg
(metadata) (text + PDF via header-only) audio segments →
unpdf/pdf.js) backend → text)Public links are resolved with megajs — both /folder/…#key and /file/…#key forms.
PDFs are extracted with unpdf (a serverless-friendly pdf.js build). Scanned/image-only PDFs yield no text (OCR not included).
Video metadata is read by streaming only the header into ffprobe — a 1 GB file is probed in seconds without downloading it.
Transcription downloads the file (needed because many mp4s store their index at the end and pipes aren't seekable), then segments audio so even hour-long lectures stay within backend size limits.
Do I need a MEGA account? No. mega-mcp only uses public share links.
Does it support private/account files? Not currently — public links only, by design. See the roadmap.
Are my files re-uploaded anywhere? No. Files are fetched directly from MEGA on demand. With the local transcription backend, nothing leaves your machine.
Can it read Word/Excel/PowerPoint? Not yet — text files and PDFs today. Office formats are on the roadmap.
Will big transcriptions time out in my client? The server emits MCP progress notifications, which keeps compatible clients alive. Use maxMinutes to cap long files.
Does ffmpeg need to be installed? No — ffmpeg-static and ffprobe-static bundle the binaries.
Optional account login for private files
Office document extraction (docx, xlsx, pptx)
OCR for scanned PDFs / images
Cached content index for faster repeated searches
Resource endpoints (expose files as MCP resources)
Have an idea? Open an issue 🙌
Contributions are very welcome!
npm install
npm run build # compile
npm run typecheck # strict type check
npm run dev # watch modeFork the repo and create a feature branch.
Keep the code style consistent and types strict.
Open a PR describing the change. Small, focused PRs are easiest to merge.
If you find a bug or want a feature, issues and ⭐ stars are both hugely appreciated.
src/
index.ts MCP server + tool definitions
mega.ts megajs wrapper (load link, walk tree, resolve path, download)
pdf.ts PDF text extraction (unpdf)
video.ts ffprobe streaming + metadata distillation
transcribe.ts optional, pluggable audio/video transcription
types.d.ts ambient module declaration for ffprobe-static
scripts/
whisper_cli.py local faster-whisper transcription backendMIT © Ananya Fekeremariam (Anicodeth)
Built with the Model Context Protocol. If it helped, drop a ⭐ — thank you!
List files and folders in a public MEGA folder link. Use recursive to walk the entire tree, or path to scope into a subfolder. Returns name, path, type, and size for each entry.
| Name | Required | Description | Default |
|---|---|---|---|
| link | No | Public MEGA folder/file link. Defaults to MEGA_LINK env. | |
| path | No | Subfolder path within the link to list, e.g. 'docs/2024'. | |
| recursive | No | List the full tree under the path (default false). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but description discloses read-only behavior (list), output fields, and parameter effects. Adequate transparency for a listing tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences: purpose, parameter usage, and output. Front-loaded with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers essential output fields. Lacks mention of error handling or pagination, but sufficient for a folder listing tool with sibling differentiation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers all parameters with descriptions; description adds context on usage (recursive for tree, path for subfolder). Adds value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb 'List' and resource 'files and folders in a public MEGA folder link'. Distinguishes from siblings like mega_read_file and mega_search by specifying listing a folder's contents.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides guidance on parameters: 'Use recursive to walk the entire tree, or path to scope into a subfolder.' Does not explicitly exclude alternatives but implies usage scope.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Download and return the text contents of a file. PDFs are extracted to text automatically. Provide either a path within a folder link, or a direct file link. Other binary files are rejected. Text reads are capped at MEGA_MAX_READ_BYTES; PDFs at MEGA_MAX_PDF_BYTES.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | File path within the folder link, e.g. 'notes/todo.md'. | |
| link | No | MEGA link: a folder link (with `path`) or a direct file link. | |
| maxBytes | No | Override max bytes to read (default 2000000). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses caps (MEGA_MAX_READ_BYTES, MEGA_MAX_PDF_BYTES), PDF extraction, and binary rejection. Additional transparency on error handling or permissions would improve.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no wasted words. Front-loaded with action and resource. Efficiently covers purpose, constraints, and parameter usage.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, description mentions return of text contents. Covers caps and rejections. Missing details on error responses, but overall adequate for a read tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema describes all 3 parameters (100% coverage). Description adds meaning by explaining how path and link relate, and notes maxBytes as an override. Adds value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it downloads and returns text contents, extracts PDFs, and requires a path or link. It distinguishes from sibling tools like mega_browse and mega_search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description specifies when to use (for text/PDF files) and what is rejected (binary files). It does not explicitly name alternatives but implies context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search a public MEGA link's entire tree for files/folders whose name matches a query (case-insensitive substring, or regex with regex).
