Combine MCP Server
Multiple MCP server aggregation into one interface for client compatibility.
Data last scanned yesterday · Reviewed last month
Overview
This aggregator functions as a bridge, allowing users to bypass limitations in clients like Cursor that restrict the number of concurrent MCP server connections. It operates by acting as both an MCP client to backend servers and an MCP server to your primary interface, consolidating multiple inputs into a single stdio stream. The tool includes features such as automatic tool name sanitization, replacing dashes with underscores to ensure compatibility, and prefixing backend methods to prevent naming collisions. Configuration is handled via JSON files or environment variables, with support for adjustable debug logging levels.
Our verdict
With a security score of 16/100, this tool carries a high risk level. It is a community-maintained project with no detected license, and it has not been editorially reviewed. Given that the code is noted as being primarily AI-generated and the last commit occurred over 240 days ago, users should exercise significant caution. This aggregator is best suited for experimental environments rather than sensitive workflows.
- Zero direct dependencies reduce supply-chain surface area.
- Bypasses MCP connection limits in clients like Cursor.
- Provides documented installation via shell script or Docker.
- High risk level due to lack of security review.
- Unclear legal terms due to missing license.
- Bus factor risk with only one contributor.
- Stale repository with no updates for 246 days.
Compatibility
No compatibility data yet.
Frequently asked questions
›Why would I use this aggregator?
This aggregator allows you to bypass limitations in certain MCP clients, such as Cursor's limit of two active MCP servers, by consolidating multiple servers into a single interface.
›Does this tool modify the names of my MCP tools?
Yes, it automatically replaces dashes with underscores in tool names to ensure compatibility with Cursor, which cannot properly detect tools containing dashes.
›How can I filter which tools are exposed to my MCP client?
You can define an "allowed" list under the tools configuration for each server in your JSON config file to manage available tools and stay within client limitations.
›How are environment variables and secrets handled?
Secrets and environment variables are centralized within the aggregator's configuration file, allowing you to maintain a single source of truth that is shared across different MCP-capable clients.
›Can I run the aggregator via Docker?
Yes, you can run the aggregator using Docker by mounting a local configuration file directory and setting the MCP_CONFIG environment variable to point to your config file inside the container.
›How can I debug issues with my MCP servers?
You can troubleshoot by setting the MCP_LOG_LEVEL environment variable to debug or trace, and optionally specify a log file path using the MCP_LOG_FILE variable.
Badge
Maintain this server? Add the live badge to your README.