mcp-localintel
The routing layer between AI agents and local Florida businesses. Live data on permits, sector gaps, and market signals across 2,383 ZIP codes — so when an agent, voice assistant, or real customer needs something done, the right business gets the job. Ask LocalIntel Claim Your Listing
README
LocalIntel — Agentic Local Business Intelligence
Autonomous business intelligence for Florida ZIP codes. 20 MCP tools. 1,445 ZIP briefs. Built for LLMs and autonomous agents.
"Let Google pay for the satellites. We sell the weather forecast."
Tools
| Tool | Description | Cost |
|---|---|---|
local_intel_ask |
Plain-English question → synthesized answer (BEST FIRST CALL) | Free |
local_intel_oracle |
Pre-baked economic narrative: saturation, price-tier gaps, growth trajectory | $0.01 |
local_intel_signal |
Investment signal 0–100 with buy/hold/avoid band | $0.03 |
local_intel_tide |
Tidal momentum score synthesizing all 4 data layers | $0.03 |
local_intel_bedrock |
Infrastructure momentum: permits, roads, flood zones (12–36mo forward) | $0.02 |
local_intel_sector_gap |
NAICS sector whitespace — county presence vs ZIP absence | $0.03 |
local_intel_for_agent |
PREMIUM composite entry: top-10 signals personalized by agent type | $0.05 |
local_intel_zone |
Spending zone + demographics for a ZIP | Free |
local_intel_context |
Spatial context block: anchor business, distance rings, category breakdown | Free |
local_intel_search |
Search businesses by name, category, or semantic group | Free |
local_intel_nearby |
Businesses within radius of a lat/lon, sorted by distance | Free |
local_intel_corridor |
Businesses along a named street (A1A, Palm Valley, Crosswater) | Free |
local_intel_changes |
Recently added or owner-verified listings | Free |
local_intel_stats |
Dataset coverage stats, confidence scores, query volume | Free |
local_intel_realtor |
Real estate intelligence: demographics, gaps, flood risk, school proximity | $0.02 |
local_intel_healthcare |
Healthcare market: provider density, demand gaps, senior population | $0.02 |
local_intel_retail |
Retail: store categories, spending capture rates, undersupplied niches | $0.02 |
local_intel_construction |
Construction: contractor density, permits, housing starts | $0.02 |
local_intel_restaurant |
Restaurant: saturation, price-tier gaps, capture rates, corridor analysis | $0.02 |
local_intel_query |
Natural language entry point with ZIP auto-detection | Free |
Installation
Connect via Smithery in one command:
npx -y @smithery/cli@latest mcp add erik-7clt/local-intel
Or connect directly to the MCP endpoint:
https://gsb-swarm-production.up.railway.app/api/local-intel/mcp
Usage
Quickstart
POST https://gsb-swarm-production.up.railway.app/api/local-intel/mcp
Content-Type: application/json
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "local_intel_ask",
"arguments": {
"question": "What restaurant categories are missing in 32082?",
"zip": "32082"
}
}
}
Agent Headers
Pass x-agent-id to enable delta computation and usage tracking:
x-agent-id: your-agent-uuid
Payment
All paid calls ($0.01–$0.05) are billed in pathUSD on Tempo mainnet. Free discovery tier available for all read-only tools.
Coverage
- 1,445 ZIP briefs computed autonomously across Northeast Florida
- 982+ businesses indexed with entity resolution
- 5 vertical agents trained on 500+ real market queries
- OpenAPI spec:
GET /openapi.json - ChatGPT plugin:
GET /.well-known/ai-plugin.json - Smithery: smithery.ai/servers/erik-7clt/local-intel
Data Layers
| Layer | What it covers |
|---|---|
| Bedrock (Layer 0) | Infrastructure: permits, FDOT road projects, flood zones, utility extensions |
| Ocean Floor (Layer 1) | Demographics: income, ownership, population, ACS signals |
| Surface Current (Layer 2) | Business activity: density, category mix, sector gaps |
| Wave Surface (Layer 3) | Momentum: tidal score, trend direction, investment signal |
Homepage
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.