Skip to main content

Open-source MCP tools for AI agents — lint, security, dependency audit, web scraping and more

Project description

AgenticStore MCP Tools

Free, open-source MCP tools for AI agents — self-hosted, no account required, no API keys for core tools.

Works with Claude Desktop, Cursor, Windsurf, VS Code, and any MCP-compatible client.


What's Included

Module Tools What it does
AgenticCode python_lint_checker Static analysis for Python — bugs, style, complexity
AgenticCode repo_scanner Scan for leaked secrets, PII, and .gitignore gaps
AgenticCode dependency_audit Check for outdated and vulnerable dependencies
AgenticData agentic_web_search SEO signal extractor — metadata, OG, Twitter Card, headings, word count

Installation

Step 1 — Install uv

uv is the Python package manager used to run and install this toolkit.

macOS / Linux

curl -LsSf https://astral.sh/uv/install.sh | sh

Windows (PowerShell)

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Windows (winget)

winget install --id=astral-sh.uv -e

Verify the install:

uv --version

Step 2 — Install AgenticStore MCP Tools

Option A — Run directly (no install needed)

uvx agentic-store-mcp

uvx downloads and runs the latest version in an isolated environment. Nothing is installed globally.

Option B — Install with pip

pip install agentic-store-mcp

Start the Server

Once installed, start the MCP server from your terminal:

# All tools
uvx agentic-store-mcp

# AgenticCode tools only (lint, scan, audit)
uvx agentic-store-mcp --modules code

# AgenticData tools only (web search, SEO)
uvx agentic-store-mcp --modules data

# Multiple modules
uvx agentic-store-mcp --modules code,data

# Single tool
uvx agentic-store-mcp --tools agentic_web_search

# List all available tools and exit
uvx agentic-store-mcp --list

If you installed via pip, replace uvx agentic-store-mcp with agentic-store-mcp in all commands above.

The server runs over stdio and stays alive until your AI client disconnects.


Connect to Your AI Client

Add the server to your AI client's config file, then restart the client.

Claude Desktop

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "agenticstore": {
      "command": "uvx",
      "args": ["agentic-store-mcp", "--modules", "code,data"]
    }
  }
}

Cursor

~/.cursor/mcp.json

{
  "mcpServers": {
    "agenticstore": {
      "command": "uvx",
      "args": ["agentic-store-mcp", "--modules", "code,data"]
    }
  }
}

Windsurf

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "agenticstore": {
      "command": "uvx",
      "args": ["agentic-store-mcp", "--modules", "code,data"]
    }
  }
}

VS Code (with MCP extension)

{
  "mcpServers": {
    "agenticstore": {
      "command": "uvx",
      "args": ["agentic-store-mcp", "--modules", "code,data"]
    }
  }
}

Run from Source

Prefer cloning the repo? This also works:

# 1. Clone
git clone https://github.com/agenticstore/agenticstore-mcp-tools
cd agenticstore-mcp-tools

# 2. Install dependencies
uv sync

# 3. Start the server
uv run server.py

# Start with specific modules or tools
uv run server.py --modules code,data
uv run server.py --tools agentic_web_search
uv run server.py --list

Point your AI client config at the local clone:

{
  "mcpServers": {
    "agenticstore": {
      "command": "uv",
      "args": ["run", "--directory", "/absolute/path/to/agenticstore-mcp-tools", "server.py"]
    }
  }
}

Programmatic Usage (Python)

Embed the server directly in a Python script:

from agentic_store_mcp import start_server

start_server()                             # all tools
start_server(modules=["code"])             # AgenticCode only
start_server(modules=["code", "data"])     # multiple modules
start_server(tools=["agentic_web_search"]) # single tool

Or wire it into a Claude Desktop config:

{
  "mcpServers": {
    "agenticstore": {
      "command": "python3",
      "args": ["-c", "from agentic_store_mcp import start_server; start_server()"]
    }
  }
}

Tool Reference

python_lint_checker

Static analysis for Python files. Checks imports, bugs, style, and complexity — zero external dependencies.

repo_scanner

Scans a directory for leaked secrets (AWS keys, API tokens, private keys), PII (emails, SSNs), and missing .gitignore entries.

dependency_audit

Audits requirements.txt, pyproject.toml, package.json, go.mod, pom.xml, and more. Checks for outdated versions and known CVEs via OSV.

agentic_web_search

Fetches any URL and returns a full SEO signal report: title, meta description, canonical URL, robots directives, Open Graph tags, Twitter Card tags, heading structure, word count, and internal/external link breakdown.


Contributing

  • Tools must be pure Python — no external API calls, no managed services
  • Each tool lives in modules/<category>/<tool_name>/ with handler.py, schema.json, and README.md
  • Run tests: uv run pytest

License

MIT — free to use, fork, and modify.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agentic_store_mcp-0.3.0.tar.gz (47.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agentic_store_mcp-0.3.0-py3-none-any.whl (55.1 kB view details)

Uploaded Python 3

File details

Details for the file agentic_store_mcp-0.3.0.tar.gz.

File metadata

  • Download URL: agentic_store_mcp-0.3.0.tar.gz
  • Upload date:
  • Size: 47.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.8 {"installer":{"name":"uv","version":"0.10.8","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for agentic_store_mcp-0.3.0.tar.gz
Algorithm Hash digest
SHA256 b05f5467688707a226ada414f3ae15f53ffff604e74e8362c110ef1a4ac833fd
MD5 ff1b5409f06eee9e7caac9951d9a1777
BLAKE2b-256 bb4249d46452beddbf2f77b09de544c4f8e6640da6025e078affa2d204305fe2

See more details on using hashes here.

File details

Details for the file agentic_store_mcp-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: agentic_store_mcp-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 55.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.8 {"installer":{"name":"uv","version":"0.10.8","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for agentic_store_mcp-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 00db4ad94ce4259ffff7382d8147303e10a572b5aa77ea684093944ab02dde64
MD5 5b59cec53009ba06d21b463cd719a1f0
BLAKE2b-256 79b67da36cf80532c1b1397314fcdffd2a3f8c13d606959d465b7b7665e951a3

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page