The @bitatlas/mcp-server allows AI agents to securely manage a zero-knowledge, end-to-end encrypted cloud vault using client-side AES-256-GCM encryption. Available capabilities:
Vault Status: Check vault health, total file count, and storage usage.
List Files: Browse files with optional filters by folder, category (identity, financial, legal, medical, digital), or search term.
Search Files: Search vault files by query string, optionally narrowed to a specific category.
Get/Download a File: Retrieve file metadata and decrypt file content — returned as UTF-8 text for text files or base64 for binary files (requires BITATLAS_MASTER_KEY).
Upload a File: Read a local file, encrypt it client-side, and upload it to the vault with an optional display name, category, and destination folder (requires BITATLAS_MASTER_KEY; max 100 MB).
Delete a File: Permanently remove a file from the vault by its UUID.
Create a Folder: Organize the vault by creating new folders at the root or nested under a parent folder.
Zero Knowledge Cloud Drive for Humans and Agents
BitAtlas is a next-generation cloud storage platform designed with privacy and AI agents in mind. It provides a secure, zero-knowledge environment where your most sensitive documents are encrypted client-side and accessible only to you and the agents you authorize.
BitAtlas aims to be the secure "atlas" for your digital life, providing a foundation for both human productivity and AI agent assistance without compromising on privacy.
Related MCP server: Sylex Memory
🛡️ E2E Encryption (AES-256-GCM): All files are encrypted in the browser (or at the SDK level) before being uploaded. The server never sees your plaintext data or your encryption keys.
🤖 Agent-Native (MCP Server): Built from the ground up to support AI agents via the Model Context Protocol (MCP). Let your agents safely search, read, and manage your vault.
🔐 Personal Vault: A dedicated space for your most critical documents—identity papers, property deeds, medical records, and digital assets.
🇪🇺 European Data Sovereignty: All infrastructure is hosted on European soil, subject to the world's strongest privacy regulations (GDPR).
💸 Pay-per-Request (x402): Anonymous access via the x402 payment standard. Agents pay with USDC stablecoins on Base — no account, no API key, no KYC. Files include 30 days of storage with pay-to-renew. Learn more →
mcp-server/: The Model Context Protocol server for integrating with AI agents like Claude Desktop, OpenClaw, and more.
sdk/encryption/: The core encryption logic used for client-side security.
LegacyShield (legacyshield.eu): The first production application built on BitAtlas. A digital legacy platform and encrypted document vault for humans and their descendants.
To use BitAtlas with your AI agent, configure the MCP server:
{
"mcpServers": {
"bitatlas": {
"command": "npx",
"args": ["-y", "@bitatlas/mcp-server"],
"env": {
"BITATLAS_API_KEY": "your-api-key",
"BITATLAS_MASTER_KEY": "your-derived-master-key"
}
}
}
}MIT License. See LICENSE for details.
Built with ❤️ by BitAtlas Group
Create a new folder in the vault.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Folder name | |
| parent_id | No | Parent folder ID (omit to create at root) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. While 'Create' implies a write/mutation operation, it doesn't specify permissions needed, whether the operation is idempotent, what happens on duplicate names, or error conditions. This leaves significant behavioral gaps for a creation 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?
The description is a single, clear sentence with zero wasted words. It's front-loaded with the core purpose and efficiently communicates the essential action without unnecessary elaboration.
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 creation tool with no annotations and no output schema, the description is insufficient. It doesn't address what happens on success (e.g., returns folder ID), error conditions, permissions required, or how it fits within the broader file/folder management context with sibling tools.
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 description adds no parameter information beyond what's already in the schema (which has 100% coverage). It doesn't explain naming constraints, what constitutes a valid parent_id, or provide examples. The baseline of 3 is appropriate since the schema already documents both parameters adequately.
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 action ('Create') and resource ('new folder in the vault'), making the tool's purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'bitatlas_upload_file' or specify what distinguishes a folder from other file types in this system.
