protocols-io-mcp-server
This server enables MCP clients like Claude Desktop to interact with protocols.io for searching, retrieving, creating, and managing scientific protocols.
Search & Discovery
Search public protocols by keyword with paginated results (3 per page)
Retrieve all protocols from your account
Get protocol information by ID (title, description, URL, dates, DOI, publication status)
View detailed protocol steps including materials, quantities, and reference protocols
Protocol Creation & Editing
Create new protocols with title and description (requires searching at least 2 reference protocols first for credibility)
Update protocol titles and descriptions
Step Management
Replace all steps in a protocol at once
Add individual steps to the end of protocols with descriptions, materials (name, quantity, unit), and references to other protocol IDs
Delete specific steps by step ID
Key Features
Material tracking with quantities and units (mL, g, μL, etc.)
Protocol referencing system for credibility
Date filtering recommendations (avoids pre-2015 protocols)
Multiple authentication methods: client access tokens (STDIO) and OAuth 2.0 (HTTP/SSE)
Multiple transport options: STDIO, HTTP, and SSE for different deployment scenarios
Error handling with descriptive messages
Enables searching, retrieving, creating, and managing scientific protocols and their steps on the protocols.io platform, including protocol metadata management and step-by-step procedure handling.
Click on "Deploy 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., "@protocols-io-mcp-server search for CRISPR protocols"
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.
Protocols.io MCP Server
A Model Context Protocol (MCP) server that enables MCP clients like Claude Desktop to interact with protocols.io, a popular platform for sharing scientific protocols and methods.
Available Tools
The server provides the following tools that can be used by MCP clients:
Search and Retrieval
search_public_protocols- Search for public protocols by keywordget_protocol- Get basic protocol information by IDget_protocol_steps- Get detailed steps for a specific protocolget_my_protocols- Retrieve all protocols from your account
Protocol Creation and Management
create_protocol- Create a new protocol with title and descriptionupdate_protocol_title- Update the title of an existing protocolupdate_protocol_description- Update the description of an existing protocol
Step Management
set_protocol_steps- Replace all steps in a protocoladd_protocol_step- Add a single step to the end of a protocoldelete_protocol_step- Delete a specific step from a protocol
Related MCP server: 302AI Sandbox MCP Server
Requirements
Python 3.10 or higher
protocols.io account with API credentials
MCP client (such as Claude Desktop)
Obtain Protocols.io API Credentials
Visit protocols.io/developers
Sign in to your account
Navigate to the API Clients section
Click ADD CLIENT to create a new application
Configure and copy the credentials based on your use case:
Client Access Token: Copy the generated token for simple authentication (suitable for local STDIO transport)
Client ID and Client Secret: For OAuth 2.0 authentication (suitable for remote HTTP/SSE transport):
Set the redirect URL to
{your_mcp_base_url}/auth/callbackCopy the Client ID and Client Secret
Installation
Quick Start with Docker
docker run -d -p 8000:8000 -e PROTOCOLS_IO_CLIENT_ID="your_client_id" -e PROTOCOLS_IO_CLIENT_SECRET="your_client_secret" -e PROTOCOLS_IO_MCP_BASE_URL="https://example.com" --name protocols-io-mcp --restart always ghcr.io/hqn21/protocols-io-mcp:latestThe server will be accessible at http://0.0.0.0:8000/mcp with HTTP transport
Install via pip
pip install protocols-io-mcpSet Environment Variables
STDIO Transport
export PROTOCOLS_IO_CLIENT_ACCESS_TOKEN="your_client_access_token"HTTP/SSE Transport
export PROTOCOLS_IO_CLIENT_ID="your_client_id"
export PROTOCOLS_IO_CLIENT_SECRET="your_client_secret"
export PROTOCOLS_IO_MCP_BASE_URL="https://example.com"Usage
Command Line Interface
Run the MCP server with various transport options:
# Default: STDIO transport
protocols-io-mcp
# HTTP transport
protocols-io-mcp --transport http --host 127.0.0.1 --port 8000
# SSE transport
protocols-io-mcp --transport sse --host 127.0.0.1 --port 8000CLI Options
Usage: protocols-io-mcp [OPTIONS]
Run the protocols.io MCP server.
