retrieve_memories and create_memory — over the Model Context Protocol. Connect it to any MCP-capable agent or IDE and your AI assistant will automatically query past lessons before hard tasks and record new ones after each run.
MCP endpoint: https://api.starlight-search.com/mcpAuth:
Authorization: Bearer <your-api-key>Transport: Streamable HTTP Get your API key from the Reflect console.
Claude Code
Add the server to your project or global config:.claude/settings.json (project) or ~/.claude/settings.json (global):
Cursor
Open Settings → MCP (or~/.cursor/mcp.json) and add:
Windsurf
Open Settings → Cascade → MCP Servers and add a new server:Cline / Continue / other MCP clients
Any client that supports streamable HTTP transport uses the same config pattern:Per-project scoping with X-Project-Id
By default the server uses the project ID configured on your API key. To scope memories to a specific project per-request, pass theX-Project-Id header:
Available tools
retrieve_memories
Search the memory store for lessons from prior tasks. Call this before starting non-trivial work.
Returns a list of memories with
id, task, reflection, q_value, similarity, score, and success. Save the memory_ids — you’ll pass them to create_memory.
create_memory
Persist a memory the agent writes itself. You author the reflection (summary + guidance) from what you just did and submit it with a pass/fail result — Reflect stores it directly, with no trajectory and no background model. Call this after the user confirms success or gives corrective feedback.