MCP Server

TheMCP Serverprovides a comprehensive framework for AI-powered command execution, plugin-based tools, and advanced features including synchronous script execution, secure Python evaluation, and knowledge management. It can be run as a standalone service or embedded in other projects to expose a consistent API for invoking tools and managing tasks.

- mcp_tools/– Plugin framework and built-in tools with enhanced concurrency management
- server/– Starlette server implementation with HTTP/SSE endpoints and DataFrame UI
- plugins/– Extensible plugins (Azure DevOps, Git tools, knowledge indexing, Kusto, CircleCI)
- config/– Environment manager and configuration helpers
- utils/– Core utilities (async jobs, graph interface, memory management, vector store, PyEval)
- scripts/– Installation, utility scripts, and automated submission workflows
- assets/– Images and documentation resources

The project usesuvfor dependency management. Install dependencies with:

Or install in development mode using pip:

Configuration is controlled by.envfiles. Create one from the template and edit it with your settings:

Important variables include repository paths (GIT_ROOT), Azure Repo details (AZREPO_ORG,AZREPO_PROJECT,AZREPO_REPO), and optionalPRIVATE_TOOL_ROOTfor external tool configuration. The environment manager automatically loads.envfiles from the repository root, current directory, and your home directory.

from config import env_manager env_manager.load() root = env_manager.get_git_root()

Seedocs/config_overview.mdfor more information.

After installing dependencies and configuring.env, start the server with:

Connect to the SSE endpoint athttp://0.0.0.0:8000/sseor use the additional routes inserver/api.py. Background job endpoints are documented indocs/background_jobs_api.md.

ADockerfileis included for running the server in a container. Build the image with:

Then start the container exposing port8000:

The server loads prompts and tool definitions from YAML files:

Private overrides can be placed inserver/.private/or in a folder pointed to byPRIVATE_TOOL_ROOT. Files are resolved in this order:
- PRIVATE_TOOL_ROOT
- server/.private/
- Defaults inserver/

Tools are modular plugins registered throughmcp_tools. Built-in utilities include:

- Command Executor– Synchronous and asynchronous command execution with run-to-completion support
- Browser Automation– Playwright integration for web interaction
- PyEval– Secure Python expression evaluation using RestrictedPython
- DataFrame Service– Data analysis and visualization with web interface
- Time Helpers– Time-based utilities and scheduling
- YAML Tool Loader– Dynamic tool definitions from YAML files

Additional plugins in theplugins/directory include Azure DevOps integration, Git operations, knowledge indexing, Kusto queries, and CircleCI workflows. Seemcp_tools/docs/creating_tools.mdfor details on building custom tools.

The web interface offers comprehensive dashboards:

- /tools– Browse all registered tools and view their details
- /dataframes– Interactive DataFrame management and visualization
- /knowledge– Knowledge graph exploration and management
- /pyeval– Secure Python evaluation interface

External plugins can be installed by declaring them inplugin_config.yaml. Each entry should specify aplugin_repoin the formowner/repositoryand an optionalsub_dirif the plugin lives in a subfolder. Example:

plugins: - plugin_repo: "github_owner/repo" sub_dir: "path/to/plugin" type: "python"

Run themcp_admintool with therefresh_pluginsoperation to clone or update plugins based on this configuration. Passforce=trueto remove all installed plugins before reinstalling.

Or runpytestdirectly onmcp_tools/tests,plugins/*/tests, orserver/tests.

- Run-to-Completion Execution– Synchronous script execution with comprehensive output capture
- PyEval Security– Safe Python expression evaluation using RestrictedPython
- Enhanced DataFrame UI– Responsive web interface for data analysis and visualization
- Browse the documentation undermcp_tools/docs/anddocs/to learn about tool creation, dependency injection, and advanced features.
- Review the sample configuration files inserver/and try adding your own tools.
- Explore plugins in theplugins/directory for concrete implementations.
- Check theutils/directory for advanced utilities like vector stores, graph interfaces, and memory management.
- See theCHANGELOG.mdfor detailed release notes and recent updates.

Editors like Cursor/VSCode can use the SSE endpoint by adding the following to your settings:

{ "mcpServers": { "mymcp-sse": { "url": "http://0.0.0.0:8000/sse" } } }

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