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., "@renamed-to rename all PDF invoices in ~/Downloads with format: {date} - {vendor}"
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.
Model Context Protocol (MCP) server for renamed.to — bring AI-powered file renaming, organization, and PDF splitting into Claude Code, Claude Desktop, Cursor, Windsurf, and any MCP-compatible client. Tell the AI how you want your files named using plain English — it reads the actual document content (OCR, tables, headers) and follows your instructions.
Natural-language prompts — describe your naming rules in plain English and the AI follows them (per-document-type rules, conditional logic, localization, and more)
AI content analysis — OCR and NLP extract dates, vendors, amounts, document types, and reference numbers from the actual file contents
PDF splitting — split PDFs by content/topic (AI), bookmarks, or page ranges
Organization strategies — auto-sort into folders by year, company, document type, or combinations
Dry-run mode — preview renames before committing changes
Multi-platform — works with Claude Code, Claude Desktop, Cursor, and Windsurf
Related MCP server: File Organizer AI MCP
claude mcp add renamed-to -- npx -y @renamed-to/mcpSet your API key and you're ready to go:
export RENAMED_API_KEY="rt_..."Using Claude Desktop, Cursor, or Windsurf? See Configuration below.
npx -y @renamed-to/mcpnpm install -g @renamed-to/mcp
renamed-mcpgit clone https://github.com/renamed-to/mcp.renamed.to.git
cd mcp.renamed.to
npm install
npm run build
node dist/index.jsclaude mcp add renamed-to -- npx -y @renamed-to/mcpAdd to your claude_desktop_config.json:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"renamed-to": {
"command": "npx",
"args": ["-y", "@renamed-to/mcp"],
"env": {
"RENAMED_API_KEY": "rt_your_key_here"
}
}
}
}Add to your MCP configuration (Settings → MCP Servers):
{
"mcpServers": {
"renamed-to": {
"command": "npx",
"args": ["-y", "@renamed-to/mcp"],
"env": {
"RENAMED_API_KEY": "rt_your_key_here"
}
}
}
}Add to your MCP configuration:
{
"mcpServers": {
"renamed-to": {
"command": "npx",
"args": ["-y", "@renamed-to/mcp"],
"env": {
"RENAMED_API_KEY": "rt_your_key_here"
}
}
}
}Sign up for a renamed.to account
Go to Settings → API Keys and create a key
Set the environment variable:
export RENAMED_API_KEY="rt_..."The server also accepts RENAMED_TOKEN as a fallback. Use the status tool to verify your connection.
renameRename files using AI content analysis. Sends files to the renamed.to API which reads the actual document content — OCR for scans, NLP for text — extracts metadata (dates, vendors, amounts, reference numbers), and generates filenames based on your instructions.
Parameter | Type | Required | Default | Description |
|
| Yes | — | Absolute or relative paths to the files to rename |
|
| No | Source directory | Directory to write renamed files to |
|
| No | AI-chosen | Natural-language prompt describing how filenames should be formatted (see Prompt examples below) |
|
| No |
| Preview the rename without writing any files |
The format parameter accepts plain English instructions. The AI interprets them and applies them to each file based on its content:
Invoices: {date} - {vendor} - Invoice #{number} - ${amount}
Contracts: {vendor} - {type} - {date}
Receipts: {date} - {vendor} - ReceiptYou can specify per-document-type rules, conditional logic, localization, and more:
Department prefixes — "Add HR_ prefix for employment documents, FIN_ for financial records"
Localization — "Use German date format DD.MM.YYYY, translate document types to German"
Conditional logic — "If invoice amount > $1000, add LARGE_ prefix"
Industry formats — "Include matter number for legal documents, client code for accounting"
When no format is provided, the AI automatically selects the best naming pattern for each document.
{
"dryRun": true,
"files": [
{
"original": "scan_001.pdf",
"suggested": "2024-03-15 - Quarterly Report Q1.pdf",
"destination": "/Users/you/Documents/2024-03-15 - Quarterly Report Q1.pdf",
"renamed": false
}
]
}pdf_splitSplit PDFs by content or topic using AI, by bookmarks, or by page ranges. The AI reads the full document, identifies logical sections and topic boundaries, and creates individually named PDFs for each.
Parameter | Type | Required | Default | Description |
|
| Yes | — | Path to the PDF file to split |
|
| No |
| Splitting strategy |
|
| No | Source directory | Directory to write the split PDF files to |
Strategies:
ai — analyzes content and splits by topic or logical sections
bookmarks — splits at PDF bookmark boundaries
pages — splits by page ranges
{
"originalFile": "annual-report.pdf",
"documentsCreated": 3,
"outputDir": "/Users/you/Documents",
"files": [
{
"filename": "annual-report - Financial Summary.pdf",
"pages": "1-12",
"path": "/Users/you/Documents/annual-report - Financial Summary.pdf",
"reason": "Financial data and balance sheets"
},
{
"filename": "annual-report - Operations Review.pdf",
"pages": "13-28",
"path": "/Users/you/Documents/annual-report - Operations Review.pdf",
"reason": "Operational metrics and departmental reviews"
}
]
}watchWatch a directory for new files and auto-process them using rename or pdf-split.
