runelay
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | Where the server listens (`0.0.0.0` in Docker). | 0.0.0.0 |
| PORT | No | Where the server listens. | 4312 |
| PUBLIC_URL | No | Public URL of the panel and API. Used for OAuth callbacks and cookies. | http://localhost:4312 |
| ALLOW_SIGNUP | No | Keep signups open after the first account. | false |
| RUNELAY_DATA | No | Where the SQLite database lives (`/data` in Docker). | /data |
| RUNELAY_SECRET | Yes | Required, 32+ chars. Encrypts connection configs, OAuth tokens and recoverable API keys. Losing it means reconnecting everything. | |
| GITHUB_CLIENT_ID | No | Enables "Sign in with GitHub" on the panel. | |
| RUNELAY_SETUP_TOKEN | No | One-time token required to create the first account (generated if not set). | |
| RUNELAY_UPDATER_URL | No | Where the updater listens (set by `compose.yaml`). | |
| GITHUB_CLIENT_SECRET | No | Enables "Sign in with GitHub" on the panel. | |
| RUNELAY_ENABLE_STDIO | No | Enables local MCP servers by command. | false |
| RUNELAY_UPDATER_TOKEN | No | Shared with the `updater` container. Owners and admins can then update from the panel (generated if not set). | |
| RUNELAY_ENABLE_EXECUTE | No | Enables the sandboxed `execute` tool. | true |
| RUNELAY_ALLOW_PRIVATE_URLS | No | Allows connections to private network addresses. | false |
| RUNELAY_RATE_LIMIT_PER_MINUTE | No | Requests per minute allowed for each API key. | 240 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
runelay aggregates every account the user connected and the user's memories and skills. Use search_tools to find tools (named source.tool), then call_tool for one call or execute to chain several calls in JavaScript. If a source shows needs_auth, tell the user to reconnect it in the runelay dashboard. Before acting on a topic, use search_context, then read_memory or read_skill for details; save new facts with write_memory. The user's golden rules follow and always apply.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_connectionsA | List every connected source with status, tool count and the link to reconnect it. |
| search_toolsB | Search tools across all connected sources. Returns full input schemas when 10 or fewer match. An empty query lists every tool. |
| call_toolC | Call one tool by its full name (source.tool) with arguments. |
| executeA | Run an async JavaScript snippet that chains tools across sources. Each tool is |
| search_contextB | Full-text search across the user's memories and skills. Returns slug, name, description and a snippet, best match first. |
| read_memoryA | Read one memory by slug, with its body, links and backlinks. |
| write_memoryB | Create or update a memory by slug. Updating keeps the previous content as a version. Link other memories with [[slug]] in the body. |
| read_skillB | Read one skill by slug: its full instructions and the list of extra files. |
| read_skill_fileC | Read one extra file of a skill by its path. |
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 9 tools
The tools mostly target distinct areas: tool discovery/execution, connection listing, memory, and skills. call_tool and execute overlap slightly because both can invoke tools, and search_tools with an empty query overlaps with list_connections, but the descriptions make the intended distinctions clear enough.
Almost all tools follow a consistent snake_case verb_noun pattern such as call_tool, list_connections, read_memory, search_tools, and write_memory. execute is the only notable deviation as a bare verb, but the overall convention remains predictable.
Nine tools is well scoped for an agent runtime covering tool discovery, execution, memory, and skills. Each tool has a clear role without excessive surface area.
The set covers core workflows: discovering and calling tools, executing chained calls, managing memories, and reading skills. Minor gaps exist, such as no delete_memory or explicit list_memories/list_skills operations, but agents can mostly work around these with search and read tools.