mcflamingo avatar

Local Intel

mcflamingo/gsb-swarm

This server connects Claude to hyperlocal business intelligence for Florida ZIP codes, starting with 1,445 pre-computed briefs across the northeast region. You get 20 tools ranging from free discovery queries (search businesses, check demographics, find corridor listings) to paid intelligence calls like sector gap analysis, investment signals, and tidal momentum scores that synthesize infrastructure permits, flood zones, and business density. The premium tool costs five cents and returns personalized top-10 signals by agent type. Paid calls run $0.01 to $0.05 and bill in pathUSD on Tempo mainnet. Reach for this when you're building agents that need to answer "what's missing in this market" or "where should I open a location" with real permit data and spending patterns instead of vibes.

tools
27
transport
HTTP, SSE
last updated
Apr 24, 2026

Install

From registry metadata
$ npx add-mcp https://gsb-swarm-production.up.railway.app/api/local-intel/mcp --name local-intel

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http local-intel https://gsb-swarm-production.up.railway.app/api/local-intel/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 27 tools

Verified live against the running server on Nov 6, 2026.

local_intel_querySTART HERE. Natural language entry point for both market intelligence AND business routing. Ask about a market, find a business, or route a customer request. Auto-detects ZIP, industry vertical, and intent. For customer agents: "Find a restaurant in 32082 that serves lunch" or...4 params

START HERE. Natural language entry point for both market intelligence AND business routing. Ask about a market, find a business, or route a customer request. Auto-detects ZIP, industry vertical, and intent. For customer agents: "Find a restaurant in 32082 that serves lunch" or...

Parameters* required
latnumber
Optional latitude (WGS84). Resolves to nearest FL ZIP. Use instead of zip for coordinate-based queries.
lonnumber
Optional longitude (WGS84). Required if lat is provided.
query*string
Any plain-English market question. ZIP can be in the query or passed separately.
zipstring
Optional ZIP override. If omitted, ZIP is detected from the query or resolved from lat/lon.
local_intel_contextFull spatial context block for any FL zip or lat/lon. Returns anchor business, nearby businesses in distance rings, zone intelligence, and category breakdown. Best first call for any location query. Covers all 1,473 FL ZIPs via fl_zip_geo.4 params

Full spatial context block for any FL zip or lat/lon. Returns anchor business, nearby businesses in distance rings, zone intelligence, and category breakdown. Best first call for any location query. Covers all 1,473 FL ZIPs via fl_zip_geo.

Parameters* required
latnumber
Latitude (WGS84) — resolves to nearest FL ZIP
lonnumber
Longitude (WGS84) — required if lat is provided
radius_milesnumber
Search radius in miles (default 1.0)
zipstring
Any FL ZIP code
local_intel_searchSearch businesses by name, category, or semantic group (food, retail, health, finance, civic, services).5 params

Search businesses by name, category, or semantic group (food, retail, health, finance, civic, services).

Parameters* required
categorystring
Exact OSM category (restaurant, bank, dentist...)
groupstring
Semantic group: food | retail | health | finance | civic | services
limitinteger
Max results (default 20, max 50)
querystring
Text search on name/category/address
zipstring
Filter by ZIP code
local_intel_nearbyFind businesses within a radius of any lat/lon point, sorted by distance with compass bearing.6 params

Find businesses within a radius of any lat/lon point, sorted by distance with compass bearing.

Parameters* required
categorystring
Filter by OSM category
groupstring
Filter by semantic group
lat*number
Latitude of center point
limitinteger
Max results (default 15)
lon*number
Longitude of center point
radius_milesnumber
Search radius in miles (default 0.5)
local_intel_zoneSpending zone and demographic data for a ZIP code: population, income, home value, rent, ownership rate, zone score. Pass zip or lat/lon.3 params

Spending zone and demographic data for a ZIP code: population, income, home value, rent, ownership rate, zone score. Pass zip or lat/lon.

Parameters* required
latnumber
Latitude (WGS84) — resolves to nearest FL ZIP
lonnumber
Longitude (WGS84) — required if lat is provided
zipstring
FL ZIP code
local_intel_corridorBusinesses along a named street corridor. Use for queries like "what is on A1A" or "businesses on Palm Valley Road".3 params

Businesses along a named street corridor. Use for queries like "what is on A1A" or "businesses on Palm Valley Road".

Parameters* required
limitinteger
Max results (default 20)
street*string
Street name (e.g. "A1A", "Palm Valley", "Crosswater")
zipstring
Optional ZIP filter
local_intel_changesRecently added or owner-verified business listings. Use to detect new openings or data updates.2 params

Recently added or owner-verified business listings. Use to detect new openings or data updates.

