agentprofile MCP server
Commit Sep 12, 2026Syncs skills, credentials, and memory across different AI agents and tools using a single MCP URL.
Also known as everyai-com/agentprofile
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.1.0
- Last commit
- Sep 12, 2026
- License
- Apache-2.0
What is agentprofile MCP?
agentprofile syncs skills, credentials, and memory across different AI agents and tools using a single MCP URL.
Summary generated from the project's README
About agentprofile MCP server
agentprofile provides a unified identity for AI agents by syncing skills, credentials, and memory across different tools. It functions as a remote MCP server using Streamable HTTP, allowing users to maintain a consistent profile regardless of which client they use. This prevents the common issue where tools like Claude Code, Cursor, or Codex start with no context or shared knowledge.
Developers can connect via a single MCP URL using OAuth or a bearer token. The system is built on Cloudflare Workers and uses a dedicated Durable Object per user to manage data through a SQLite backend. Users can manage their information via a live dashboard or through a CLI that automates configuration for various MCP clients. The server exposes six specific tools including remember, recall, and forget to handle information exchange.
This solution is open source and can be self-hosted on a personal Cloudflare account. While the current phase focuses on memory and skills, the architecture supports future expansions like semantic recall and zero-knowledge credentials.
What you can do with it
- 1Automate client configurationUse a single command to automatically detect and configure all installed MCP clients on your machine.
- 2Self-host the identity layerDeploy the entire infrastructure to your own Cloudflare account to maintain control over your data.
Written from the project's README. Every use case is checked against a quote from it.
How to install agentprofile MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall agentprofile MCP in Claude Code
$ claude mcp add --transport http agentprofile https://agentprofile.everyai-com.workers.dev/mcpInstall agentprofile MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agentprofile": {
"url": "https://agentprofile.everyai-com.workers.dev/mcp"
}
}
}Install agentprofile MCP in VS Code
.vscode/mcp.json
{
"servers": {
"agentprofile": {
"type": "http",
"url": "https://agentprofile.everyai-com.workers.dev/mcp"
}
}
}Install agentprofile MCP in VS Code CLI
$ code --add-mcp '{"name":"agentprofile","type":"http","url":"https://agentprofile.everyai-com.workers.dev/mcp"}'Install agentprofile MCP in Codex
$ codex mcp add agentprofile --url https://agentprofile.everyai-com.workers.dev/mcpInstall agentprofile MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.agentprofile] url = "https://agentprofile.everyai-com.workers.dev/mcp"
Install agentprofile MCP in Gemini CLI
$ gemini mcp add -s user --transport http agentprofile https://agentprofile.everyai-com.workers.dev/mcpInstall agentprofile MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agentprofile": {
"url": "https://agentprofile.everyai-com.workers.dev/mcp",
"type": "http"
}
}
}Configuration
AGENTPROFILE_SERVERAGENTPROFILE_TOKEN
| Name | Description | |
|---|---|---|
| AGENTPROFILE_SERVER | — | |
| AGENTPROFILE_TOKEN | — |
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableeveryai-com/agentprofile is public and reachablegithub.com/everyai-com/agentprofile ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-09-12github.com/everyai-com/agentprofile ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubagentprofile
Your agent's identity, everywhere. One profile — skills, credentials, and memory — synced to every agent tool through a single MCP URL. Open source, zero-knowledge, and self-hostable on your own Cloudflare account.
Every AI tool you use — Claude Code, Cursor, Codex — starts from zero: its own skills, its own pasted API keys, its own amnesia. agentprofile gives them one shared brain.
Live now: hosted at https://agentprofile.everyai-com.workers.dev · dashboard at
/app
Connect (any MCP client)
The server is a remote MCP server (Streamable HTTP) — no install needed, just one URL:
https://agentprofile.everyai-com.workers.dev/mcp
It supports two ways to authenticate:
- OAuth (recommended) — clients that support MCP OAuth discover it automatically from the URL and show a consent screen.
- Bearer token — run
npx @magicteams_ai/agentprofileto get a token, or hitPOST /profiles.
claude mcp add --transport http agentprofile https://agentprofile.everyai-com.workers.dev/mcp
Or with a bearer token:
claude mcp add --transport http agentprofile https://agentprofile.everyai-com.workers.dev/mcp \
--header "Authorization: Bearer ap_…"
{
"mcpServers": {
"agentprofile": {
"url": "https://agentprofile.everyai-com.workers.dev/mcp",
"headers": { "Authorization": "Bearer ap_…" }
}
}
}
export AGENTPROFILE_TOKEN="ap_…"
codex mcp add agentprofile --url https://agentprofile.everyai-com.workers.dev/mcp --bearer-token-env-var AGENTPROFILE_TOKEN
Or, for a client that does OAuth discovery:
codex mcp add agentprofile --url https://agentprofile.everyai-com.workers.dev/mcp
{
"servers": {
"agentprofile": {
"type": "http",
"url": "https://agentprofile.everyai-com.workers.dev/mcp"
}
}
}
Or just run npx @magicteams_ai/agentprofile and it configures every client it finds.
