Skip to main content
V3Code’s Context Bridge isn’t locked inside its own chat. You can expose the same structural tools — symbol context, call graphs, dependencies, notes, semantic search — to any agent that speaks MCP, over a single endpoint.

​
Why do this

It turns V3Code into an intelligence layer for whatever agent you already use. Point Claude Code or Cursor at the endpoint and they get the same LSP-backed view of your codebase that V3Code’s own agent has — structure and relationships, not just text.

​
How it works

V3Code serves a curated set of tools over one MCP endpoint. Any MCP client you configure can call them in-process against your local project. What’s exposed:
  • Structural reads — get_symbol_context, get_call_graph, get_file_context, get_file_dependencies, pack_context, get_project_briefing, semantic_search, find_text.
  • Memory & recall — list_notes, search_notes, deep_recall, get_shadow_record, workspace_delta, recent_edits, session_diff, index_health, plus write-side remember / forget.
  • Handy composites — orient (a briefing + index health in one call), run_subagent (a read-only subagent on your own key), and send_chat / get_chat to drive and read your live V3Code chat.
Editing, terminal, and git-write tools are deliberately not exposed over the endpoint — external agents get V3Code’s intelligence, not the keys to your filesystem.