Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
Local Intel is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
tool-list score
27
tools declared
remote
at its publisher
—
calls last 7d
What it does
Hyperlocal business intelligence for AI agents. 20 MCP tools. Florida-first, Sunbelt expansion.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http local-intel-mcp https://gsb-swarm-production.up.railway.app/api/local-intel/mcp
# 2 — ask your agent for something these tools do
# local_intel_query, local_intel_context, local_intel_search and 24 more
Local Intel costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http local-intel-mcp https://gsb-swarm-production.up.railway.app/api/local-intel/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
27 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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 "Who can do landscaping in Ponte Vedra?" — returns the matching business so your agent can route the order to them. For ma
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Any plain-English market question. ZIP can be in the query or passed separately. |
| zip | string | no | Optional ZIP override. If omitted, ZIP is detected from the query or resolved from lat/lon. |
| lat | number | no | Optional latitude (WGS84). Resolves to nearest FL ZIP. Use instead of zip for coordinate-based queries. |
| lon | number | no | Optional longitude (WGS84). Required if lat is provided. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| zip | string | no | Any FL ZIP code |
| lat | number | no | Latitude (WGS84) — resolves to nearest FL ZIP |
| lon | number | no | Longitude (WGS84) — required if lat is provided |
| radius_miles | number | no | Search radius in miles (default 1.0) |
Search businesses by name, category, or semantic group (food, retail, health, finance, civic, services).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| zip | string | no | Filter by ZIP code |
| query | string | no | Text search on name/category/address |
| category | string | no | Exact OSM category (restaurant, bank, dentist...) |
| group | string | no | Semantic group: food | retail | health | finance | civic | services |
| limit | integer | no | Max results (default 20, max 50) |
Find businesses within a radius of any lat/lon point, sorted by distance with compass bearing.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| lat | number | yes | Latitude of center point |
| lon | number | yes | Longitude of center point |
| radius_miles | number | no | Search radius in miles (default 0.5) |
| category | string | no | Filter by OSM category |
| group | string | no | Filter by semantic group |
| limit | integer | no | Max results (default 15) |
Spending zone and demographic data for a ZIP code: population, income, home value, rent, ownership rate, zone score. Pass zip or lat/lon.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| zip | string | no | FL ZIP code |
| lat | number | no | Latitude (WGS84) — resolves to nearest FL ZIP |
| lon | number | no | Longitude (WGS84) — required if lat is provided |
Businesses along a named street corridor. Use for queries like "what is on A1A" or "businesses on Palm Valley Road".
| Parameter | Type | Required | Notes |
|---|---|---|---|
| street | string | yes | Street name (e.g. "A1A", "Palm Valley", "Crosswater") |
| zip | string | no | Optional ZIP filter |
| limit | integer | no | Max results (default 20) |
Recently added or owner-verified business listings. Use to detect new openings or data updates.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| zip | string | no | Optional ZIP filter |
| limit | integer | no | Max results (default 20) |
Dataset coverage stats: total businesses, confidence scores, query volume, revenue earned.
No parameter schema on file.
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| zip | string | yes | ZIP code to read tidal state for |
| include_layers | array | no | Layers to include: bedrock, ocean_floor, surface_current, wave_surface (default: all) |
| query_context | object | no | Optional: { agent_type, agent_id, purpose } |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| zip | string | yes | ZIP code |
| agent_type | string | no | real_estate | financial | ad_placement | logistics | business_owner | civic |
| query_context | object | no | Optional: { agent_id, purpose } |
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.'