Options:
--transport [stdio|http|sse] Transport protocol to use [default: stdio]
--host TEXT Host to bind to when using http and sse
transport [default: 127.0.0.1]
--port INTEGER Port to bind to when using http and sse
transport [default: 8000]
--help Show this message and exit.Integration with Claude Desktop
To use this server with Claude Desktop, add the following configuration to your claude_desktop_config.json:
{
"mcpServers": {
"protocols-io": {
"command": "protocols-io-mcp",
"env": {
"PROTOCOLS_IO_CLIENT_ACCESS_TOKEN": "your_client_access_token"
}
}
}
}Troubleshooting
MCP protocols-io: spawn protocols-io-mcp ENOENT
This error indicates that Claude Desktop cannot find the protocols-io-mcp command. To resolve this:
Make sure you have installed the
protocols-io-mcppackage globally using pip.Change the
commandfield in yourclaude_desktop_config.jsonto the full path of theprotocols-io-mcpexecutable. You can find the path by running:which protocols-io-mcpYour final configuration should look like:
{ "mcpServers": { "protocols-io": { "command": "/full/path/to/protocols-io-mcp", "env": { "PROTOCOLS_IO_CLIENT_ACCESS_TOKEN": "your_client_access_token" } } } }
Development
Running Tests
Ensure you have set the PROTOCOLS_IO_CLIENT_ACCESS_TOKEN environment variable, then run:
pytestLicense
This project is licensed under the MIT License. See the LICENSE file for details.
Available Tools
10 toolsadd_protocol_stepA
Add a step to the end of the steps list for a specific protocol by its protocol ID.
Inputs: protocol_id (required), step (required). Returns: result
create_protocolA
Create a new protocol with the given title and description.
Before creating a new protocol, ensure you have searched for at least 2 relevant public protocols using search_public_protocols and reviewed their detailed steps with get_protocol_steps for reference when adding steps.
Inputs: title (required), description (required). Returns: result
delete_protocol_stepB
Delete a specific step from a protocol by providing both the protocol ID and step ID.
Inputs: protocol_id (required), step_id (required). Returns: result
get_my_protocolsA
Retrieve basic information for all protocols belonging to the current user. To get detailed protocol steps, use get_protocol_steps.
Inputs: no named parameters. Returns: result
get_protocolA
Retrieve basic information for a specific protocol by its protocol ID. To get detailed protocol steps, use get_protocol_steps.
Inputs: protocol_id (required). Returns: result
get_protocol_stepsA
Retrieve the steps for a specific protocol by its protocol ID.
Inputs: protocol_id (required). Returns: result
search_public_protocolsA
Search for public protocols on protocols.io using a keyword. Results are sorted by protocol popularity and paginated with 3 protocols per page (use the page parameter to navigate, default is 1).
When searching for reference protocols to create a new protocol:
Avoid referencing protocols from before 2015 as they may be outdated.
If the found protocols have topics that are not closely related to your needs, ask the user for clearer direction before proceeding.
If the found protocols are highly relevant, use get_protocol_steps to examine at least 2 protocols' detailed steps and integrate insights from different approaches to ensure more reliable protocol development.
Inputs: keyword (required), page. Returns: result
set_protocol_stepsA
Replace the entire steps list of a specific protocol by its protocol ID with a new steps list. The existing steps will be completely overwritten.
Inputs: protocol_id (required), steps (required). Returns: result
update_protocol_descriptionA
Update the description of an existing protocol by its protocol ID.
Inputs: protocol_id (required), description (required). Returns: result
update_protocol_titleA
Update the title of an existing protocol by its protocol ID.
Inputs: protocol_id (required), title (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Each tool has a clearly distinct purpose: create, read, update, delete for protocols and steps, plus search. No overlapping functionality.
All tool names follow a consistent verb_noun pattern using snake_case (e.g., create_protocol, get_protocol_steps). No deviations.
10 tools is well-scoped for managing protocols and steps, covering CRUD operations and search without excess.
Missing explicit delete_protocol tool and individual step update (only add, delete, replace all). Users cannot delete a protocol entirely, which is a notable gap.
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.
The Telnyx MCP server is an official implementation of the Model Context Protocol that enables AI clients (like Claude Desktop, Cursor, and OpenAI Agents) to interact with Telnyx's telephony, messaging, and AI assistant APIs. It provides comprehensive capabilities including making and managing phone calls, sending SMS/MMS messages, purchasing and configuring phone numbers, creating AI assistants with custom instructions, managing cloud storage buckets, scraping and embedding website content, and handling integration secrets. The server exists as both a local implementation and a remotely hosted version, allowing developers to integrate real-world communication infrastructure directly into AI applications.
Related MCP Servers
- AlicenseDqualityDmaintenanceA server built on mcp-framework that enables integration with Claude Desktop through the Model Context Protocol.11MIT
- AlicenseAqualityDmaintenanceA Model Context Protocol (MCP) server for Claude Desktop that connects to 302AI's API services, allowing users to integrate and leverage 302AI capabilities through a structured communication interface.928 npm21MIT
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) server that allows Claude AI to interact with custom tools, enabling extension of Claude's capabilities through the MCP framework.-
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that allows integration with Claude Desktop by creating and managing custom tools that can be executed through the MCP framework.-