Skip to main content
Glama

protocol-mcp

BioContextAI - Registry Tests Documentation

MCP that connects to wetlab protocol resources, including protocols.io

Getting started

Please refer to the documentation, in particular, the API documentation.

You can also find the project on BioContextAI, the community-hub for biomedical MCP servers: protocol-mcp on BioContextAI.

Related MCP server: LabArchives MCP Server

Installation

You need to have Python 3.10 or newer installed on your system. If you don't have Python installed, we recommend installing uv.

There are several alternative options to install protocol-mcp:

1. Use uvx to run it immediately

After publication to PyPI:

uvx protocol_mcp

Or from a Git repository:

uvx git+https://github.com/biocontext-ai/protocol-mcp.git@main

2. Include it in one of various clients that supports the mcp.json standard

If your MCP server is published to PyPI, use the following configuration:

{
  "mcpServers": {
    "protocol-mcp": {
      "command": "uvx",
      "args": ["protocol_mcp"]
    }
  }
}

In case the MCP server is not yet published to PyPI, use this configuration:

{
  "mcpServers": {
    "protocol-mcp": {
      "command": "uvx",
      "args": ["git+https://github.com/biocontext-ai/protocol-mcp.git@main"]
    }
  }
}

For purely local development (e.g., in Cursor or VS Code), use the following configuration:

{
  "mcpServers": {
    "protocol-mcp": {
      "command": "uvx",
      "args": [
        "--refresh",
        "--from",
        "path/to/repository",
        "protocol_mcp"
      ]
    }
  }
}

If you want to reuse and existing environment for local development, use the following configuration:

{
  "mcpServers": {
    "protocol-mcp": {
      "command": "uv",
      "args": ["run", "--directory", "path/to/repository", "protocol_mcp"]
    }
  }
}

3. Install it through pip:

pip install --user protocol_mcp

4. Install the latest development version:

pip install git+https://github.com/biocontext-ai/protocol-mcp.git@main

Contact

If you found a bug, please use the issue tracker.

Citation

t.b.a

Available Tools

2 tools
get_protocolA

Retrieve full protocol details from protocols.io.

Parameters

protocol_id : str Protocol identifier - can be a URI (e.g., 'rna-extraction-abc123'), DOI (e.g., '10.17504/protocols.io.xxx'), or numeric ID. include_steps : bool Whether to include step-by-step instructions, defaults to True. include_materials : bool Whether to include materials/reagents list, defaults to True.

Returns

str Formatted markdown with protocol metadata, materials, and steps.

Inputs: protocol_id (required), include_steps, include_materials. Returns: result

search_protocolsA

Search protocols.io for laboratory protocols.

Parameters

query : str Search term to find protocols. max_results : int Number of results (1-50), defaults to 10.

Returns

str Formatted list of matching protocols with title, DOI, URI, and step count.

Inputs: query (required), max_results. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: one retrieves a specific protocol by ID, the other searches for protocols by query. No overlap in functionality.

    Naming Consistency5/5

    Both tools follow a consistent verb_noun pattern with underscores: 'get_protocol' and 'search_protocols'. The naming is predictable and clear.

    Tool Count2/5

    With only 2 tools, the server feels under-scoped for the domain of laboratory protocols. A typical server covering protocols would require more tools for CRUD operations and listing.

    Completeness2/5

    The server only provides read operations (get and search). Missing create, update, delete, and list functionalities, leaving significant gaps in protocol management.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers