{
  "markdown": "# Tabula MCP Server\n\nOne memory. Every AI.\n\n[Tabula](https://www.tabula360.com) is a shared memory layer for your AIs. Tell Claude once, and ChatGPT already knows. Connected AIs save the durable facts you share (who you are, what you're building, how you like to work) and recall them in any other AI, so you never re-explain yourself.\n\nThis repo documents Tabula's hosted MCP server and how to connect it from any MCP client.\n\n## Endpoint\n\n|             |                                              |\n| ----------- | -------------------------------------------- |\n| URL         | `https://www.tabula360.com/api/mcp/mcp`      |\n| Transport   | Streamable HTTP                              |\n| Auth        | OAuth 2.1 (web clients) or Bearer token (CLIs and IDEs) |\n\nSign up at [tabula360.com](https://www.tabula360.com), then get your access token on the [Connect page](https://www.tabula360.com/connect). The token is shown once, treat it like a password.\n\n## Tools\n\n| Tool            | What it does                                        |\n| --------------- | --------------------------------------------------- |\n| `save_memory`   | Save a durable fact, preference, or decision        |\n| `search_memory` | Semantic search across everything saved             |\n| `list_memories` | Browse saved memories                               |\n| `update_memory` | Correct or refresh an existing memory               |\n| `delete_memory` | Remove a memory for good                            |\n\n## Connect\n\n### ChatGPT, Claude, Mistral, Grok, Perplexity, Manus\n\nWeb clients connect as a custom connector with OAuth. Follow the step-by-step [guide](https://www.tabula360.com/guide).\n\n### Claude Code\n\n```bash\nclaude mcp add --transport http tabula \\\n  https://www.tabula360.com/api/mcp/mcp \\\n  --header \"Authorization: Bearer YOUR_TOKEN\"\n```\n\n### Cursor\n\nAdd to `~/.cursor/mcp.json` (or `.cursor/mcp.json` in a project):\n\n```json\n{\n  \"mcpServers\": {\n    \"tabula\": {\n      \"url\": \"https://www.tabula360.com/api/mcp/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer ${env:TABULA_MCP_TOKEN}\"\n      }\n    }\n  }\n}\n```\n\n### VS Code\n\nAdd to `.vscode/mcp.json`. VS Code uses `servers` and prompts for the token via `inputs`:\n\n```json\n{\n  \"servers\": {\n    \"tabula\": {\n      \"type\": \"http\",\n      \"url\": \"https://www.tabula360.com/api/mcp/mcp\",\n      \"headers\": { \"Authorization\": \"Bearer ${input:tabula-token}\" }\n    }\n  },\n  \"inputs\": [\n    { \"type\": \"promptString\", \"id\": \"tabula-token\", \"description\": \"Tabula token\", \"password\": true }\n  ]\n}\n```\n\n### Windsurf\n\nAdd to `~/.codeium/windsurf/mcp_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"tabula\": {\n      \"serverUrl\": \"https://www.tabula360.com/api/mcp/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer ${env:TABULA_MCP_TOKEN}\"\n      }\n    }\n  }\n}\n```\n\n### Codex CLI\n\nAdd to `~/.codex/config.toml`:\n\n```toml\n[mcp_servers.tabula]\nurl = \"https://www.tabula360.com/api/mcp/mcp\"\nbearer_token_env_var = \"TABULA_MCP_TOKEN\"\n```\n\n### Mistral Vibe CLI\n\nAdd to `~/.vibe/config.toml`, with `TABULA_MCP_TOKEN` in `~/.vibe/.env`:\n\n```toml\n[[mcp_servers]]\nname = \"tabula\"\ntransport = \"http\"\nurl = \"https://www.tabula360.com/api/mcp/mcp\"\n\n[mcp_servers.auth]\ntype = \"static\"\napi_key_env = \"TABULA_MCP_TOKEN\"\n```\n\n### Your own code (OpenRouter or any OpenAI-compatible API)\n\nGive a plain API script persistent memory with the standard tool-calling loop. A complete single-file example lives in [`examples/openrouter-memory`](examples/openrouter-memory): it fetches Tabula's tools over MCP, hands them to the model, and executes the calls.\n\n## What to expect\n\nAsking always works: say \"Save that to Tabula\" or \"Ask Tabula\" and any model will call the right tool. Fully automatic saving and recall depends on the model and the client, because MCP offers tools, it cannot force a call.\n\nTo make recall automatic in clients with a system prompt or custom instructions, add this line:\n\n```text\nAlways check Tabula before answering anything about me, my work, or my projects, even if you think you already know.\n```\n\nThe [guide](https://www.tabula360.com/guide) has the per-platform version of this for ChatGPT, Claude, Mistral, and the rest.\n\n## Privacy\n\nMemories are isolated per account with row-level security, and never sold or shared. You can view, edit, export, or delete everything at any time. [Privacy policy](https://www.tabula360.com/privacy).\n\n## Pricing\n\nFree during beta, no card required.\n\n## Links\n\n- [Website](https://www.tabula360.com)\n- [Setup guide](https://www.tabula360.com/guide)\n- [Blog](https://www.tabula360.com/blog)\n- [Manifesto](https://www.tabula360.com/manifesto)\n",
  "bytes": 4630,
  "sha": "4f711ffb575a5e0217ee672030d4f533d39ec513e75beb90dbe1db791c4bb599",
  "repo_slug": "nikhilbhima/tabula-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_nikhilbhima_tabula_d3445178/readme"
}