lugh
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LUGH_MODEL | No | Selects the model used by `think` when ANTHROPIC_API_KEY is set. | |
| ANTHROPIC_API_KEY | No | Set this so `think` uses a real LLM instead of the local stub. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Lugh is a programming language for AI agents: a program declares what it may touch (use), its limits (budget) and which actions need a human (policy). Call lugh_reference first, write the program, check it with lugh_check, then dry-run it with lugh_run and show the person the policy log before running it for real with the Lugh CLI.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| lugh_referenceA | Syntax and semantics of Lugh, a programming language for AI agents where permissions (policy), budgets and human approval are part of the code. Read this before writing a program. |
| lugh_checkA | Compile a Lugh program without running it. Reports syntax errors, unknown functions and adapters, and counts goals, tests, routes and pages. |
| lugh_runA | Run a Lugh program's goals in a sandbox. fs, http, mcp and shell act on a simulated world (see lugh_sandbox), but every call passes the real policy gate and budgets. Returns the output and a policy log of every action and its decision (allowed, approved, declined, denied). Use it to show a person exactly what an agent would do before it runs for real. |
| lugh_testA | Run the |
| lugh_sandboxA | List the simulated files, HTTP endpoints, MCP servers (with each tool's effect) and shell commands that programs run by lugh_run can use. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool occupies a clearly distinct stage: reference (docs), check (compile only), run (execute goals in sandbox), test (execute test blocks), and sandbox (inspect the simulated world). The descriptions explicitly contrast check vs. run vs. test, so an agent can select without guessing.
All names share the consistent `lugh_` prefix with snake_case, giving a predictable namespace. Minor deviation: `reference` and `sandbox` are nouns while `check`, `run`, and `test` are verbs, so the verb_noun pattern isn't uniform.
Five tools map neatly onto the lifecycle of writing and validating a Lugh program: read docs, compile, run, test, inspect sandbox. Nothing feels padded or missing at this scope.
The surface covers the full authoring loop through simulated execution and policy logging, which is the stated purpose. Minor gaps: no lint/format or scaffolding tool, and no way to progress from sandbox to a real deployment, but agents can work around these via reference.