🦊 Kitsune MCP

One config entry. 130,000+ servers on demand. Up to 95% less MCP token overhead.

Kitsune is a gateway MCP server that discovers, installs, and dynamically loads any of 130,000+ MCP servers at runtime (134,945 indexed on Glama alone as of May 2026). Instead of keeping every server's tools in context permanently, Kitsune mounts tools on demand via shapeshift() and releases them when done. Thousands available on request. No restarts.

Kitsune is not free at rest. It is itself an always-on MCP server: its six built-in tools cost ~1,321 tokens in every turn, whether you use them or not. That is its fixed floor — it never drops to zero. The win is that this floor stays flat no matter how many servers sit behind it, whereas always-on servers stack linearly. So Kitsune only pays for itself once you'd otherwise be loading more than one non-trivial server (see the break-even note below).

Why not just shell out to a CLI?

Shelling out to aws, gcloud, kubectl, or gh from a Bash tool also costs ~0 tokens at rest. So why MCP at all?

Because long-tail CLI commands fail. LLMs have great recall on the top ~20 commands of a CLI they've seen in training (git status, gh pr list, aws s3 cp) and steeply degraded recall on everything else. For an API surface the size of aws (~9,000 subcommands), first-call success drops to 30–50% on long-tail operations — wrong flag names, singular-vs-plural verbs, case-sensitive enums, and silently-deprecated options. Each miss costs a retry turn, and the worst failures aren't errors but plausible-looking wrong calls that succeed.

MCP gives you structured tool schemas the model can read and validate against:

That's the structural argument for the hub model: CLI-cheap at rest, MCP-accurate when it matters. For one-off ops on a CLI the model knows cold, gh is fine. For unfamiliar APIs, internal tooling, or any operation where a wrong call has real cost (production AWS changes, billing operations, security flows), Kitsune gives you schema-validated execution without the a

... View full README on GitHub