Note: Directory watching requires a long-running process that doesn't fit the MCP request/response model. This tool returns instructions to use the CLI instead:
npx @renamed-to/cli watch <directory> --action rename
npx @renamed-to/cli watch <directory> --action pdf-splitSee the @renamed-to/cli docs for more details.
statusCheck authentication status and API connectivity. Takes no parameters.
{
"status": "authenticated",
"email": "you@example.com",
"name": "Your Name",
"credits": 500
}Tool | Read-Only | Destructive | Idempotent |
| No | Yes (renames files in place) | No |
| No | No (creates new files) | Yes |
| Yes (informational only) | No | Yes |
| Yes | No | Yes |
Rename scanned documents based on their content:
"Rename all the PDFs in my Downloads folder based on their content"
The AI reads each file — even scanned images via OCR — extracts dates, vendors, document types, and generates descriptive names like 2024-03-15 - Quarterly Report Q1.pdf.
Use natural-language rules for different document types:
"Rename these files. For invoices use '{date} - {vendor} - Invoice #{number}', for contracts use '{vendor} - {type} - {date}', and add a LARGE_ prefix if the amount is over $1000"
The AI applies different naming rules per document type, with conditional logic, all from a single plain-English prompt.
Split a long report into separate documents by topic:
"Split this 50-page annual report into separate documents by topic"
The AI analyzes content boundaries and creates individually named PDFs for each logical section — no bookmarks required.
Preview renames with localized formatting:
"Do a dry run rename of these invoices using German date format DD.MM.YYYY and translate document types to German"
Shows what the new filenames would be without moving any files. The AI handles localization and translation in the naming.
The server provides clear error messages for common issues:
Error | Cause | Resolution |
Not configured |
| Add your API key to the environment (get one here) |
Authentication failed | Invalid or expired API key | Generate a new key at Settings → API Keys |
Insufficient credits | Account credits depleted | Top up at Settings → Billing |
Rate limit exceeded | Too many requests | Wait and retry (the error includes a retry-after interval when available) |
Network error | Cannot reach the API | Check your internet connection |
File not found | Invalid file path | Verify the path exists and is accessible |
API key is read from environment variables only — never hardcoded or logged
File contents are sent to the renamed.to API for analysis — be aware of this when processing sensitive documents
Runs locally via stdio transport — no network ports are opened on your machine
No data stored — the server is stateless between requests
@renamed-to/cli — command-line tool for renamed.to (includes watch for directory monitoring)
@renamed-to/sdk — multi-language SDKs for the renamed.to API
Claude Code plugin — Claude Code skills for renamed.to
Contributions are welcome. Please open an issue before submitting significant changes. Run npm run typecheck before opening a PR.
Split PDFs by content or topic using AI, by bookmarks, or by page ranges. Sends the PDF to the renamed.to API for processing.
| Name | Required | Description | Default |
|---|---|---|---|
| filePath | Yes | Path to the PDF file to split | |
| strategy | No | Splitting strategy. "ai" uses content analysis, "bookmarks" uses PDF bookmarks, "pages" uses page ranges | |
| outputDir | No | Directory to write the split PDF files to |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds a key behavioral trait by disclosing that the PDF is sent to the renamed.to API for processing, which is useful context. However, with no annotations, it does not disclose whether the operation is read-only, modifies the original file, is asynchronous, or has any rate limits or side effects. The external API mention is a positive but insufficient disclosure.
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, front-loaded with the core purpose and strategy options. The second sentence adds essential external API context. Every word earns its place; there is no redundancy or filler.
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 tool that sends PDFs to an external API and has no output schema, the description is somewhat incomplete. It does not mention whether the operation returns anything, how to monitor progress (potentially via sibling 'status'), or whether the original file is modified. This would be clearer with a note on asynchronous behavior or output handling.
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%, and all parameters have descriptions (e.g., strategy enum values). The description's mention of 'content or topic using AI, bookmarks, or page ranges' aligns with the enum values but does not add any new semantics beyond what the schema already provides. Baseline of 3 applies.
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 tool's function: 'Split PDFs by content or topic using AI, by bookmarks, or by page ranges.' It uses a specific verb (split), a specific resource (PDFs), and lists the main modes. This clearly distinguishes it from sibling tools like rename, watch, and status.
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 by listing splitting strategies (content/topic, bookmarks, page ranges), but it does not explicitly state when to use this tool versus alternatives or provide any exclusions. It lacks context such as prerequisites, typical use cases, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Rename files using AI content analysis. Sends files to the renamed.to API which analyzes content and returns intelligent filenames.
| Name | Required | Description | Default |
|---|---|---|---|
| dryRun | No | Preview the rename without writing any files | |
| format | No | Format template for the new filename (e.g. "{date} - {title}") | |
| filePaths | Yes | Absolute or relative paths to the files to rename | |
| outputDir | No | Directory to write renamed files to. Defaults to the source directory |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden of behavioral disclosure. It usefully reveals that files are sent to an external API, which is a key behavioral trait. However, it does not mention dry-run behavior, handling of original files, or output directory semantics, leaving some gaps.
