Skip to main content
Glama
Sign In

AILANG Executor

by io.github.sunholo-data
OverviewDiscussionsAdmin

Run AILANG code (sandboxed)

ailang_run
Read-onlyIdempotent

Run AILANG source in the hosted sandbox. Entry point is main, with no arguments. Only the IO capability is granted (println works; FS, Net, Process, Env and AI are refused by name before the program starts), and the run is killed at the policy timeout. stdout is the program's output; stderr carries the policy decision JSON.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "code": "<code>"
    },
    "name": "ailang_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Although the annotations already declare readOnly, idempotent, closed-world and non-destructive, the description adds real detail beyond them: the capability allowlist (IO only, with FS/Net/Process/Env/AI refused by name before the program starts), and the fact that the run is killed at the policy timeout. The placement of kernel-level detail with stdout/stderr is exactly the behavioral context an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences with no waste, front-loaded with the core action and then layering constraints and output-channel semantics. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter tool with no output schema, the description covers the execution model, failure mode and output channels well. Minor gaps remain: it doesn't say how errors from the program itself surface (exit status, or how they mix with the policy JSON), and it doesn't say what 'stdout is the program's output' means for size, truncation or cost.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is only one parameter and the schema coverage is 0%, so the description has to carry the meaning of `code`, and it does so indirectly by naming the entry point (`main`) and the no-argument calling convention. A brief note on the expected source form would help, but a single-parameter tool is easy to call correctly from this text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb ('Run') and resource ('AILANG source'), and it names the environment ('hosted sandbox'), so an agent can distinguish this from ailang_check and ailang_eval without opening a schema. The phrase 'Entry point is `main`, with no arguments' further pins down what 'run' means.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the execution contract: only IO is granted, other capabilities are refused, and the policy timeout is binding. That implicitly tells the agent when a program will run and when it will fail, but the description never says when to prefer this over ailang_check or ailang_eval, and it gives no exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All AILANG Executor toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources