Just found this project, I worked on something similar with different architecture that used a mid layer between the LLM and the user's dev environment (language agnostic, they just add a small interpreter) The LLM works with super small token-efficient instructions:
Example:
// x = 10
0.11("x", 10)
// x = x + 5
0.17($x, 5)
0.11("x", $result)
// print x, then stop
0.13($x)
0.1()These instructions would then be run inside javascript, python, or whatever language (I have a template for generating new interpreters). Very different approach than zerolang but may have some tricks you guys can draw inspiration from for saving tokens.
Activity
2
TolinSimpson5mo agoMCP wraps a vectorizer and is just an example of how an LLM can interact with the main layer using a tool call. A more intentional implementation would be required. I speculate something could be learned from the pattern. The above AI generated reply isn't helpful since it lacks full context of the repo I cited.
The title says MCP but the body is about token-efficient encoding. Worth separating, because Zero arguably already has the first.
On tokens:
query/patch --opis functionally what the LLMVCS opcodes reach for — a compact structured edit channel where the compiler, not regenerated text, is ground truth. The graph already hands the agent node ids,graphHash, types, effects and call edges, andzero patchrejects a stale hash or invalid shape before the store is written. That transactional boundary is the part an opcode stream lacks, and it's exactly what makes an MCP wrapper safe.On MCP: since the
--jsoncontract is already stable, a server is a thin adapter, not new semantics. What tends to work in agent-facing MCP servers:query?fn=…|find=…|refs=…, and diagnostics fromzero dev --json. Reads never mutate, so agents can poll them cheaply.apply_patch(ops[], expectGraphHash),check,test(filter),run(args),explain(code).apply_patchshould require the caller to echo thegraphHashit read, so a stale edit fails closed instead of racing.Three pitfalls from building agent-facing MCP servers:
run_zero(cmd)passthrough. It defeats the schema — the model loses the typed errors that make Zero legible, and you can't gate mutation from inspection.{code, span, message}(whichcheck --json/dev --jsonalready emit), not rendered prose. Models repair far better against fields, andexplain(code)becomes a real follow-up tool..0text, soimport/exportstay the only entry for human edits — the invariant the CLI already enforces.Open question for maintainers: is an MCP server in scope, or is the intended path the version-matched skill + plain CLI? If skill-first, the real "MCP optimization" may just be tightening which
--jsonfields the skill tells agents to request. Happy to prototype a reference server against the current--jsonshapes if that'd be useful.