RestoSignals MCP Server
by paperandbeyond23-gifcom.restosignals/restosignalsv1.0.0
Pre-opening US restaurant and bar leads, scored from liquor, permit and business filings.
context tax
~478 tok/turn4 tools
security
pending
cold start
hosted
freshness
pending
Our reading of RestoSignals, from the data
RestoSignals is an MCP server from paperandbeyond23-gif, listed in the official MCP Registry.
Its 4 tools add about 478 tokens to every model turn (measured 2026-10-19).
It runs as a hosted endpoint, so there is nothing to install.
Install RestoSignals MCP server
Install in Claude Code
claude mcp add --transport http restosignals https://api.restosignals.com/mcpInstall in Cursor
{
"mcpServers": {
"restosignals": {
"url": "https://api.restosignals.com/mcp"
}
}
}Install in Claude Desktop
{
"mcpServers": {
"restosignals": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://api.restosignals.com/mcp"
]
}
}
}Or add it as a custom connector under Settings → Connectors. The config above bridges via mcp-remote.
Install in VS Code
{
"servers": {
"restosignals": {
"type": "http",
"url": "https://api.restosignals.com/mcp"
}
}
}Install in Windsurf
{
"mcpServers": {
"restosignals": {
"serverUrl": "https://api.restosignals.com/mcp"
}
}
}Remote endpoints
- streamable-http
https://api.restosignals.com/mcp
Context tax
Connecting this server adds ~478 tokens of tool definitions to every model turn (lean, 4 tools). Measured 2026-10-19 via its hosted endpoint; o200k tokenizer, worst case for clients that load all tools up front. How we measure
| Model | Per 1,000 turns | With prompt caching |
|---|---|---|
| Claude Opus 5.5 | $1.91 | $0.096 |
| Claude Sonnet 5.5 | $0.956 | $0.096 |
| Claude Haiku 5.5 | $0.048 | — |
Input prices as of 2026-10-06. Excludes your own prompt and output.
Tools (4)
new_openings232 tokFind restaurants/bars about to open in a state, ranked by opening_score (0-100). Fuses liquor licenses, food permits and new-business filings into one scored venue. signal_types on each lead are 'liquor', 'food_permit' and 'business'. Live states: NY, TX, IL, OR, CO, WA, CA (call `coverage` for the current list). 1 credit per returned lead.
watch_area97 tokRegister a webhook that fires when a new matching venue opens in an area. criteria = {state, city, signal_type, min_opening_score}. Free.
coverage77 tokList the states RestoSignals currently has data for and how many scored venues each holds (with a count of hot leads, opening_score >= 80). Call this FIRST to see live inventory before new_openings — querying a state with no data returns nothing. Free (0 credits).
venue_signals71 tokReturn the raw underlying signals (liquor/permit/business filings) that were fused into one venue, for transparency. 1 credit.
Freshness
Not enough public signals yet to judge maintenance.
Last commit (default branch)
2026-10-17 · 1d ago · GitHub
Latest release
no data · GitHub
Package published
no data · npm/PyPI
Registry entry updated
2026-10-17 · 1d ago · official registry · v1.0.0
FAQ
›How do I install the RestoSignals MCP server in Claude Code?
Run: claude mcp add --transport http restosignals https://api.restosignals.com/mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.
›Does RestoSignals require an API key?
No required environment variables are declared in its published metadata.
›Can I use RestoSignals as a remote (hosted) MCP server?
Yes. It is a hosted MCP server; connect to its URL with any client that supports remote MCP.
›Is RestoSignals in the official MCP registry?
Yes, as com.restosignals/restosignals.
›How many tokens does RestoSignals add to my context?
Its tool definitions total about 478 tokens, resent on every turn.
Sources and method
- Official MCP Registry entry
- updated 2026-10-17
- GitHub repository
- fetched 2026-10-19
- Tool list (tools/list), measured by us
- 2026-10-19
- Last checked against all sources
- 2026-10-19
The description, packages and links come from the maintainer's own published metadata. Token cost, security signals, freshness and the reading above are MCPSkillHub's own measurements; see the methodology. Spot an error? Request a correction or claim the listing.