# Cursor + CoreStory

Connect Cursor to the CoreStory MCP server so project plans and code changes can use persistent code intelligence.

## Before you connect

- Use the MCP endpoint and authentication method shown in your CoreStory account or onboarding material. Do not copy tokens into source files, prompts, or chat.

- Confirm the target project is ingested and that your identity is authorized to read it.

- Treat tool discovery as authoritative: available tool names and parameters may change as the service evolves.

## Procedure

1. In Cursor's current MCP settings, add a remote HTTP server named `corestory`. Use the endpoint and credential reference issued by CoreStory.

2. Reload Cursor and inspect the live CoreStory tool list.

3. Call `list_projects`, select the project explicitly, then retrieve the relevant document sections or semantic results.

4. Require the agent to separate CoreStory evidence, local code observations, and inference in its answer.

## Validation

- The MCP client reports a connected `corestory` server.

- `list_projects` returns only projects your identity should access.

- A project-document or semantic query returns evidence from the expected project.

- The agent cites retrieved context in its plan or answer and distinguishes retrieved facts from inference.

## Failure handling

- For authentication errors, create or rotate credentials through the product workflow; never print a token to diagnose it.

- For missing data, verify project identity and ingestion state before changing the prompt.

- If the advertised tools differ from this guide, use the server's live tool schema and report the documentation drift.