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?
No guidance is provided about when to use this tool versus alternatives. The description doesn't mention prerequisites (like needing write permissions), when not to use it, or how it relates to sibling tools like 'bitatlas_upload_file' for files versus folders.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Permanently delete a file from the vault.
| Name | Required | Description | Default |
|---|---|---|---|
| file_id | Yes | File UUID to delete |
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 mentions 'permanently delete,' which implies destructive action, but doesn't cover critical aspects like permissions required, error handling, or confirmation steps. This leaves significant gaps in understanding the tool's behavior.
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, efficient sentence that directly states the tool's action without unnecessary words. It is front-loaded and wastes no space, making it highly concise and well-structured for quick comprehension.
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 destructive nature, lack of annotations, and no output schema, the description is incomplete. It doesn't address what happens post-deletion, potential side effects, or return values, leaving the agent with insufficient context for safe and effective use.
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 has 100% description coverage, with the parameter 'file_id' documented as 'File UUID to delete.' The description doesn't add any extra meaning beyond this, such as format examples or validation rules, so it meets the baseline for high schema coverage without enhancing parameter understanding.
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 action ('permanently delete') and the resource ('a file from the vault'), making the purpose unambiguous. However, it doesn't explicitly differentiate from sibling tools like bitatlas_get_file or bitatlas_list_files, which prevents a perfect score.
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 no guidance on when to use this tool versus alternatives, such as whether deletion is irreversible or if there are prerequisites like checking file existence first. It lacks context about when-not-to-use or comparisons to siblings, offering minimal usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get file metadata and download + decrypt the file content. Returns decrypted content as UTF-8 text for text files, or base64 for binary files. Requires BITATLAS_MASTER_KEY.
| Name | Required | Description | Default |
|---|---|---|---|
| file_id | Yes | File UUID |
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 traits: it performs read operations (get metadata and download), decrypts content, handles different file types (UTF-8 for text, base64 for binary), and specifies an authentication requirement (BITATLAS_MASTER_KEY). However, it lacks details on rate limits, error handling, or whether metadata includes specific fields like size or timestamps.
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 appropriately sized and front-loaded, with two sentences that efficiently convey the tool's purpose, behavior, and requirements without unnecessary details. Every sentence adds value: the first explains the core functionality and output formats, and the second states the authentication prerequisite.
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 complexity of a tool that retrieves metadata, downloads, and decrypts files, with no annotations and no output schema, the description does a good job covering essential aspects: it explains the dual functionality, output formats, and authentication need. However, it could be more complete by detailing the metadata structure or potential errors, which would help an agent understand the full context better.
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 has 100% description coverage, with 'file_id' documented as 'File UUID.' The description does not add any additional meaning or context about this parameter beyond what the schema provides. According to the rules, when schema coverage is high (>80%), the baseline score is 3, as the schema already handles the parameter documentation adequately.
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 specific action ('Get file metadata and download + decrypt the file content'), identifies the resource ('file'), and distinguishes from siblings like 'bitatlas_list_files' (which lists files) and 'bitatlas_upload_file' (which uploads files). It goes beyond just restating the name by detailing the dual functionality of metadata retrieval and content decryption.
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 'Requires BITATLAS_MASTER_KEY,' which suggests a prerequisite for authentication. However, it does not explicitly state when to use this tool versus alternatives like 'bitatlas_list_files' for browsing or 'bitatlas_search' for finding files, nor does it provide exclusions or clear contextual boundaries beyond the key requirement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List files in the vault. Optionally filter by folder, category, or search term.
| Name | Required | Description | Default |
|---|---|---|---|
| folderId | No | Filter by folder ID | |
| category | No | Filter by category | |
| search | No | Search by file name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions optional filtering but doesn't describe key behaviors such as pagination, sorting, default listing behavior (e.g., all files if no filters), error handling, or authentication requirements. For a list operation without annotations, this leaves significant gaps in understanding how the tool behaves beyond basic functionality.
