Skip to main content
Glama

EQVPS — VPS and code sandboxes for AI agents

by io.github.Poiuyhje
OverviewDiscussionsAdmin

Create a code sandbox

create_sandbox

Start an isolated Firecracker microVM sandbox (ready in about 1 s; Linux with Python 3.12 + pip, Node.js 22 + npm, bash, git and curl; internet egress allowed so pip/npm install and git clone work; no inbound ports, SMTP blocked). mode: "ephemeral" (default — billed per second, minimum 60 s, auto-deleted after idle_timeout s of inactivity, default 300, max lifetime ttl up to 24 h) or "persistent" (billed per started hour, a month costs at most 730 h minus 25%; survives host maintenance; max ttl 30 days). tariff (default small): micro 0.25 vCPU/512 MB RAM/3 GB disk $0.0165/h · small 0.5 vCPU/1 GB RAM/5 GB disk $0.033/h · standard 1 vCPU/2 GB RAM/10 GB disk $0.066/h · plus 2 vCPU/4 GB RAM/15 GB disk $0.132/h · pro 4 vCPU/8 GB RAM/20 GB disk $0.264/h · max 8 vCPU/16 GB RAM/40 GB disk $0.528/h (pick plus or bigger for heavy pip installs such as torch, builds or data work). Headless browsers (Chromium via Playwright/Puppeteer) need standard or bigger — micro/small do not have enough RAM. If the host is busy the call fails with 503 capacity (Retry-After) — retry or choose a smaller tariff. Charged from the same prepaid balance as VPS (no subscription). Empty balance → 402 insufficient_balance (top up with topup_balance). If the balance runs out later, persistent sandboxes are paused (memory+disk snapshot, not billed) and resume automatically after a top-up; paused snapshots are deleted after 14 days. The response has state: "running" and ready: true once you can exec (usually immediately); if it says starting, call get_sandbox after 1-2 s. Always kill_sandbox when done. Requires: token + balance (a new account's first sandbox gets a free $1 trial credit once the account email is confirmed with a 6-digit code — 402 with trial=email_unverified until then: the human confirms it in the dashboard, or POST /auth/email/verification/send, then /confirm {code}; no top-up needed; until the first real top-up: micro or small, ephemeral, up to 2 at once, each deleted after 20 min (the $1 credit itself lasts 14 days) → 403 trial_tariff / trial_persistent, 429 trial_limit). Typical errors: 402 insufficient_balance → topup_balance; 503 capacity → retry or smaller tariff.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
envNoEnvironment variables for every command and code run in this sandbox, e.g. {"OPENAI_API_KEY": "sk-..."}. Stored encrypted; responses show only the names (env_keys). Up to 64 variables, 64 KB in total.
ttlNoMaximum lifetime in seconds (ephemeral up to 86400, persistent up to 2592000).
modeNo
tariffNoTariff: micro | small | standard | plus | pro | max (see sandbox_pricing).
idle_timeoutNoSeconds of inactivity before an ephemeral sandbox is deleted (default 300, max 3600). 0 = none (persistent only).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / env
      Added value: +{
+  "additionalProperties": {
+    "maxLength": 32768,
+    "type": "string"
+  },
+  "description": "Environment variables for every command and code run in this sandbox, e.g. {\"OPENAI_API_KEY\": \"sk-...\"}. Stored encrypted; responses show only the names (env_keys). Up to 64 variables, 64 KB in total.",
+  "propertyNames": {
+    "pattern": "^[A-Za-z_][A-Za-z0-9_]{0,127}$"
+  },
+  "type": "object"
+}
  2. Changed2 schema fields changed
    • addedInput schema / properties / tariff / description
      Added value: +"Tariff: micro | small | standard | plus | pro | max (see sandbox_pricing)."
    • changedInput schema / properties / tariff / enum
      Previous value: -[
-  "micro",
-  "small",
-  "std"
-]New value: +[
+  "micro",
+  "small",
+  "standard",
+  "plus",
+  "pro",
+  "max"
+]
  3. Added

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: readiness (~1 s), billing model per mode, minimum 60 s, idle_timeout auto-deletion, ttl caps, pause/snapshot/resume semantics, 14-day snapshot deletion, capacity 503 with Retry-After, and the full trial-account restriction set (402 trial=email_unverified, 403 trial_tariff/trial_persistent, 429 trial_limit, 2-concurrent/20-min/14-day limits). This is unusually complete behavioral disclosure for a mutation tool.

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

Conciseness3/5

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

The core facts are front-loaded, but the description is a single sprawling paragraph dense with nested parentheticals, and the full tariff pricing table duplicates the sibling sandbox_pricing tool. Several sentences (pricing tiers, balance mechanics) could be deferred to that sibling. It reads as over-sized for a create call even though much of the content is genuinely useful.

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

Completeness5/5

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

No output schema exists, yet the description specifies the response shape ('state: running', 'ready: true', or 'starting'), and it covers the nested env object's storage/encryption behavior and limits. Given the tool's complexity (5 params, nested object, no annotations), an agent has everything needed to call it correctly and interpret the result.

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

Parameters5/5

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

Schema coverage is 80%, but the description adds meaning the schema lacks — mode's enum has no schema description yet is fully defined here (ephemeral vs persistent, billing, survival across maintenance, differing ttl caps), and tariff's enum is expanded into vCPU/RAM/disk/pricing guidance plus a sizing recommendation. idle_timeout's 0 = none (persistent only) nuance is also supplied. Value is added well beyond the structured fields.

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?

Opens with a specific verb+resource: 'Start an isolated Firecracker microVM sandbox', immediately identifying this as the creation tool among siblings create_*/get_sandbox/list_sandboxes/kill_sandbox. The runtime contents (Python 3.12, Node 22, bash, git, curl) and network posture make the resource concrete rather than generic. An agent can distinguish it from every sibling without opening a schema.

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

Usage Guidelines5/5

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

Gives explicit routing: call get_sandbox after 1-2 s if state is 'starting', 'Always kill_sandbox when done', topup_balance on 402, and 'retry or choose a smaller tariff' on 503. It also states when to pick each mode and tariff (e.g. 'pick plus or bigger for heavy pip installs', headless browsers need standard+). Alternatives and conditions are named rather than inferred.

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

All EQVPS — VPS and code sandboxes for AI agents 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