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Substring or regex to match against names. | |
| link | No | Public MEGA link. Defaults to MEGA_LINK. | |
| regex | No | Treat query as a regex. | |
| filesOnly | No | Exclude folders from results. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description must disclose behavioral traits. It does: it searches the entire tree, supports regex with the `regex` flag, and is case-insensitive. It omits details like output format, pagination, or authentication, but for a read-oriented search tool, it is fairly transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence (22 words) that is front-loaded and contains no filler. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is adequate for a search tool but lacks details about the return format (list of files/folders? paths? names?). With no output schema, these details would be helpful. It covers parameter semantics well but misses output behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (all parameters have descriptions). The description adds value by clarifying the default link value and explaining the regex flag, but repeats schema info. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it searches a public MEGA link's entire tree for files/folders by name, using case-insensitive substring or regex. This distinguishes it from siblings like mega_search_content (content search) and mega_browse (browsing structure).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for filename-based searches but does not explicitly state when to use this tool over alternatives (e.g., mega_search_content for content search) or when not to use it. No exclusions or context are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search inside text files and PDFs under a MEGA folder link for a query string (or regex). Returns matching files with line snippets. By default PDFs are included; set includePdf:false to skip them (faster).
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Text or regex to find inside files. | |
| link | No | Public MEGA link. Defaults to MEGA_LINK. | |
| regex | No | Treat query as a regex. | |
| includePdf | No | Include PDFs in the scan (default true). | |
| maxFiles | No | Max files to scan (default 50). | |
| maxMatchesPerFile | No | Max snippet lines per file (default 5). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description carries full burden. It discloses that search uses regex capability and includes PDF handling, but does not mention auth requirements, rate limits, or whether the tool is destructive (not needed). Returns are described as 'line snippets', which is helpful. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: first defines core purpose, second adds optimization detail. Every word is useful. No fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a search tool with 6 params and no output schema, the description covers main behavior, regex, PDF handling, and performance. Could mention maxFiles and maxMatchesPerFile bounds or result format, but overall adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. Description adds value by explaining 'line snippets' (not in schema), noting default includePdf=true, and the performance implication of including PDFs. This goes beyond the schema's bare descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb ('Search'), resource ('text files and PDFs under a MEGA folder link'), action ('for a query string or regex'), and output ('Returns matching files with line snippets'). Distinguishes from siblings like mega_search (likely broader) and mega_read_file (reads a file, does not search).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description implies use when full-text search inside files is needed, and notes performance tip ('set includePdf:false to skip them (faster)'). However, it does not explicitly state when not to use this tool versus siblings like mega_search (which may search by filename) or mega_browse (directory listing). No alternatives mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Transcribe spoken audio from a video/audio file to text, so it can be used as knowledge. OPT-IN: disabled unless a backend is configured via MEGA_TRANSCRIBE (openai or command) — see README. Audio is extracted and segmented with ffmpeg, then sent to the backend. The file is downloaded first; use maxMinutes to transcribe only the start of a long file.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | Media file path within the folder link. | |
| link | No | MEGA link: folder link (with `path`) or direct file link. | |
| maxMinutes | No | Only transcribe the first N minutes of the file. | |
| language | No | Optional ISO language hint, e.g. 'en'. | |
| segmentMinutes | No | Audio segment length sent per request (default 10). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses that the tool is disabled by default, requires backend configuration, downloads the file, extracts/segments audio with ffmpeg, and sends to backend. This is good transparency, though it omits rate limits or response format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (4 sentences) and front-loaded with purpose. Each sentence adds information without fluff, though it could be slightly more structured (e.g., grouping prerequisites).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 5 parameters and no output schema, the description explains the process and prerequisites but does not specify the output format (beyond 'to text') or whether results are returned directly. Somewhat incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds specific context for maxMinutes ('transcribe only the start of a long file'), but other parameters are already well-described in the schema. The added value is minimal.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Transcribe') and resource ('spoken audio from a video/audio file'), and this purpose is distinct from sibling tools (e.g., mega_browse, mega_read_file) which are not transcription-related.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions the OPT-IN requirement and provides a usage hint for maxMinutes, but it does not explicitly compare to alternatives or state when to use this tool vs. others. The sibling tools are unrelated, so context is implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Probe a video or audio file's technical metadata (duration, resolution, codecs, bitrate, fps) using ffprobe. Streams only the header, not the whole file. Provide path within a folder link or a direct file link.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | Media file path within the folder link. | |
| link | No | MEGA link: folder link (with `path`) or direct file link. | |
| raw | No | Include full raw ffprobe JSON in the response. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It explicitly states 'Streams only the header, not the whole file,' which is a key efficiency trait. It also mentions using ffprobe. Additional behavioral details (e.g., error handling, size limits) are absent, but the core safety and performance implication is conveyed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences: the first states the purpose and typical metadata fields, the second gives input conventions. Every word earns its place; there is no redundancy or fluff. It is front-loaded with the most critical information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (3 parameters, no output schema), the description covers the purpose, method, behavioral trait, and input conventions. It also lists typical output fields, which compensates for the lack of an output schema. Minor gaps: no explicit mention of return format structure or error conditions, but overall it is sufficient for an agent to understand and invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds value by clarifying the relationship between path and link ('Provide path within a folder link or a direct file link'), and implies that raw includes full ffprobe JSON. This goes beyond the schema's basic descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool probes technical metadata using ffprobe, and enumerates typical fields (duration, resolution, codecs, bitrate, fps). It distinguishes itself from siblings like mega_read_file and mega_transcribe by focusing on metadata extraction, though it does not explicitly contrast with alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides input usage instructions (path within folder link or direct link) but offers no guidance on when to use this tool versus siblings such as mega_transcribe for audio transcription or mega_read_file for content reading. The agent receives no decision support for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0mega_browsemega_read_filemega_searchmega_search_contentmega_transcribemega_video_infoEach tool targets a distinct operation: browsing folders, reading file contents, searching file names, searching file contents, transcribing audio, and extracting video metadata. There is no overlap, as even the two search tools are clearly separated by scope (names vs. content).
All tools share the 'mega_' prefix and use snake_case, but the pattern is slightly inconsistent: most are verb or verb_noun (browse, read_file, search, search_content, transcribe), while 'video_info' is a noun phrase. Otherwise predictable.
With 6 tools, the server is well-scoped for accessing public MEGA folders. Each tool serves a clear purpose, and the count is neither too sparse nor too heavy for the domain.
The tool set covers the core workflows for a read-only MEGA access server: browsing, reading text/PDF files, searching by name and content, transcribing audio, and probing video metadata. No obvious gaps exist for the intended use case.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Give Claude only the Google Drive files you choose. Every action logged.
Private persistent memory for Claude, ChatGPT & Gemini via MCP - semantic search, zero-code setup.
Connect AI assistants to your GitHub-hosted Obsidian vault to seamlessly access, search, and analy…
Parse, extract, split, and ask over digital PDFs (text layer, no OCR) from Cursor and Claude.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Anicodeth/mega-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