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, efficient sentence that front-loads the core purpose ('List files in the vault') and follows with optional features. There is no wasted language, making it easy to parse quickly. It appropriately balances brevity with essential 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 lack of annotations and output schema, the description is incomplete for effective tool use. It doesn't explain what the output looks like (e.g., list structure, file details), behavioral aspects like pagination or rate limits, or how it differs from sibling tools. For a list operation with three parameters and no structured output guidance, more context is needed to ensure reliable agent 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?
Schema description coverage is 100%, with clear descriptions for each parameter (folderId, category, search). The description adds minimal value by listing the filter types ('folder, category, or search term'), which aligns with but doesn't significantly expand upon the schema. Since the schema already documents parameters well, the baseline score of 3 is appropriate, as the description doesn't provide additional syntax or format details.
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 ('List') and resource ('files in the vault'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'bitatlas_search' or 'bitatlas_get_file', which likely have overlapping functionality for retrieving files. A 5 would require specific distinction from these 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 implies usage through the phrase 'Optionally filter by folder, category, or search term,' suggesting this tool is for listing with optional filtering. However, it doesn't provide explicit guidance on when to use this versus siblings like 'bitatlas_search' (which might offer more advanced search capabilities) or 'bitatlas_get_file' (for retrieving a single file). No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search vault files by a query string, optionally narrowed to a category.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query (file name) | |
| category | No | Narrow results to this category |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool is for searching files, implying a read-only operation, but it doesn't disclose any behavioral traits such as whether it requires authentication, how results are returned (e.g., pagination, sorting), rate limits, or error conditions. This leaves significant gaps for an AI agent to understand how to use it effectively.
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, efficient sentence that directly states the tool's purpose and key optional feature. It is front-loaded with the main action ('Search vault files') and wastes no words, making it easy for an AI agent to parse quickly.
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 moderate complexity (search with optional filtering), lack of annotations, and no output schema, the description is minimally adequate. It covers the basic purpose and parameters but lacks details on behavior, output format, or integration with sibling tools. This leaves the agent with incomplete context for reliable use, though it meets the minimum viable threshold.
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%, meaning the input schema already fully documents the parameters ('query' and 'category'). The description adds marginal value by mentioning 'optionally narrowed to a category,' which aligns with the schema but doesn't provide additional semantic context beyond what's in the schema descriptions. With high schema coverage, the baseline score of 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 the tool's purpose: 'Search vault files by a query string, optionally narrowed to a category.' It specifies the verb ('Search'), resource ('vault files'), and scope ('by a query string, optionally narrowed to a category'). However, it doesn't explicitly differentiate from sibling tools like 'bitatlas_list_files' or 'bitatlas_get_file', which is why it doesn't achieve a perfect score.
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 minimal usage guidance. It mentions that results can be 'optionally narrowed to a category,' but it doesn't specify when to use this tool versus alternatives like 'bitatlas_list_files' (which might list all files without a query) or 'bitatlas_get_file' (which might retrieve a specific file by ID). No exclusions, prerequisites, or explicit alternatives are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read a local file, encrypt it client-side with AES-256-GCM, and upload it to the vault. Requires BITATLAS_MASTER_KEY. Files over 100 MB are not supported via MCP.
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Absolute or relative path to the local file | |
| name | No | Override display name (defaults to the filename) | |
| category | No | File category | |
| folder_id | No | Destination folder ID (omit for root) |
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 critical traits: the encryption method (AES-256-GCM), client-side processing, a prerequisite ('Requires BITATLAS_MASTER_KEY'), and a size limitation ('Files over 100 MB are not supported'). However, it lacks details on error handling, rate limits, or response format, leaving some gaps in transparency.
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 front-loaded with the core purpose in the first sentence and efficiently adds constraints in the second. Every sentence earns its place by providing essential information without redundancy, making it appropriately sized and well-structured for quick understanding.
