mcpField
F
flock-mcp

flock-mcp

Local
github.com/whiteducksoftwareAI & Agents2Updated 57w ago
Repository

About flock-mcp

flock-mcp is a collection of MCP servers and tools for the Flock agent framework. Its optional dependency groups let users install selected capabilities, including web, Azure, language-processing, and code tools.

Key features

  1. 01MCP servers and tools for Flock
  2. 02Optional dependency groups
  3. 03Web scraping, markdown, and search tools
  4. 04Azure integration tools
  5. 05Language processing and code tools

Use cases

  1. 01Adding selected tools to a Flock agent
  2. 02Installing only the needed tool groups

MCP support

Provides MCP servers and tools for use with the Flock agent framework.

#flock-mcp#mcp-servers#agent-framework

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

flock-mcp

Multiple MCP servers and tools for the agent framework Flock.

Installation

This package has no main dependencies by design, allowing you to install only the tools you need. You can install it in several ways:

Option 1: Install All Tools (Recommended)
pip install flock-mcp[all]

Or with uv:

uv add flock-mcp[all]

This installs all available tools and dependencies.

Option 2: Install Specific Tool Groups

Choose the specific tool groups you need:

# Basic tools (web scraping, markdown, search)
pip install flock-mcp[basic-tools]
uv add flock-mcp[basic-tools]

# Azure integration tools
pip install flock-mcp[azure-tools]
uv add flock-mcp[azure-tools]

# LLM and text processing tools
pip install flock-mcp[llm-tools]
uv add flock-mcp[llm-tools]

# Code and Docker tools
pip install flock-mcp[code-tools]
uv add flock-mcp[code-tools]

# All tools (same as [all] but without extra ML dependencies)
pip install flock-mcp[all-tools]
uv add flock-mcp[all-tools]
Option 3: Combine Multiple Groups

You can combine multiple optional dependency groups:

pip install flock-mcp[basic-tools,azure-tools]
uv add flock-mcp[basic-tools,azure-tools]
Option 4: Base Installation Only

Install just the base package without any optional dependencies:

pip install flock-mcp
uv add flock-mcp
Available Tool Groups
  • basic-tools: Web scraping (docling, tavily-python), markdown processing (markdownify), search (duckduckgo-search)
  • azure-tools: Azure cloud integration (azure-identity, azure-storage-blob, azure-search-documents)
  • llm-tools: Natural language processing (nltk)
  • code-tools: Code analysis and containerization (docker)
  • all-tools: All of the above tool groups
  • all: All tools plus additional ML/AI dependencies (datasets, rouge-score, sentence-transformers, zep-python, mem0ai, chromadb, matplotlib)

Usage

After installation, you can use the various MCP servers and tools provided by this package with the Flock agent framework.

# eg
from flock.tools.file_tools import file....

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.