How do I use couchdrop-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@couchdrop-mcp list files in the root directory" 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.

couchdrop-mcp

by OraDavis

Overview Schema Related Servers Score Discussions

TypeScript

Remote

couchdrop-mcp

Local stdio MCP server for Couchdrop. It lets MCP clients list Couchdrop files, inspect file metadata, download and upload files, list users and groups, and read folder permissions.

Requirements

Node.js 22 or newer
A Couchdrop API token

Related MCP server: MCP Local Filesystem Server

Couchdrop Token

Create or retrieve an API token from your Couchdrop account, then provide it to the server as COUCHDROP_API_TOKEN. Keep the token in your local MCP client configuration or shell environment. Do not commit it to source control.

Use a token with the narrowest access that fits your workflow.

Install And Configure

You can run the package with npx; no global install is required.

Claude Desktop

Add the server to your Claude Desktop MCP configuration, then restart Claude Desktop.

{
  "mcpServers": {
    "couchdrop": {
      "command": "npx",
      "args": ["-y", "couchdrop-mcp"],
      "env": {
        "COUCHDROP_API_TOKEN": "your-couchdrop-api-token"
      }
    }
  }
}

Codex

Codex reads MCP servers from ~/.codex/config.toml or a trusted project .codex/config.toml.

[mcp_servers.couchdrop]
command = "npx"
args = ["-y", "couchdrop-mcp"]

[mcp_servers.couchdrop.env]
COUCHDROP_API_TOKEN = "your-couchdrop-api-token"

Generic MCP Client

Configure the client to start a stdio server with this command:

{
  "command": "npx",
  "args": ["-y", "couchdrop-mcp"],
  "env": {
    "COUCHDROP_API_TOKEN": "your-couchdrop-api-token"
  }
}

If your client prefers an installed binary, install the package and run couchdrop-mcp as the stdio command.

Environment Variables

Variable	Required	Default	Description
`COUCHDROP_API_TOKEN`	Yes	None	Couchdrop API token sent to Couchdrop API and FileIO requests.
`COUCHDROP_API_BASE`	No	`https://api.couchdrop.io`	Base URL for Couchdrop management API requests.
`COUCHDROP_FILEIO_BASE`	No	`https://fileio.couchdrop.io`	Base URL for Couchdrop FileIO requests.
`COUCHDROP_MAX_INLINE_BYTES`	No	`65536`	Maximum bytes returned inline for downloads without `outputPath`.

Tools

All Couchdrop paths must start with /. Path segments must not contain ...

Tool	Arguments	Description
`couchdrop_list_files`	`path` optional, default `/`	Lists files and folders at a Couchdrop path.
`couchdrop_get_file_info`	`path` required	Gets metadata for a Couchdrop file or folder.
`couchdrop_download_file`	`path` required, `outputPath` optional	Downloads a file. Without `outputPath`, returns small UTF-8 text inline. With `outputPath`, saves the file locally.
`couchdrop_upload_file`	`localPath` required, `destinationPath` required	Uploads a local file to a Couchdrop path.
`couchdrop_list_users`	None	Lists Couchdrop users visible to the token.
`couchdrop_list_groups`	None	Lists Couchdrop groups visible to the token.
`couchdrop_get_folder_permissions`	`path` required	Gets permissions for a Couchdrop folder path.

Safety Notes

Tokens stay local to your MCP client configuration or environment. This server does not persist tokens.
v0.1 exposes no delete, move, chmod, user mutation, or group mutation tools.
couchdrop_upload_file writes to the requested destinationPath; check the path before calling it.
Use outputPath for large or binary downloads. Inline downloads are intended for small UTF-8 text files.
In v0.1, uploads and downloads saved with outputPath are buffered in memory before being sent or written.

Local Development

npm install
npm run typecheck
npm test
npm run build
npm run dev

To inspect the package contents before publishing:

npm run build
npm pack --dry-run

Contributing

Contributions are welcome. Keep changes small, add or update tests for behavior changes, and run the local verification commands before opening a pull request.

Do not commit real Couchdrop tokens, generated secrets, or private customer paths in tests or documentation.

License

MIT

Available Tools

7 tools

couchdrop_download_fileD

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes
`outputPath`	No

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

couchdrop_get_file_infoD

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

couchdrop_get_folder_permissionsD

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

couchdrop_list_filesD

ParametersJSON Schema

Name	Required	Description	Default
`path`	No		/

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

couchdrop_list_groupsD

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

couchdrop_list_usersD

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

couchdrop_upload_fileD

ParametersJSON Schema

Name	Required	Description	Default
`localPath`	Yes
`destinationPath`	Yes

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

7 tool updatesv0.1.0Jun 30, 2026
- First observedcouchdrop_download_file
- First observedcouchdrop_get_file_info
- First observedcouchdrop_get_folder_permissions
- First observedcouchdrop_list_files
- First observedcouchdrop_list_groups
- First observedcouchdrop_list_users
- First observedcouchdrop_upload_file

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

C2.1/5.0

Disambiguation5/5

Each tool targets a distinct file or administrative operation (download, get info, list, upload, permissions, groups, users) with no overlap in purpose, making them easily distinguishable even without descriptions.

Naming Consistency5/5

All tools follow the consistent 'couchdrop_verb_noun' pattern (e.g., couchdrop_download_file, couchdrop_list_users), with no mixing of conventions or ambiguous verbs.

Tool Count5/5

Seven tools is well-scoped for a file management and permissions service; not too few to feel thin nor too many to overwhelm, covering core operations without redundancy.

Completeness3/5

Covers key file operations (upload, download, list, info) and some admin actions (list users/groups, get permissions), but notably lacks file deletion, file update, and any user/group creation or modification, creating significant gaps for full lifecycle management.

Maintenance

ActivityStale

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

thoughtsOAuth
ai.thoughtbox.api
An MCP server that provides read access to your cloud storage providers, bank accounts and more.
Cloud Storage Finance
2
SupabaseOAuth
com.supabase
MCP server for interacting with the Supabase platform
Cloud Platforms Databases Developer Tools
32,890
mcp AOAuth
com.mux
The official MCP Server for the Mux API
Multimedia Processing Entertainment & Media API Testing
22168
Appcircle MCP
io.appcircle
MCP server for Appcircle mobile CI/CD platform.
CI/CD & DevOps Developer Tools
2

Related MCP Servers

drive-mcp
Cloud Storage Workplace & Productivity
henrysouchien
A
license
Not graded
quality
C
maintenance
MCP server enabling file operations (list, search, read, rename, move) on Google Drive and OneDrive.
Updated 11 days ago (2026-08-26 20:50 UTC)
MIT
MCP Local Filesystem Server
File Systems Developer Tools
DAVIDSUSAIRAJ
F
license
Not graded
quality
D
maintenance
An MCP server that provides secure access to local file system operations.
Updated 6 months ago (2026-03-15 09:01 UTC)
-
saveformedearai
Cloud Storage
bramato
A
license
Not graded
quality
D
maintenance
MCP server for uploading, listing, and retrieving files on S3-compatible storage (AWS S3, DigitalOcean Spaces) with public/private access and temporary URLs.
Updated a year ago (2025-09-08 07:37 UTC)
15
MIT
fsext-mcp-server-java
File Systems Image & Video Processing Search
kurtzhi
A
license
Not graded
quality
A
maintenance
A full-featured secure MCP server for local file system operations, with built-in image processing, OCR and media tools.
Updated 2 months ago (2026-07-05 08:27 UTC)
Apache 2.0

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/OraDavis/couchdrop-mcp'

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