MCP servers · byggarepop

McpOrchestrator: MCP relay with on-demand tool discovery

An MCP relay that connects one agent to several downstream MCP servers and loads their tool definitions only when needed.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

McpOrchestrator sits between an agent and any number of other MCP servers. Downstream tool manifests are loaded on demand, so the agent's always-on context does not grow with each server added. The agent sees three meta-tools: list_capabilities, discover_tools and route. The orchestrator forwards requests without interpreting them. It can also serve Agent Skills, using the same on-demand loading.

It suits setups where many MCP servers would otherwise load their full tool lists into every prompt. In the publisher's measurement against a workplace MCP setup, counted with the Copilot CLI's /usage command, a server connected directly used 17,900 tokens of context, while the same server behind the orchestrator used 1,400. The publisher states that the savings grow with the number of servers.

Setup starts from an existing host config such as .mcp.json, .vscode/mcp.json or a Cursor config. The init step converts stdio servers into a generated orchestrator.config.json, backs up the host config and rewrites it to launch only the orchestrator. Later edits to the config reload without a restart. Skills are folders containing a SKILL.md file, and the config points to those folders. Skills can also come from git repositories or HTTP indexes, with allow and deny lists and integrity pinning. A profile command measures token use, and full documentation is in the repository's README and docs folder.

Limitations and requirements

The profile command needs the .NET SDK. Skills are available to the agent only: they do not appear as host-native skills, so there is no /skills listing or slash command in Claude Code and no entry in an IDE skill picker.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    McpOrchestrator

    Route one agent through one MCP server to many, with progressive tool discovery to shrink context.

    v0.7.6
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
neondatabase

Neon MCP Server (Postgres)

Neon's MCP server for managing Neon Postgres in plain language: create projects and branches, run queries and prepare schema migrations from your editor.

663 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
supabase-community

Supabase MCP Server

Supabase's MCP server that connects an AI assistant to your Supabase project to design tables, run queries, read configuration and look up documentation.

Data & databasesSoftware development
Updated 17 Nov 2026