rent.dev

Store a vendor key

rent_set_byok_credential

Stores your own vendor key (BYOK) for e2b and vercel sandboxes or runpod GPU pods, after one read-only call to the vendor checks it. The secret is an argument of this call; it is stored sealed and never returned. fields: e2b {api_key}, vercel {token, team_id, project_id}, runpod {api_key}. The credential id (cred_…) stays valid until you delete it (DELETE /v1/byok/credentials/{id}). An API key with a spend limit cannot store one (403 forbidden): use an uncapped key or a signed-in person.

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": {
      "vendor": "<vendor>",
      "fields": "<fields>"
    },
    "name": "rent_set_byok_credential"
  }
}

Input Schema

Name	Required	Description
`label`	No
`fields`	Yes	The vendor's secret fields.
`vendor`	Yes

Output Schema

Name	Required	Description	Default
`id`	Yes
`label`	Yes
`vendor`	Yes
`created_at`	Yes
`validated_at`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A3.9/5.0

Behavior3/5

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

Beyond the annotations it discloses the sealing of the secret, that it is never returned, an outbound read-only vendor validation call, and credential lifetime until explicit deletion. The annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false; the description never clarifies re-invocation behavior, which is the key ambiguity left by idempotentHint=false.

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

Conciseness4/5

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

Front-loaded with the core action and scoped to the three relevant vendors, then layered with storage, lifetime, and error details. The trailing DELETE-endpoint parenthetical is slightly tangential but does useful work by pointing at the revocation path.

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?

An output schema exists, so return values need not be described, and the definition covers validation, sealed storage, lifetime, and one failure mode for a nested-object mutation. The remaining gap is what happens on repeat calls for the same vendor (replace vs duplicate), which matters for a non-idempotent write.

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

Parameters3/5

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

The vendor-to-fields mapping (e2b {api_key}, vercel {token, team_id, project_id}, runpod {api_key}) is genuinely additive given the flat four-property `fields` object with only 33% schema coverage. However `label` is never explained, and per-vendor required vs optional fields are not stated.

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 names a specific verb and resource ('Stores your own vendor key (BYOK)') and enumerates the exact targets: e2b and vercel sandboxes, runpod GPU pods. That is enough to separate it from rent_create_sandbox and rent_create_gpu_pod, which consume the credential rather than store it.

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

Usage Guidelines4/5

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

It gives the pre-condition (the key must pass a read-only vendor check) and a concrete remediation for the 403 spend-limit case: 'use an uncapped key or a signed-in person.' What it does not say is when an agent should prefer BYOK over the default provider credentials, so the use-vs-alternative framing is incomplete.

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

All rent.dev tools Inspect

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

Need Help?