MCP Setup

MemContext provides a hosted MCP server. You can connect with OAuth from any client that supports remote MCP sign-in (Claude.ai, Claude Desktop, ChatGPT, Claude Code, Codex CLI, Cursor, VS Code, OpenCode), or use an API key header in coding agents. Both work side by side.

Prerequisites

A MemContext account at app.memcontext.in
An API key if you are connecting a coding agent (create one under Settings > API Keys)

The MCP page in your dashboard has step-by-step OAuth instructions for each client (recommended) and an API-key section that generates ready-to-paste configs with your key pre-filled.

Claude.ai & Claude Desktop

Use this path when you want everyday Claude conversations to remember preferences, project context, and recurring details without editing config files. Step 1 - Open Connectors In Claude.ai or Claude Desktop, open Settings → Connectors. Step 2 - Add a custom connector Choose Add custom connector. Step 3 - Enter the production URL Use:

https://mcp.memcontext.in/mcp

Step 4 - Connect and approve access Click Connect, sign in to MemContext if prompted, then approve the requested scopes on the consent screen.

Recommended instructions

Paste this into Claude → Settings → Profile → Instructions for Claude:

- Search MemContext before assuming my preferences, projects, or past decisions.
- Save only stable preferences, recurring facts, and useful project context.
- Do not save one-off questions, random searches, or temporary details unless I ask you to remember them.
- Keep memory updates brief, accurate, and practical.

Claude.ai and Claude Desktop use OAuth for this flow. You do not need to paste API keys, headers, or config files.

Other clients with OAuth

Any client that supports MCP OAuth can connect with just the server URL, with no API key. The client discovers MemContext’s authorization server, opens a browser to sign in, and shows a consent screen with the client’s name and logo. Pick the workspace for the connection and approve.

https://mcp.memcontext.in/mcp

ChatGPT: add a custom connector (developer mode) with the URL above.
Claude Code: claude mcp add --transport http memcontext https://mcp.memcontext.in/mcp, then run /mcp to sign in.
Codex CLI: codex mcp add memcontext --url https://mcp.memcontext.in/mcp, then codex mcp login memcontext.
Cursor / VS Code / OpenCode: add the server with only the url (no headers). The client prompts you to sign in.

Connections stay signed in: clients receive refresh tokens and renew access automatically. Each connection is bound to the workspace you approved on the consent screen. To use a different workspace, connect again and pick it. To see or remove connected apps, open the MCP page in the dashboard and scroll to Active connections. It shows each app, when it was connected, and when it was last active. Disconnect signs the app out immediately. Workspace owners and admins can manage every member’s connections.

OAuth connections created before the MCP 2026-07-28 upgrade must be reconnected once. API-key setups are unaffected.

The sections below use API keys, which are useful for clients without OAuth support and for scripted setups.

Claude Code

Step 1 - Add the MCP server via CLI:

claude mcp add memcontext --scope user --transport http https://mcp.memcontext.in/mcp \
  --header "MEMCONTEXT-API-KEY:mc_your_key"

Or add this to ~/.claude.json:

{
  "mcpServers": {
    "memcontext": {
      "url": "https://mcp.memcontext.in/mcp",
      "headers": {
        "MEMCONTEXT-API-KEY": "mc_your_key"
      }
    }
  }
}

Step 2 - Add agent instructions to ~/.claude/CLAUDE.md:

# MemContext

At conversation start, ALWAYS call search_memory to load user context - do not skip.
Before making decisions or assumptions, search_memory to check for past context.
SAVE immediately (do not defer) when any of these happen:

- User shares a preference → save_memory(category: "preference")
- A technology or architecture decision is made → save_memory(category: "decision")
- User corrects you or says "remember" → save_memory(category: "fact")
- Important project fact learned → save_memory(category: "fact", project: "<known-project-name>")
- Significant work completed → save_memory(category: "context")
- MCP tools do not accept scope. Use the REST API or TypeScript SDK when an app needs hard per-user or per-tenant isolation.
- Use project only when a clear project/app name is already known. Good: "memcontext", "carq". Omit if unsure. Never invent vague names like "123" or "abc".
- MCP memories use automatic TTL. Use the REST API, TypeScript SDK, or dashboard when exact expiry is required.
- After using search results, call memory_feedback to rate memories as helpful/not_helpful/outdated/wrong.
- If a retrieved memory is wrong or outdated and you know the corrected fact, call update_memory with the corrected content. Feedback alone only changes retrieval ranking; update_memory changes the saved memory.
- Use delete_memory only when a memory was saved incorrectly and should be removed entirely.
- Duplicates are handled automatically - when in doubt, save.
- Memory persists across all sessions. Use project only for known project-specific context.