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 complexity (file upload with encryption), no annotations, and no output schema, the description is mostly complete. It covers the main action, encryption details, prerequisites, and size limits, but it lacks information on return values (e.g., success confirmation or file ID) and potential errors, which would enhance completeness for a mutation 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?
The schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description does not add any specific meaning or usage details beyond what the schema provides (e.g., it doesn't explain how 'category' affects the upload or what 'folder_id' entails). Baseline 3 is appropriate as the schema handles parameter documentation adequately.
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 specific action ('Read a local file, encrypt it client-side with AES-256-GCM, and upload it to the vault') and distinguishes it from siblings like bitatlas_get_file (retrieval), bitatlas_delete_file (deletion), and bitatlas_list_files (listing). It goes beyond just restating the name/title by detailing the encryption and upload process.
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 clear context for when to use this tool (uploading files to the vault with encryption) and mentions a key constraint ('Files over 100 MB are not supported via MCP'), but it does not explicitly state when not to use it or name alternatives like bitatlas_create_folder for organizing content. It implies usage for file uploads without direct comparison to siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get vault health status, file count, and storage usage.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
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 implies a read-only operation ('Get'), but doesn't specify if it requires authentication, has rate limits, returns real-time or cached data, or details the response format. This is a significant gap for a tool with zero annotation coverage.
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, efficient sentence that front-loads the core purpose without any wasted words. It directly states what the tool does ('Get vault health status, file count, and storage usage'), making it highly concise and well-structured.
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 complexity of retrieving system status (which could involve permissions, data freshness, or error handling), no annotations, and no output schema, the description is incomplete. It lacks details on behavioral traits, response format, or error conditions, leaving gaps for the agent to infer how to use the tool effectively.
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 0 parameters, and the schema description coverage is 100%, so there are no parameters to document. The description appropriately doesn't add parameter details, earning a high score as it avoids redundancy. A perfect 5 is reserved for cases where the description adds value beyond the schema, which isn't applicable here.
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 purpose with specific verbs ('Get') and resources ('vault health status, file count, and storage usage'), making it easy to understand what information it retrieves. However, it doesn't explicitly differentiate this read-only status tool from its sibling tools like bitatlas_list_files or bitatlas_search, which prevents a perfect score.
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 no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, context for usage, or compare it to sibling tools like bitatlas_list_files (which might list files) or bitatlas_search (which might search content), leaving the agent without usage direction.
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.
v0.1.0bitatlas_create_folderbitatlas_delete_filebitatlas_get_filebitatlas_list_filesbitatlas_searchbitatlas_upload_filebitatlas_vault_statusEach tool has a clearly distinct purpose with no ambiguity: create_folder, delete_file, get_file, list_files, search, upload_file, and vault_status all target specific, non-overlapping operations in the file vault domain. The descriptions reinforce these distinctions, making misselection unlikely.
All tools follow a consistent 'bitatlas_verb_noun' pattern with snake_case throughout (e.g., bitatlas_create_folder, bitatlas_delete_file). This predictability makes the tool set easy to navigate and understand at a glance.
With 7 tools, the count is well-scoped for a file vault management server. Each tool earns its place by covering essential operations like CRUD for files/folders, listing, searching, and status checks, without being overly sparse or bloated.
The tool set provides complete CRUD/lifecycle coverage for the vault domain: create (upload_file, create_folder), read (get_file, list_files, search), update (implied via re-upload), delete (delete_file), and administrative status (vault_status). There are no obvious gaps that would hinder agent workflows.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Sovereign E2E cloud storage for AI agents. Zero-knowledge, RGPD-compliant.
Persistent memory for AI assistants — one shared, OAuth-secured vault for every MCP client.
MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.
Encrypted A2A object storage for autonomous agent state and artifacts
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/bitatlas-group/bitatlas'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
