Skip to content
weside.aiweside docs

MCP server

The MCP server is how other AI tools meet your companion. The Model Context Protocol (MCP) is an open standard for connecting AI clients to external tools and data. weside speaks it, so a Claude Code session — or any MCP-compatible client — can adopt your companion’s identity, read and write its memories, and track its goals, instead of starting cold every time.

What it exposes

Section titled “What it exposes”

Connected to your weside account, the server lets a client act on the same companion state the app and CLI use:

  • Identity — get_companion_identity, list_companions, select_companion, get_council
  • Memory — search_memories (semantic), save_memory, list_memories
  • Goals — list_goals, save_goal, update_goal_status
  • Threads — list_threads, show_thread, delete_thread
  • Provider — show_provider, list_provider_presets, set_provider
  • Tools — discover_tools, execute_tool for actions your companion can perform

It’s the same API surface the CLI and the we plugin sit on top of — one companion, reachable from many places.

Connecting

Section titled “Connecting”

The server lives at https://api.weside.ai/mcp/ and authenticates through your weside.ai account. The simplest path is the we plugin, which wires it up during /we:setup. Any client that supports MCP — Claude Code, Claude Desktop, and others — can connect the same way.

What it’s for

Section titled “What it’s for”

Two patterns show up most:

  • Companion-aware skills — a Claude Code session that loads your companion’s identity and goals, so the work stays aligned with what you’re actually building.
  • Memory-backed context — pulling persistent memory into a tool that would otherwise forget everything between sessions.