Timepoint MCP
OfficialSupports Apple IAP (In-App Purchase) for billing and payment processing through the Timepoint Billing service, enabling subscription management for Timepoint AI services.
Used for deployment of the MCP server via Docker containers on Railway, providing containerized runtime environment for the Timepoint AI service infrastructure.
Hosts the open source repositories for Timepoint AI services including Flash, Clockchain, Pro, Proteus, TDF, SNAG Bench, and the MCP server itself.
Supports Google OAuth authentication through the Timepoint API Gateway, enabling user authentication and access control for Timepoint AI services.
Provides iOS client application (timepoint-iphone-app) for accessing Timepoint AI services, enabling synthetic time travel and historical exploration on mobile devices.
Serves as the primary database for the MCP server, storing API keys, usage logs, and operational data for the Timepoint AI platform.
Primary implementation language for the MCP server and associated Timepoint AI services including Flash, Clockchain, Pro, and TDF, using FastMCP and Starlette frameworks.
Hosting and deployment platform for the MCP server, providing Docker-based infrastructure for running the Timepoint AI MCP service in production.
Payment processing integration through the Timepoint Billing service, handling subscription payments, credit purchases, and financial transactions for Timepoint AI services.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Timepoint MCPSearch for key moments in the French Revolution and let me chat with a citizen"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
timepoint-mcp
MCP server for the Timepoint AI temporal knowledge platform.
Live at: mcp.timepointai.com
What is this?
A hosted Model Context Protocol server that gives AI agents structured access to the Timepoint ecosystem:
Search & browse a causal graph of 3,900+ historical moments and 5M+ edges spanning 700 BCE to 2026
Generate timepoints — rich historical scenes with narratives, characters, dialog, and AI images (Phase 2 — in development)
Navigate time — step forward/backward from any moment to discover what came before and after (Phase 2 — in development)
Chat with historical characters — in-context conversations with period-appropriate personalities (Phase 2 — in development)
Run simulations — multi-entity temporal scenarios via the SNAG engine (Phase 3 — planned)
Works with Claude Desktop, Cursor, Windsurf, VS Code Copilot, the Anthropic Agent SDK, and any MCP-compatible client.
Get an API key
Visit timepointai.com or reach out on X @timepointai to request access.
Clockchain read tools (search, browse, moment detail) work without authentication at 30 req/min. Generation and simulation tools require an API key and credits.
Quick start
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"timepoint": {
"url": "https://mcp.timepointai.com/mcp",
"headers": {
"X-API-Key": "tp_mcp_..."
}
}
}
}Cursor / Windsurf
Add to .cursor/mcp.json or equivalent:
{
"mcpServers": {
"timepoint": {
"url": "https://mcp.timepointai.com/mcp",
"headers": {
"X-API-Key": "tp_mcp_..."
}
}
}
}Anthropic Agent SDK
from claude_agent_sdk import Agent
from claude_agent_sdk.mcp import MCPServerRemote
agent = Agent(
model="claude-sonnet-4-6",
mcp_servers=[
MCPServerRemote(
url="https://mcp.timepointai.com/mcp",
headers={"X-API-Key": "tp_mcp_..."},
)
],
)
result = agent.run("What happened in Rome in 44 BC?")Local development
git clone https://github.com/timepointai/timepoint-mcp.git
cd timepoint-mcp
pip install -e .