Parameters* required
limitinteger
Max results (default 20)
zipstring
Optional ZIP filter
local_intel_statsDataset coverage stats: total businesses, confidence scores, query volume, revenue earned.

Dataset coverage stats: total businesses, confidence scores, query volume, revenue earned.

No parameters. Call it with no arguments.

local_intel_tideTidal reading for a ZIP — temperature (0-100), direction (surging/heating/stable/cooling/receding), seasonal context. Synthesizes all 4 data layers. Best for agents deciding WHERE to act next.3 params

Tidal reading for a ZIP — temperature (0-100), direction (surging/heating/stable/cooling/receding), seasonal context. Synthesizes all 4 data layers. Best for agents deciding WHERE to act next.

Parameters* required
include_layersarray
Layers to include: bedrock, ocean_floor, surface_current, wave_surface (default: all)
query_contextobject
Optional: { agent_type, agent_id, purpose }
zip*string
ZIP code to read tidal state for
local_intel_signalInvestment and activity signal for a ZIP. Composite score 0-100 with band (strong_buy/accumulate/hold/reduce/avoid), top reasons, and avoid flags. Best for real estate and financial agents.3 params

Investment and activity signal for a ZIP. Composite score 0-100 with band (strong_buy/accumulate/hold/reduce/avoid), top reasons, and avoid flags. Best for real estate and financial agents.

Parameters* required
agent_typestring
real_estate | financial | ad_placement | logistics | business_owner | civic
query_contextobject
Optional: { agent_id, purpose }
zip*string
ZIP code
local_intel_bedrockInfrastructure momentum score and active leading indicators for a ZIP from Layer 0. Permits, road projects, flood zones, utility extensions. Predicts conditions 12-36 months ahead. 'Let Google pay for the satellites — we sell the weather forecast.'2 params

Infrastructure momentum score and active leading indicators for a ZIP from Layer 0. Permits, road projects, flood zones, utility extensions. Predicts conditions 12-36 months ahead. 'Let Google pay for the satellites — we sell the weather forecast.'

Parameters* required
query_contextobject
Optional: { agent_type, agent_id }
zip*string
ZIP code
local_intel_for_agentPREMIUM composite entry point ($0.05). Declare your agent_type and intent, receive pre-ranked top-10 signals assembled from all 4 data layers, personalized for your use case. Includes delta since your last query if agent_id provided. Best first call for any new agent.8 params

PREMIUM composite entry point ($0.05). Declare your agent_type and intent, receive pre-ranked top-10 signals assembled from all 4 data layers, personalized for your use case. Includes delta since your last query if agent_id provided. Best first call for any new agent.

Parameters* required
agent_idstring
Your agent UUID for memory + delta computation
agent_typestring
real_estate | financial | ad_placement | logistics | business_owner | civic
budgetnumber
Agent budget in pathUSD (optional, for signal prioritization)
depthstring
quick (top 5 signals) | full (top 10 + context blocks)
intentstring
Plain-language description of what you are trying to decide or do
latnumber
Latitude (if no ZIP)
lonnumber
Longitude (if no ZIP)
zipstring
Target ZIP code
local_intel_oraclePre-baked economic oracle for a ZIP. Returns: restaurant saturation (is there room for another?), price-tier gap analysis (what menu price is missing?), growth trajectory (growing/empty-nest/stable), and 3 pre-formed questions with answers baked in. No LLM needed — answers der...1 params

Pre-baked economic oracle for a ZIP. Returns: restaurant saturation (is there room for another?), price-tier gap analysis (what menu price is missing?), growth trajectory (growing/empty-nest/stable), and 3 pre-formed questions with answers baked in. No LLM needed — answers der...

Parameters* required
zip*string
ZIP code to analyze (e.g. 32081)
local_intel_sector_gapRanked sector gap analysis for a ZIP. Identifies NAICS sectors present at county level (CBP/CES employment) but underrepresented at ZIP (OSM business counts) — the structural whitespace in a local economy. Returns ranked opportunities with: NAICS code, sector label, county emp...1 params

Ranked sector gap analysis for a ZIP. Identifies NAICS sectors present at county level (CBP/CES employment) but underrepresented at ZIP (OSM business counts) — the structural whitespace in a local economy. Returns ranked opportunities with: NAICS code, sector label, county emp...