60-second demo
npx @magicteams_ai/agentprofile
That creates an anonymous profile (no signup) on the hosted instance, auto-detects your installed MCP clients, and writes their config. Restart your tools, then:
- In Claude Code: "Remember that I prefer pnpm over npm."
- In Cursor: "What package manager do I prefer?"
It recalls it. That's your profile, everywhere.
What's in this repo (Phase 1)
This is the Phase 1 implementation from the master plan: a working end-to-end skeleton that syncs skills and memory across tools over MCP. Credentials (zero-knowledge), OAuth, semantic recall, and the skill registry land in later phases — see Roadmap.
| Path | What it is |
|---|---|
apps/worker |
The Cloudflare Worker: a remote MCP server backed by one Durable Object per profile (SQLite for memory, R2 for skill bundles), plus a landing page (/) and a live dashboard (/app) with real-time WebSocket sync. |
packages/cli |
The agentprofile CLI: instant-profile onboarding, client auto-config, doctor, skill add. |
Web UI
/— landing page with the one-command install and the pitch./app— live dashboard. Paste your token (or hit "Create new") and watch skills and memory update in real time: when any agent callsremember, the fact appears instantly over a WebSocket. Add or delete memories and skills right from the page./setup-prompt— the "set up with your agent" prompt: paste it into Claude Code or Cursor and your own agent installs and verifies agentprofile for you.
How it works
agent tool ──Streamable HTTP──▶ Worker ──idFromName(profileId)──▶ ProfileDO
(Claude Code / Cursor) /mcp per-user SQLite
• facts (memory)
• skills
- One Durable Object per user is the source of truth. It validates the profile's secret on every call and owns that profile's memory and skills.
- Bearer token =
ap_<profileId>.<secret>. TheprofileIdroutes to the DO; the DO verifies a SHA-256 hash of the secret. No central token table. - The MCP surface is 6 tools:
get_context,list_skills,get_skill,remember,recall,forget. Deliberately small — every description byte is paid on every client turn (pinned in tests).
Run it locally
npm install
npm run dev # starts the Worker on http://localhost:8787
In another terminal:
# point the CLI at your local server
AGENTPROFILE_SERVER=http://localhost:8787 npx @magicteams_ai/agentprofile
Run the tests and typecheck:
npm --workspace apps/worker run test
npm --workspace apps/worker run typecheck
Deploy your own (self-host)
agentprofile self-hosts on your own Cloudflare account — the free Workers tier covers personal use.
cd apps/worker
npx wrangler r2 bucket create agentprofile-bundles
npx wrangler deploy
# then set PUBLIC_BASE_URL to your deployed URL and connect with:
AGENTPROFILE_SERVER=https://agentprofile.<you>.workers.dev npx @magicteams_ai/agentprofile
Roadmap
- P1: MCP server + ProfileDO, 6 tools, memory + skills, instant-profile CLI, live dashboard. ✅
- P2: per-client grants + audit log with live enforcement + dashboard access panel ✅; MCP sessions (
Mcp-Session-Id) ✅; semantic recall via Workers AI embeddings (keyword fallback) ✅; pluggable memory providers (builtin default + Mem0 + Supermemory adapters,/memory-config) ✅; OAuth 2.0 + PKCE consent flow with discovery, dynamic registration, and consent screen ✅. - P3: zero-knowledge credentials (client-side E2E), JIT injection, approval flow.
- P4: one-click Deploy-to-Cloudflare, signed skill registry, format translators.
- P5: teams, SSO, hosted cloud.
See the full plan in docs/.
Contributing
Contributions are welcome under the DCO —
sign off commits with git commit -s. See SECURITY.md for
responsible disclosure.
License
Part of the everyai-com agent stack
Open-source infrastructure for local-first, governed AI agents:
- distillory — local-first memory engine that reasons at ingestion
- agent-ready — turn any app into an MCP server + API + CLI, safe by default
- primer — live business context injected into any agent
- plainsync — local-first Markdown workspace for humans + agents
- argus — cloud-native software verification with parallel browser testing
- mintly-alternative — self-hostable documentation layer for humans + AI agents
- talltrack — sales calls in, publishable content out
Built by Phanindra Reddy · magicteams.ai
agentprofile MCP questions
How do I add agentprofile MCP to Claude Code?
Run claude mcp add --transport http agentprofile https://agentprofile.everyai-com.workers.dev/mcp in your terminal. Add --scope user to make it available in every project.
How do I add agentprofile MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How do I connect agentprofile to my MCP client?
You can connect using a single URL via Streamable HTTP, or use the CLI command npx @magicteams_ai/agentprofile to automatically configure your installed clients.
Can I host this myself?
Yes, you can self-host agentprofile on your own Cloudflare account using the provided worker implementation.