# stdio transport (for Claude Desktop local)
python -m app.server --transport stdio
# HTTP transport (for remote testing)
python -m app.server --transport http --port 8000Available tools
Phase 1 (live now) — Clockchain read tools
Tool | Auth | Description |
| Optional | Search the temporal causal graph for historical events |
| Optional | Get full detail for a historical moment by its canonical path |
| Optional | Browse the graph hierarchy — year, month, day, location, event |
| Optional | Get causal/thematic connections: what caused this, what it caused |
| Key | Events that happened on today's date across all eras |
| Key | Random historical moment for serendipitous discovery |
| Optional | Node/edge counts, date range, source distribution |
Phase 2 (coming soon) — Generation tools
Tool | Credits | Description |
| 5-10 | Generate a historical timepoint with scene, characters, dialog, image |
| 2 | Step forward/backward in time from an existing timepoint |
| 1 | Converse with a historical character in context |
| 0 | Retrieve a previously generated timepoint |
| 0 | List your generated timepoints |
| 0 | Check credits and usage |
Phase 3 (planned) — Simulation tools
Tool | Credits | Description |
| 10 | Run a SNAG temporal simulation |
| 0 | Get simulation results |
Pricing
Tier | Price | Monthly Credits | Rate Limit |
Anonymous | Free | — | 30 req/min (read-only) |
Free | Free | 5 signup credits | 60 req/min |
Explorer | $7.99/mo | 100 | 60 req/min |
Creator | $19.99/mo | 300 | 300 req/min |
Studio | $49.99/mo | 1,000 | 1,000 req/min |
Credit packs also available as one-time purchases.
HTTP endpoints
In addition to the MCP protocol at /mcp, the server exposes:
Method | Path | Description |
GET |
| Landing page (JSON for agents, redirect for browsers) |
GET |
| Service health check |
GET |
| Auth status and tier info |
POST |
| Create API key (requires admin key) |
Architecture
MCP Clients (Claude Desktop, Cursor, agents, SDKs)
|
| Streamable HTTP + X-API-Key
v
timepoint-mcp (mcp.timepointai.com)
FastMCP + Starlette + asyncpg
|
-----+------+----------+
| | |
v v v
Clockchain Flash Billing
(graph) (writer) (Stripe/IAP)The MCP server is a thin coordination layer. It authenticates requests via API keys, resolves user tiers via Billing, checks credit balance via the Gateway, routes tool calls to the appropriate backend, and enforces per-tier rate limits. It never stores credits or subscriptions — the Gateway and Billing own those.
Tech stack
Python 3.11+ with FastMCP, Starlette, httpx, asyncpg
Transport: Streamable HTTP (production), stdio (local dev)
Database: PostgreSQL (API keys + usage logs)
Deployment: Railway (Docker)
Environment variables
# Downstream services
FLASH_URL=https://api.timepointai.com
FLASH_OUTBOUND_KEY=... # key sent to Flash as X-Service-Key (was FLASH_SERVICE_KEY)
FLASH_ADMIN_KEY=...
CLOCKCHAIN_URL=...
CLOCKCHAIN_SERVICE_KEY=...
BILLING_URL=...
BILLING_SERVICE_KEY=...
# Database
DATABASE_URL=postgresql://...
# Server
PORT=8000Timepoint Suite
Render the past. Simulate the future. Score the predictions. Accumulate the graph.
Service | Type | Repo | Role |
API Gateway | Private | timepoint-api-gateway | Auth authority — JWT, OAuth (Apple/Google/GitHub), credits, rate limiting at api.timepointai.com |
Flash | Open Source | timepoint-flash | Reality Writer — pure generation engine (no auth), renders grounded historical moments |
Clockchain | Open Source | timepoint-clockchain | Temporal Causal Graph — 3,900+ nodes, 5M+ edges, MCP endpoint, growing 24/7 |
Pro | Open Source | timepoint-pro | SNAG Simulation Engine — temporal simulation, TDF output, training data |
Proteus | Open Source | proteus | Settlement Layer — prediction markets for Rendered Futures |
TDF | Open Source | timepoint-tdf | Data Format — JSON-LD interchange across all services |
SNAG Bench | Open Source | timepoint-snag-bench | Quality Certifier — measures Causal Resolution across renderings |
Billing | Private | timepoint-billing | Payment Processing — Apple IAP + Stripe |
MCP | Public | timepoint-mcp | MCP Server — AI agent access to Flash and Clockchain |
Web App | Private | timepoint-web-app | Browser client at app.timepointai.com |
Landing | Private | timepoint-landing | Marketing site at timepointai.com |
iPhone App | Private | timepoint-iphone-app | iOS client — Synthetic Time Travel on mobile |
Skip Meetings | Private | skipmeetingsai | Meeting intelligence SaaS powered by Flash |
License
Proprietary. Copyright 2026 Timepoint AI.
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/timepointai/timepoint-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server