Relay

Cross-AI memory sync for coding tools.

CommunityOnlineAPI key requiredGlobalFreeRead-only

What it can do

  • List Projects: List all Relay projects you have access to. Returns project IDs, names, slugs, routing keywords, and which project is currently active for this MCP session. Do not call this before the
  • Set Current Project: Switch the current Relay project for this token. Use this when the user is clearly working on a different project than the cached one. The switch persists across future MCP calls
  • Get Brief: Fetch a project context brief from Relay. This is the default session-start tool. - If projectId is omitted, Relay first tries the cached or token-scoped project. - If that fails, Relay res

What data it sees

Do you need an account

An API key from the service settings is required

Cross-AI memory sync for coding tools. Relay keeps project context — decisions, progress, constraints, and notes - synchronized across ChatGPT, Claude, Cursor, Codex, and other AI assistants. Capture conversations from any AI tool on the web and with agents, then access unified project memory via MCP. Tools include project briefs, memory search, context saving, and structured state management. Set up in one command with npx @onrelay/wizard.

How to connect

How to connect Relay to Claude

The server address to paste into Claude settings:

https://relay--onrelay.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Relay to ChatGPT

The server address to paste into ChatGPT settings:

https://relay--onrelay.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Relay to Cursor

The server address to paste into Cursor settings:

https://relay--onrelay.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (6)

Raw names from tools/list. Only developers need these.

list_projectsList all Relay projects you have access to. Returns project IDs, names, slugs, routing keywords, and which project is currently active for this MCP session. Do not call this before the first get_brief unless Relay explicitly reports project ambiguity or resolves to the wrong project.
set_current_projectSwitch the current Relay project for this token. Use this when the user is clearly working on a different project than the cached one. The switch persists across future MCP calls with the same token. Call list_projects first to find the correct projectId.
get_briefFetch a project context brief from Relay. This is the default session-start tool. - If projectId is omitted, Relay first tries the cached or token-scoped project. - If that fails, Relay resolves the project only when there is a single obvious candidate. - Only call list_projects and set_current_project if get_brief reports ambiguity or the wrong project.
recallUnified read tool — replaces recall_context, search_context, get_project_state, list_memory, get_memory, list_sessions, list_recent_activity, trace_context_sources, and list_briefs. - No params → project state overview - query → hybrid search + project state - memoryId → single item detail - include: ["sessions"] → list sessions - include: ["activity"] → recent activity - include: ["briefs"] → list briefs - tracePhrase → trace provenance of a phrase - filters → filter memory listing by type/tags/pinned/archived If returned context is stale, completed, contradicted, or superseded, clean it up with save action: "manage_memory" or correct project state with save action: "set_state".
saveUnified write tool — replaces save_context, checkpoint_context, add_memory, manage_memory, set_project_state, update_project, archive_session, regenerate_brief, and delete_brief. Actions: save_session, checkpoint, add_memory, manage_memory, set_state, update_project, archive_session, regenerate_brief, delete_brief. Pass action-specific fields in payload. Use manage_memory whenever get_brief or recall shows stale, completed, contradicted, or superseded context.
sourcesProject-governed source lifecycle for Relay docs and repository sources. Use resolve to find evidence-backed source candidates, index to add URLs, search/read/explore/grep/context_pack to retrieve citations, import to store external Context7/Nia citations, refresh to update indexed sources, and promote only when the user wants a citation saved into durable memory.