Runlater

This connector has been deprecated

Duplicate

set_secret

Store a credential once and refer to it instead of pasting it into requests: put {{secret:NAME}} in a header value of schedule_http, create_cron, watch_http or set_wake, e.g. "Authorization": "Bearer {{secret:GITHUB_TOKEN}}". AgentLater encrypts the value, fills it in only at the moment it sends, and only to allowed_hosts: a request to any other host is refused, so a tricked or mistaken call cannot leak it. The value is never returned by any call, and if a destination echoes it back as sent, JSON-escaped or URL-encoded, a captured response shows [secret:NAME] instead (best effort: other encodings are not caught). Calling again with the same name replaces the value and hosts; work that refers to it uses the new value from its next attempt. At most 50 secrets.

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": {
      "name": "<name>",
      "value": "<value>",
      "allowed_hosts": "<allowed_hosts>"
    },
    "name": "set_secret"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	The secret's name, e.g. "GITHUB_TOKEN".
`value`	Yes	The credential: 16 to 4096 characters of printable ASCII, no line breaks (it is sent in a header).
`allowed_hosts`	Yes	The exact host names it may be sent to, e.g. "api.github.com". No scheme, port, path or wildcard: under shared domains (workers.dev, amazonaws.com) anyone can get a name, so a wildcard can't be made safe.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 3, 2026

TDQS

A4.6/5.0

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 thoroughly: encryption at rest, injection only at send time, host allowlisting with refusal to other hosts, value never returned, redaction of echoed values with an explicit best-effort caveat about other encodings, replace semantics, and a 50-secret cap.

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 idea and use case, then security guarantees, then mutation semantics. Dense but every sentence carries information; the final clauses about replacement and the secret cap are slightly rushed together.

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?

Covers everything an agent needs for a 3-param write tool with no output schema: how the secret is referenced later, what hosts may receive it, what happens on overwrite, redaction expectations, and the quota.

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?

Schema coverage is already 100%, but the description adds value beyond it: it ties `name` to the {{secret:NAME}} placeholder syntax and justifies the no-wildcard host rule (shared domains like workers.dev make wildcards unsafe), which the schema only asserts.

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?

States a specific verb and resource ("Store a credential") and goes further by explaining the reference mechanism ({{secret:NAME}}) and naming the four sibling tools that consume it. An agent can distinguish this from list_secrets/delete_secret immediately.

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?

Gives concrete usage context: place {{secret:NAME}} in a header value of schedule_http, create_cron, watch_http or set_wake, with a worked example. It also states the replace-on-same-name behavior. It stops short of routing to the secret-management siblings (list_secrets, delete_secret) for viewing or removal.

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

All Runlater tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?