{
  "markdown": "# Atlaso — remote MCP server\n\n**Atlaso is an AI memory layer: one shared, persistent memory across every AI tool you connect.**\n\nTell it once in one tool, and it's already there in the next. Atlaso recalls the\ncontext that matters before each turn and captures the durable facts after — your\ndecisions, your preferences, and where you left off.\n\nThis repository documents Atlaso's **hosted MCP server**. Atlaso is a managed\nservice, so there is nothing to self-host and no server code here — you connect\nto the endpoint below and authorize in your browser.\n\n- **Endpoint:** `https://mcp.atlaso.ai/mcp`\n- **Transport:** Streamable HTTP\n- **Auth:** OAuth 2.1 with dynamic client registration — your MCP client walks you\n  through it; there are no API keys to paste\n- **Website:** https://www.atlaso.ai\n- **Docs:** https://docs.atlaso.ai\n\n## Connect\n\nAny MCP client that supports remote servers can connect. Add\n`https://mcp.atlaso.ai/mcp` as a connector and authorize in the browser when\nprompted.\n\n**Claude Desktop / claude.ai** — Settings → Connectors → Add custom connector →\npaste the endpoint → Connect → authorize.\n\n**Cursor, VS Code, and other MCP clients** — add it as a remote MCP server:\n\n```json\n{\n  \"mcpServers\": {\n    \"atlaso\": {\n      \"url\": \"https://mcp.atlaso.ai/mcp\"\n    }\n  }\n}\n```\n\n**Terminal-based tools** (Claude Code, Codex, OpenCode, Antigravity) get a richer\nintegration than MCP alone — automatic recall before each turn and automatic\ncapture after, via hooks. One command sets all of them up:\n\n```bash\ncurl -fsSL https://atlaso.ai/install.sh | bash    # macOS / Linux\nirm https://atlaso.ai/install.ps1 | iex           # Windows\n```\n\nThat installs the `atlaso` CLI, links the machine (creating your account if you\ndon't have one), then asks which of your AI tools should share the memory.\n\n## Tools\n\n| Tool | What it does |\n| --- | --- |\n| `recall(query, limit=5)` | Search your memory for notes relevant to `query`. Returns a ranked list of `{id, content}`. Read-only. |\n| `remember(text, polarity)` | Save a durable note — a decision, preference, or gotcha. `polarity` is one of `positive`, `open`, `cautionary`, `negative`. Returns the new id. |\n| `recent(limit=10)` | List the most recent memories, newest first. Read-only. |\n| `forget(id)` | Permanently delete a memory by id. Destructive and not undoable. |\n| `status()` | Connection state, how many memories are stored and pending, and your memory health score. Read-only. |\n\nEvery recall carries a verdict on whether a memory is settled or contested, so\nthe model isn't acting on shaky context.\n\n## Memory scopes\n\nMemories are either **personal** (they follow you everywhere) or **project**\n(scoped to the repository or workspace you were in). Both are recalled\nautomatically in the right place — you don't manage scopes by hand.\n\n## Privacy\n\nSecrets are scrubbed before anything is stored. Data is encrypted in transit and\nat rest. Your memory is never used to train AI models and never sold. On the free\nplan it is never sent to any LLM at all. You can delete any single memory, or your\nwhole account, at any time.\n\n## Pricing\n\nFree for one device and one tool. Pro is **$10/month** for unlimited devices and\ntools sharing one memory, plus Ambient Memory, background enrichment, Ask your\nmemory, and JSON export. Build is **$25/month** and adds a developer memory API.\n\n## Registry\n\nListed in the official MCP Registry as `io.github.imashishkh21/atlaso`. The\n[`server.json`](./server.json) in this repository is the published manifest.\n\n---\n\nAtlaso is a product of Atlaso Labs Inc. This repository is documentation for the\nhosted service; the service itself is not open source.\n",
  "bytes": 3661,
  "sha": "2f0811f6325cebaf71066cd344a04b818cc4c9b2aa17c4d486f0d6079e278c28",
  "repo_slug": "atlaso-labs/mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_atlaso_mcp_552777a2/readme"
}