Cursor

Step 1 - Add this to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "memcontext": {
      "url": "https://mcp.memcontext.in/mcp",
      "headers": {
        "x-api-key": "mc_your_key"
      }
    }
  }
}

Step 2 - Add the agent instructions to Cursor Settings > Rules and commands > User Rules.

OpenCode

Step 1 - Add the MCP server to ~/.config/opencode/opencode.json:

{
  "mcp": {
    "memcontext": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mcp-remote",
        "https://mcp.memcontext.in/mcp",
        "--header",
        "MEMCONTEXT-API-KEY:mc_your_key"
      ],
      "enabled": true
    }
  }
}

Step 2 - Add the agent instructions to ~/.config/opencode/AGENTS.md.

Codex CLI

Step 1 - Add the MCP server to ~/.codex/config.toml:

[mcp_servers.memcontext]
url = "https://mcp.memcontext.in/mcp"

[mcp_servers.memcontext.http_headers]
MEMCONTEXT-API-KEY = "mc_your_key"

Step 2 - Add the agent instructions to ~/.codex/instructions.md.

Agent instructions

These instructions tell your AI assistant how and when to use MemContext. Add them to the preferences file for your client (listed above):

# MemContext

At conversation start, ALWAYS call search_memory to load user context - do not skip.
Before making decisions or assumptions, search_memory to check for past context.
SAVE immediately (do not defer) when any of these happen:

- User shares a preference → save_memory(category: "preference")
- A technology or architecture decision is made → save_memory(category: "decision")
- User corrects you or says "remember" → save_memory(category: "fact")
- Important project fact learned → save_memory(category: "fact", project: "<known-project-name>")
- Significant work completed → save_memory(category: "context")
- MCP tools do not accept scope. Use the REST API or TypeScript SDK when an app needs hard per-user or per-tenant isolation.
- Use project only when a clear project/app name is already known. Good: "memcontext", "carq". Omit if unsure. Never invent vague names like "123" or "abc".
- MCP memories use automatic TTL. Use the REST API, TypeScript SDK, or dashboard when exact expiry is required.
- After using search results, call memory_feedback to rate memories as helpful/not_helpful/outdated/wrong.
- If a retrieved memory is wrong or outdated and you know the corrected fact, call update_memory with the corrected content. Feedback alone only changes retrieval ranking; update_memory changes the saved memory.
- Use delete_memory only when a memory was saved incorrectly and should be removed entirely.
- Duplicates are handled automatically - when in doubt, save.
- Memory persists across all sessions. Use project only for known project-specific context.

Client	Preferences file
Claude Code	`~/.claude/CLAUDE.md`
Cursor	Cursor Settings > Rules and commands > User Rules
OpenCode	`~/.config/opencode/AGENTS.md`
Codex CLI	`~/.codex/instructions.md`

Available tools

Once connected, your assistant has access to five tools:

Tool	Purpose
`save_memory`	Persist preferences, facts, decisions, and context
`search_memory`	Find relevant memories before responding
`memory_feedback`	Rate memory quality after retrieval
`update_memory`	Correct or refine an existing saved memory
`delete_memory`	Remove a memory by ID

See the MCP Tools section for parameter documentation.

Verifying the connection

After setup, ask Claude or your coding assistant:

“Search your memory for any information about me.”

If the connection is working, it will call search_memory and return results (or an empty set if no memories exist yet).

Get Started

Concepts

Context Vault

Guides

SDK

API Reference

MCP Tools

Prerequisites

Claude.ai & Claude Desktop

Recommended instructions

Other clients with OAuth

Claude Code

Cursor

OpenCode

Codex CLI

Agent instructions

Available tools

Verifying the connection

​Prerequisites

​Claude.ai & Claude Desktop

​Recommended instructions

​Other clients with OAuth

​Claude Code

​Cursor

​OpenCode

​Codex CLI

​Agent instructions

​Available tools

​Verifying the connection

Prerequisites

Claude.ai & Claude Desktop

Recommended instructions

Other clients with OAuth

Claude Code

Cursor

OpenCode

Codex CLI

Agent instructions

Available tools

Verifying the connection