Parameters* required
zip*string
ZIP code to analyze (e.g. 32081, 32082, 32259)
local_intel_realtorReal estate intelligence for a ZIP. Ask natural-language questions: demographics, commercial gaps, flood risk, school proximity, infrastructure signals, market saturation. Returns structured data with confidence score. Trained on 100 realtor use-case prompts.4 params

Real estate intelligence for a ZIP. Ask natural-language questions: demographics, commercial gaps, flood risk, school proximity, infrastructure signals, market saturation. Returns structured data with confidence score. Trained on 100 realtor use-case prompts.

Parameters* required
latnumber
Latitude (WGS84) — resolves to nearest FL ZIP
lonnumber
Longitude (WGS84)
query*string
Natural language question (e.g. "What is the flood risk for this ZIP?", "What commercial gaps exist?")
zipstring
ZIP code to analyze
local_intel_healthcareHealthcare market intelligence for a ZIP. Ask about provider density, patient demographics, demand gaps, senior population. Returns structured data with confidence score. Trained on 100 healthcare business prompts.4 params

Healthcare market intelligence for a ZIP. Ask about provider density, patient demographics, demand gaps, senior population. Returns structured data with confidence score. Trained on 100 healthcare business prompts.

Parameters* required
latnumber
Latitude (WGS84) — resolves to nearest FL ZIP
lonnumber
Longitude (WGS84)
query*string
Natural language question about healthcare market
zipstring
ZIP code to analyze
local_intel_retailRetail market intelligence for a ZIP. Ask about store categories, spending capture rates, consumer profile, undersupplied niches. Returns structured data with confidence score. Trained on 100 retail business prompts.4 params

Retail market intelligence for a ZIP. Ask about store categories, spending capture rates, consumer profile, undersupplied niches. Returns structured data with confidence score. Trained on 100 retail business prompts.

Parameters* required
latnumber
Latitude (WGS84) — resolves to nearest FL ZIP
lonnumber
Longitude (WGS84)
query*string
Natural language question about retail market
zipstring
ZIP code to analyze
local_intel_constructionConstruction and home services market intelligence for a ZIP. Ask about contractor density, active permits, housing starts, population growth driving demand. Returns structured data with confidence score. Trained on 100 construction business prompts.4 params

Construction and home services market intelligence for a ZIP. Ask about contractor density, active permits, housing starts, population growth driving demand. Returns structured data with confidence score. Trained on 100 construction business prompts.

Parameters* required
latnumber
Latitude (WGS84) — resolves to nearest FL ZIP
lonnumber
Longitude (WGS84)
query*string
Natural language question about construction market
zipstring
ZIP code to analyze
local_intel_restaurantRestaurant and food service market intelligence for a ZIP. Ask about saturation scores, price-tier gaps, capture rates, corridor analysis, tidal momentum. Returns structured data with confidence score. Trained on 100 restaurant business prompts.4 params

Restaurant and food service market intelligence for a ZIP. Ask about saturation scores, price-tier gaps, capture rates, corridor analysis, tidal momentum. Returns structured data with confidence score. Trained on 100 restaurant business prompts.

Parameters* required
latnumber
Latitude (WGS84) — resolves to nearest FL ZIP
lonnumber
Longitude (WGS84)
query*string
Natural language question about restaurant market
zipstring
ZIP code to analyze
local_intel_askComposite NL query layer. Ask any plain-English question about a ZIP — demographics, market opportunity, restaurant gaps, retail saturation, construction activity, investment signals, healthcare, corridor analysis, recent changes, nearby businesses. Routes internally to the ri...2 params

Composite NL query layer. Ask any plain-English question about a ZIP — demographics, market opportunity, restaurant gaps, retail saturation, construction activity, investment signals, healthcare, corridor analysis, recent changes, nearby businesses. Routes internally to the ri...

Parameters* required
question*string
Plain English question, e.g. "What restaurant categories are missing in 32082?"
zipstring
ZIP code (optional — will be extracted from question if present, defaults to 32082)
local_intel_compareCompare up to 10 ZIP codes side-by-side and get a ranked opportunity table. Returns per-ZIP signals (HHI, capture rate, infra momentum, consumer profile, top gap) plus a top_pick recommendation with reasoning. Best tool for site selection, franchise expansion, investment scree...3 params

Compare up to 10 ZIP codes side-by-side and get a ranked opportunity table. Returns per-ZIP signals (HHI, capture rate, infra momentum, consumer profile, top gap) plus a top_pick recommendation with reasoning. Best tool for site selection, franchise expansion, investment scree...

