Skip to main content
Just want to wire up an MCP client quickly? See For AI Agents for a 2-minute quickstart with all the major IDE configs in one place. This page is the deep-dive reference.
The Reflect MCP server exposes two tools — 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/mcp
Auth: 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 mcp add --transport http reflect https://api.starlight-search.com/mcp \
  --header "Authorization: Bearer rf_live_..."
Or add it manually to .claude/settings.json (project) or ~/.claude/settings.json (global): 
{
  "mcpServers": {
    "reflect": {
      "type": "http",
      "url": "https://api.starlight-search.com/mcp",
      "headers": {
        "Authorization": "Bearer rf_live_..."
      }
    }
  }
}
Verify it loaded: 
claude mcp list

​
Cursor

Open Settings → MCP (or ~/.cursor/mcp.json) and add: 
{
  "mcpServers": {
    "reflect": {
      "type": "http",
      "url": "https://api.starlight-search.com/mcp",
      "headers": {
        "Authorization": "Bearer rf_live_..."
      }
    }
  }
}
Restart Cursor. The tools appear in Agent mode automatically.

​
Windsurf

Open Settings → Cascade → MCP Servers and add a new server: 
{
  "reflect": {
    "serverUrl": "https://api.starlight-search.com/mcp",
    "headers": {
      "Authorization": "Bearer rf_live_..."
    }
  }
}

​
Cline / Continue / other MCP clients

Any client that supports streamable HTTP transport uses the same config pattern: 
{
  "mcpServers": {
    "reflect": {
      "type": "http",
      "url": "https://api.starlight-search.com/mcp",
      "headers": {
        "Authorization": "Bearer rf_live_..."
      }
    }
  }
}

​
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 the X-Project-Id header: 
{
  "headers": {
    "Authorization": "Bearer rf_live_...",
    "X-Project-Id": "my-project"
  }
}

​
Available tools

​
retrieve_memories

Search the memory store for lessons from prior tasks. Call this before starting non-trivial work.
ParameterTypeDefaultDescription
querystringrequiredNatural-language description of the task you are about to do
limitint5Max memories to return (up to 20)
lambda_float0.5Blend between semantic similarity (1.0) and Q-value / learned utility (0.0)
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.
ParameterTypeDefaultDescription
taskstringrequiredThe task the agent was executing (embedded for retrieval)
summarystringrequiredOne-line lesson from the run, written by you
guidancestringrequiredActionable guidance a future run should follow, written by you
result"pass" or "fail"requiredOutcome — drives the reward signal
key_mistakestringoptionalWhat went wrong (mainly meaningful on a fail)
correct_actionstringoptionalWhat the run should have done instead
applicable_toolslist[string]optionalTools, files, or areas this lesson applies to
retrieved_memory_idslist[string]optionalIDs from retrieve_memories — enables Q-value updates

​
Verify the connection

The health endpoint requires no auth: 
curl https://api.starlight-search.com/mcp/health
# {"status": "ok"}