SaSameFor people and AI systems
SaSame · MCP-native AI execution

SaSame

Connect AI. Choose capabilities. Let it work through MCP. Review what happened.

SaSame lets people and AI agents connect an AI, choose the capabilities it may use, let it work through MCP, and review the result and usage. The Factory, Observatory, router, Account Control, CLI and website are supporting parts of one service, not separate products.

ConsoleLive · measured 505h agoObservatory
01
82
records
02
337
relations
03
2026-08-24
updated
04
94
tools online
05
39,986
servers observed
06
2,878
observed-ready
LV

Try it live, no LLM involved

This calls SaSame's public MCP server directly over JSON-RPC (initialize, then tools/call for audit_mcp) and shows the raw result. No chatbot in the loop, no API key required.

02 · All collections

Explore SaSame

Top-level collections are data-driven. Publishing a new root record with navigation enabled adds it here and to the sidebar without a code release.

Historical records

Mission Archive

Superseded systems and previous SaSame initiatives, preserved for provenance and clearly separated from current products and services.

03 · Lifecycle

How SaSame works

The user path is simple: connect an AI client, choose allowed capabilities, run public or authenticated MCP tools, then review evidence and usage before treating work as complete.

  1. 01

    Connect

    Add SaSame to ChatGPT, Claude, Claude Code or another MCP client.

  2. 02

    Choose

    Select which capabilities, Missions and account actions the AI may use.

  3. 03

    Work

    Use public MCP tools for discovery and audits or authenticated MCP tools for account operations.

  4. 04

    Review

    Check usage, evidence, drafts, exports and outcome state.