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, front-loading the core purpose and adding the API detail. Every word contributes value, with no redundancy or filler.
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 annotations and no output schema, the description provides essential context by naming the external service and explaining the AI analysis. It covers the tool's unique behavior well, though it omits potential side effects like network requirements or preview modes, but these are not strictly necessary given the schema coverage.
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?
The input schema covers all parameters with descriptions (100% coverage), so the description adds little to parameter understanding. It merely reinforces the purpose without providing additional semantic detail beyond the schema's existing 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 the tool's function: renaming files via AI content analysis via the renamed.to API. The verb 'Rename' and the resource 'files' are specific, and the mention of AI analysis distinguishes it from sibling tools like pdf_split, watch, and status.
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 by specifying 'using AI content analysis' but does not explicitly state when to use this tool versus alternatives or when not to use it. No exclusions or alternative tools are mentioned, leaving usage somewhat inferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check authentication status and API connectivity for the renamed.to service.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of disclosing behavioral traits. It states what the tool checks (auth status and API connectivity), but does not describe side effects, return format, or whether it is read-only. This is adequate but lacks depth for a tool with no structured annotations.
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 a single, tightly worded sentence that gets straight to the point. Every word adds meaning, no fluff or redundancy, and it is front-loaded with the verb 'Check'.
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 tool with no parameters and no output schema, the description provides the essential purpose and services checked. It does not detail return values, but for such a simple diagnostic tool, the agent can invoke it without ambiguity. A minor gap is the lack of information about the response structure, but overall it is complete enough for selection and invocation.
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?
The tool has zero parameters, and schema coverage is trivially 100%. With no parameters to explain, the description does not need to add parameter-level semantics. The baseline of 4 applies, and the description correctly focuses on the tool's behavior rather than nonexistent parameters.
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 uses a specific verb ('Check') and clearly identifies the resource: authentication status and API connectivity for the renamed.to service. This unambiguously distinguishes it from sibling tools like pdf_split, rename, and watch, which are action-oriented.
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 when to use the tool—when you need to verify service status or connectivity—but it does not explicitly state when to use it versus alternatives. There are no exclusions or alternative mentions, so usage guidance is only implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Watch a directory for new files and auto-process them using rename or pdf-split.
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | Action to perform on new files | |
| config | No | Action-specific configuration | |
| directory | Yes | Directory to watch for new files |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that the tool 'watch[es]' and 'auto-process[es]', but does not clarify key behavioral traits such as whether it runs indefinitely, how it handles errors, whether existing files are processed, or what the return/exit behavior is. The description is too brief to give a complete behavioral picture.
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 a single, front-loaded sentence that efficiently states the tool's purpose without superfluous details. Every word contributes to understanding the tool's core function.
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?
Despite having a nested config object and no output schema, the description does not explain what happens when the watch runs (e.g., does it block, return a handle, list processed files?). It also doesn't clarify how config is used in practice, such as defaults or required subfields for each action. The tool is more complex than the description conveys, leaving gaps in context.
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 the baseline is 3. The description adds minimal value beyond the schema: it names the actions (rename, pdf-split) but the schema already enumerates them. The config object is not elaborated beyond the schema, so no additional semantic insight is provided.
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 tool's function: 'Watch a directory for new files and auto-process them' with specific verbs and resources. It differentiates from sibling tools by mentioning 'rename or pdf-split', which are separate tools, indicating this is a higher-level watcher that dispatches to them.
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 monitoring a directory and automatically applying actions, but does not explicitly state when to use this instead of directly calling rename or pdf-split, nor does it mention exclusions or prerequisites. It provides context (new files) but lacks clear guidance on alternatives.
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.
v0.1.2pdf_splitrenamestatuswatchEach tool has a clearly distinct purpose: pdf_split splits PDFs, rename renames files, watch automates processing, and status checks connectivity. There is no overlapping functionality or ambiguity in which tool to use for a given task.
The names follow a loose verb-centric pattern, but 'pdf_split' uses noun-verb order while 'rename', 'watch', and 'status' are single verbs/nouns. This creates a minor inconsistency in style that could be improved by renaming to 'split_pdf' or similar.
With only four tools, the server is tightly scoped to its core purpose of AI-powered file renaming and splitting, plus automation and status checking. Each tool is necessary and there are no redundant or superfluous entries.
The set covers the primary workflows: renaming, splitting, automating via watch, and checking authentication. A minor gap might be the absence of a direct upload/download or batch management tool, but the core lifecycle is fully supported.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for generating rough-draft project plans from natural-language prompts.
An MCP server that integrates with Discord to provide AI-powered features.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/renamed-to/mcp.renamed.to'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