Parameters* required
focusstring
Ranking focus: "opportunity" (default), "hhi", "saturation", "growth", or "population".
limitnumber
Max rows to return (default 10).
zips*array
Array of ZIP codes to compare, e.g. ["32082","32081","32084"]. Max 10.
local_intel_projectProject-type intelligence: pass a project_type (restaurant, clinic, banking, construction, real_estate, residential_development, fitness, legal, retail, auto, etc.) and get L1 ZIPs ranked by market or residential opportunity score plus L2 matching verified businesses already o...3 params

Project-type intelligence: pass a project_type (restaurant, clinic, banking, construction, real_estate, residential_development, fitness, legal, retail, auto, etc.) and get L1 ZIPs ranked by market or residential opportunity score plus L2 matching verified businesses already o...

Parameters* required
limitnumber
Number of L1 ZIPs to return (default 5, max 10).
project_type*string
Business type or project category. Examples: restaurant, clinic, banking, construction, real_estate, residential_development, fitness, legal, retail, grocery, auto, beauty, pets.
zipstring
Optional. Filter L2 businesses to a specific ZIP. If omitted, returns top ZIPs ranked by score.
local_intel_rfqRoute a customer request to local businesses — food orders, delivery, services, or any job. ALWAYS include the full order or ask in description (or items[]), plus business_id/business_name when ordering from a specific place. Never send a vague description like "Buy me." Use t...16 params

Route a customer request to local businesses — food orders, delivery, services, or any job. ALWAYS include the full order or ask in description (or items[]), plus business_id/business_name when ordering from a specific place. Never send a vague description like "Buy me." Use t...

Parameters* required
autonomystring
full=agent books automatically; approve=agent picks best, human confirms; human=human picks from listone of full · approve · human
budget_usdnumber
Max budget in USD (optional)
business_idstring
Target a specific LocalIntel business (required when ordering from a named restaurant)
business_namestring
Human business name, e.g. McFlamingo — shown on the Jobs card
categorystring
Business category to match, e.g. "restaurant", "food", "delivery", "landscaping", "florist", "handyman", "plumber"
customer_notestring
Extra note for the business (allergies, ETA, pickup vs delivery)
deadline_minutesnumber
Minutes until deadline (for urgent delivery jobs)
description*string
Full human-readable request. For food: include items, e.g. "Order for McFlamingo: chicken and broccoli". Do NOT use vague text like "Buy me."
dropoff_addressstring
Drop-off address (delivery jobs)
dry_runboolean
If true, match businesses but do NOT send email/SMS/push/rail notifications. Also auto-enabled for x-agent-id values starting with cursor-test-, test-, agent-test-, or dry-run.
itemsarray
Structured line items, e.g. [{ "name": "chicken and broccoli", "qty": 1 }]
job_typestring
delivery = first-to-accept wins (food orders, pickups); proposal = collect quotes, pick best (services, construction)one of delivery · proposal
notify_emailstring
Email to notify for approve/human autonomy levels
pickup_addressstring
Pickup address (delivery jobs)
taskstring
Alias for description (same meaning)
zipstring
ZIP code to search businesses in
local_intel_rfq_statusPoll the status of an RFQ. Returns the original request, all responses received so far, and booking details if booked.1 params

Poll the status of an RFQ. Returns the original request, all responses received so far, and booking details if booked.

Parameters* required
rfq_id*string
UUID returned by local_intel_rfq
local_intel_bookBook a specific response to an RFQ — confirms the job with that business. Use after reviewing local_intel_rfq_status responses.3 params

Book a specific response to an RFQ — confirms the job with that business. Use after reviewing local_intel_rfq_status responses.

Parameters* required
notestring
Optional note to the business
response_id*string
UUID of the response to accept
rfq_id*string
UUID of the RFQ
local_intel_decline_responseDecline a specific response to an RFQ and get the next in queue. Use when a client rejects the first responder — returns the next pending response automatically. First come first served queue.3 params

Decline a specific response to an RFQ and get the next in queue. Use when a client rejects the first responder — returns the next pending response automatically. First come first served queue.

Parameters* required
reasonstring
Optional reason for declining (e.g. price too high, too far)
response_id*string
UUID of the response to decline
rfq_id*string
UUID of the RFQ
local_intel_completeMark a booked job as complete and settle payment to the local merchant wallet (Tempo pathUSD when SETTLEMENT_ENABLED=true; otherwise records settled_intent and feeds the forecast loop).2 params

Mark a booked job as complete and settle payment to the local merchant wallet (Tempo pathUSD when SETTLEMENT_ENABLED=true; otherwise records settled_intent and feeds the forecast loop).

Parameters* required
booking_id*string
UUID returned by local_intel_book
notestring
Completion note or rating

Sponsors

Readme

Details

Repository
github.com/mcflamingo/gsb-swarm
Transport
HTTP, SSE
Registry
MCP registry, active
Tools verified
Nov 6, 2026