About UseMyContext.ai
UseMyContext.ai stores a user-curated profile and files for AI tools to access through MCP. It supports separate projects and sharing, while requiring approval before AI-suggested updates are applied.
Key features
- 01Maintain profiles and files by project
- 02Require approval for suggested updates
- 03Share a project's curated profile
- 04Review access in an activity feed
- 05Revoke AI access from one page
Use cases
- 01Provide personal context across AI tools
- 02Keep separate context for different projects
- 03Share selected project context with another person
- 04Review and revoke AI access
MCP support
Exposes profiles and files to MCP clients through a Streamable HTTP server with browser-based OAuth. AI-suggested changes remain pending until approved.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.usemycontext.ai/mcpclaude mcp add --transport http usemycontext-usemycontext https://mcp.usemycontext.ai/mcp{"mcpServers":{"usemycontext-usemycontext":{"type":"http","url":"https://mcp.usemycontext.ai/mcp"}}}Open in Cursor{"servers":{"usemycontext-usemycontext":{"type":"http","url":"https://mcp.usemycontext.ai/mcp"}}}Open in VS Code{"mcpServers":{"usemycontext-usemycontext":{"type":"http","url":"https://mcp.usemycontext.ai/mcp"}}}{"mcpServers":{"usemycontext-usemycontext":{"serverUrl":"https://mcp.usemycontext.ai/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
13| Parameter | Type | Required | Description |
|---|---|---|---|
| handle | string | No | Optional: name one of the user's OWN profiles by its public @handle (with or without the leading @), as listed by list_profiles - an alternative to projectId, and it takes precedence if both are given. Honored only for an account-wide connection; a single-project connection is already scoped and ignores it. A handle that is not one of the user's own profiles is refused outright, never quietly swapped for another profile. To read context someone ELSE shared with the user or published, use shared_context instead. |
| projectId | string | No | Optional: which of the user's profiles (projects) to read - a projectId from list_profiles. Honored only for an account-wide connection; a single-project connection is already scoped and ignores this. |
Details
From the project READMEUseMyContext
Your personal context for every AI. Keep one profile of who you are and what you are working on, plus the files that matter, at usemycontext.ai, and the AI you use reads it over MCP. You approve every update: an AI can only suggest a change, and nothing lands until you say yes.
One-click install
- ChatGPT: Install in ChatGPT, then sign in with your email and the code we send.
- Claude: Open in the Claude Directory and click Connect.
Coding tools
- Claude Code:
/plugin marketplace add usemycontext/claude-code-plugin, then/plugin install usemycontext@usemycontext(plugin) - Cursor: add the server below to
~/.cursor/mcp.json(plugin) - OpenCode: a
remoteserver inopencode.json(plugin) - Gemini CLI:
gemini extensions install https://github.com/usemycontext/gemini-cli-extension
For tools that read a file at startup instead of speaking MCP, npx usemycontext pull writes your
curated profile to a local UMC-CONTEXT.md (how it works).
It uses a long-lived token from the Connect page: treat it like a password, and "Disconnect
everything" on that page revokes it on the server.
Any other MCP client: add https://mcp.usemycontext.ai/mcp (Streamable HTTP). Sign-in is OAuth in
the browser, no API key to copy. Every client step is in the docs.
What you get
- Projects with their own @handle. Each project has its own profile, facts and files, and a permanent @handle any AI can use to address it, private or public.
- Share My Context. Share one project's curated profile with someone else, and revoke it any time.
- You stay in control. AI access leaves a record in your activity feed, and you can revoke any AI from one page; revoking is enforced on the server.
Plans
| Plan | Projects | Storage per project |
|---|---|---|
| Free | 2 | 20MB |
| Premium, $20/month | 10 | 100MB |
Try it first, no signup: sign in at usemycontext.ai as
[email protected] with code 424242, a shared, read-only demo account.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.