MCP tools
The tools runelay exposes to every agent at /v1/mcp.
| Tool | What it does |
|---|---|
list_connections | Every connection with status and tool count. |
search_tools | Search tools across all connections (source.tool). |
call_tool | Call one tool with arguments. |
execute | Run JavaScript that chains tools inside a WebAssembly sandbox. |
search_context | Full-text search across memories and skills. |
read_memory / write_memory | Read a memory, or create and update one (versioned). |
read_skill / read_skill_file | Read a skill and its files. |
execute
execute lets an agent chain several calls in one round trip:
await tools.linear.list_issues({...})Code runs in QuickJS compiled to WebAssembly: a fresh sandbox per run with no filesystem, network, process or timers, 32 MB of memory and CPU and wall-clock limits. Tools cross the boundary as JSON only. Turn it off with RUNELAY_ENABLE_EXECUTE=false if you only want single call_tool calls.
Agents never receive credentials: list_connections shows headers and env values as ••••••.