BaseMcpServer
About
A minimal, containerized base for building MCP servers with the Python SDK, featuring a standardized Docker image and local development setup.
Details
- Author
- dawsonlp
- GitHub stars
- 3
- Downloads
- 169
- Categories
- Other, Developer Tools
Jump to
- mcp-manager CLI for installing, managing, and configuring MCP servers
- Each server runs in its own isolated uv‑managed virtual environment
- Single config sync command updates both Cline and Claude Desktop
- Multi‑instance Jira + Confluence server (jira-helper)
- Current‑context tools: date/time, market, news, dev‑tool versions (worldcontext)
- Server generator that scaffolds new MCP servers from a code snippet (mcpservercreator)
- Starter template for building custom servers with shared infrastructure
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
BaseMcpServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install uv and mcp-manager via a one‑line curl command, then use mcp-manager install local <server> --source <path> to install individual servers. After editing per‑server config files, run mcp-manager config sync to wire all servers into VS Code/Cline and Claude Desktop over stdio.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"basemcpserver": {
"BaseMcpServer": {
"command": "uv",
"args": [
"tool",
"install",
"git+https://github.com/dawsonlp/BaseMcpServer.git#subdirectory=utils/mcp_manager"
]
}
}
}
}
McpServers
{
"BaseMcpServer": {
"command": "uv",
"args": [
"tool",
"install",
"git+https://github.com/dawsonlp/BaseMcpServer.git#subdirectory=utils/mcp_manager"
]
}
}
A monorepo ofModel Context Protocolservers plus themcp-managerCLI that installs and configures them.
BaseMcpServer/ ├── utils/mcp_manager/ # CLI for installing + managing MCP servers (canonical install path) ├── servers/ │ ├── jira-helper/ # Jira + Confluence integration server (multi-instance) │ ├── worldcontext/ # Current-context tools (date/time, market, news, dev-tool versions) │ ├── mcpservercreator/ # Generator that scaffolds new MCP servers from a code snippet │ ├── loadbearing-youtube/ # Extract a YouTube transcript + expose its load-bearing components │ └── template/ # Starter scaffold to fork when building a new server ├── docs/ │ ├── adr/ # Architecture Decision Records │ ├── developer/ # Implementation guides (build a new MCP server, client support, etc.) │ └── user/ # End-user docs (Cline compatibility, etc.) └── QUICKSTART.md # End-to-end jira-helper onboarding
Every server in this repo is a Python package installable viamcp-manager install, gets its own isolateduv-managed environment under~/.config/mcp-manager/servers/<name>/.venv, and is wired into VS Code/Cline + Claude Desktop with a singlemcp-manager synccall.
# 1. One-time: install uv and mcp-manager curl -LsSf https://astral.sh/uv/install.sh | sh uv tool install "git+https://github.com/dawsonlp/BaseMcpServer.git#subdirectory=utils/mcp_manager" uv tool update-shell # 2. Install whichever servers you want mcp-manager install jira-helper --source ./servers/jira-helper mcp-manager install worldcontext --source ./servers/worldcontext mcp-manager install mcpservercreator --source ./servers/mcpservercreator mcp-manager install loadbearing-youtube --source ./servers/loadbearing-youtube # 3. Edit the per-server config files (where credentials go) — see each server's README $EDITOR ~/.config/mcp-manager/servers/jira-helper/config.yaml # 4. Wire the servers into Cline + Claude Desktop mcp-manager sync
For an end-to-end walkthrough with jira-helper (including Atlassian API token setup), seeQUICKSTART.md.
Detailed reference:docs/developer/BUILD_A_NEW_MCP.md.
For dynamically generating a server from a code snippet, see themcpservercreatorserver itself, once installed.
mcp-manager sync # write to both Cline + Claude Desktop # or selectively: mcp-manager sync --platform cline mcp-manager sync --platform claude
mcp-managerwritesmcpServersentries that point at~/.config/mcp-manager/servers/<name>/.venv/bin/<name>over stdio. Restart your editor for the new entries to take effect.
Example entry (written automatically; shown for reference):
{ "mcpServers": { "jira-helper": { "command": "/Users/<you>/.config/mcp-manager/servers/jira-helper/.venv/bin/jira-helper", "args": ["stdio"], "disabled": false, "autoApprove": [] } } }
Hand-added entries in your editor's settings file are preserved acrosssync— only entries that match a server name in the mcp-manager registry are overwritten.
The major directional choices are tracked underdocs/adr/:
- ADR-003— current: all server installs go throughuv
- ADR-002— superseded; documents the earlier pipx-default attempt
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Create crafted UI components inspired by the best 21st.dev design engineers.
Bring agent evaluations, observability, and synthetic test set generation directly into your IDE for free with Galileo's new MCP server
An MCP server to help AI assistants to answer questions and generate AccelByte Extend SDK code more effectively .
MCP server for AI Diagram Maker — generate beautiful software engineering diagrams directly inside Cursor, Claude Desktop, Claude Code, or any MCP-compatible AI agent
ALAPI MCP Tools,Call hundreds of API interfaces via MCP
AI-powered SVG animation generator that transforms static files into animated SVG components using the Allyson platform
MCP server that gives AI assistants on-demand access to 1,500+ amCharts docs, ~300 code examples, and 1000+ class API references.
APIMatic MCP Server is used to validate OpenAPI specifications using APIMatic. The server processes OpenAPI files and returns validation summaries by leveraging APIMatic’s API.
One shared context layer for AI agents and humans — live API specs, DB schemas, and versioned contracts across repos so every agent and teammate works from the same source of truth.
Build and deploy full-stack Next.js apps with 98 tools for React, AWS, and MongoDB
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.