| Parameter | Type | Required | Notes |
|---|---|---|---|
| zip | string | yes | ZIP code |
| query_context | object | no | Optional: { agent_type, agent_id } |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_type | string | no | real_estate | financial | ad_placement | logistics | business_owner | civic |
| intent | string | no | Plain-language description of what you are trying to decide or do |
| zip | string | no | Target ZIP code |
| lat | number | no | Latitude (if no ZIP) |
| lon | number | no | Longitude (if no ZIP) |
| budget | number | no | Agent budget in pathUSD (optional, for signal prioritization) |
| depth | string | no | quick (top 5 signals) | full (top 10 + context blocks) |
| agent_id | string | no | Your agent UUID for memory + delta computation |
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 derived from population, income, business density, school count, and infrastructure signals.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| zip | string | yes | ZIP code to analyze (e.g. 32081) |
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 employment share, demand estimate, confidence tier, and LLM-ready signal narrative. Reads live from Postgres zip_signals — alw
| Parameter | Type | Required | Notes |
|---|---|---|---|
| zip | string | yes | ZIP code to analyze (e.g. 32081, 32082, 32259) |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Natural language question (e.g. "What is the flood risk for this ZIP?", "What commercial gaps exist?") |
| zip | string | no | ZIP code to analyze |
| lat | number | no | Latitude (WGS84) — resolves to nearest FL ZIP |
| lon | number | no | Longitude (WGS84) |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Natural language question about healthcare market |
| zip | string | no | ZIP code to analyze |
| lat | number | no | Latitude (WGS84) — resolves to nearest FL ZIP |
| lon | number | no | Longitude (WGS84) |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Natural language question about retail market |
| zip | string | no | ZIP code to analyze |
| lat | number | no | Latitude (WGS84) — resolves to nearest FL ZIP |
| lon | number | no | Longitude (WGS84) |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Natural language question about construction market |
| zip | string | no | ZIP code to analyze |
| lat | number | no | Latitude (WGS84) — resolves to nearest FL ZIP |
| lon | number | no | Longitude (WGS84) |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Natural language question about restaurant market |
| zip | string | no | ZIP code to analyze |
| lat | number | no | Latitude (WGS84) — resolves to nearest FL ZIP |
| lon | number | no | Longitude (WGS84) |
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 right tools and returns a synthesized, sourced answer with confidence score. Best single entry point for humans and LLMs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| question | string | yes | Plain English question, e.g. "What restaurant categories are missing in 32082?" |
| zip | string | no | ZIP code (optional — will be extracted from question if present, defaults to 32082) |
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 screening, and market prioritization.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| zips | array | yes | Array of ZIP codes to compare, e.g. ["32082","32081","32084"]. Max 10. |
| focus | string | no | Ranking focus: "opportunity" (default), "hhi", "saturation", "growth", or "population". |
| limit | number | no | Max rows to return (default 10). |
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 operating in that sector. Returns sector gap counts, HHI, population, growth state, and new-build %. Best tool for site sele
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_type | string | yes | Business type or project category. Examples: restaurant, clinic, banking, construction, real_estate, residential_development, fitness, legal, retail, grocery, auto, beauty, pets. |
| zip | string | no | Optional. Filter L2 businesses to a specific ZIP. If omitted, returns top ZIPs ranked by score. |
| limit | number | no | Number of L1 ZIPs to return (default 5, max 10). |
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 this when KDS/POS is off or for quote collection. Supports delivery (first-to-accept) and proposal (collect quotes) modes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_type | string | no | delivery = first-to-accept wins (food orders, pickups); proposal = collect quotes, pick best (services, construction) |
| category | string | no | Business category to match, e.g. "restaurant", "food", "delivery", "landscaping", "florist", "handyman", "plumber" |
| zip | string | no | ZIP code to search businesses in |
| description | string | yes | Full human-readable request. For food: include items, e.g. "Order for McFlamingo: chicken and broccoli". Do NOT use vague text like "Buy me." |
| task | string | no | Alias for description (same meaning) |
| items | array | no | Structured line items, e.g. [{ "name": "chicken and broccoli", "qty": 1 }] |
| business_id | string | no | Target a specific LocalIntel business (required when ordering from a named restaurant) |
| business_name | string | no | Human business name, e.g. McFlamingo — shown on the Jobs card |
| customer_note | string | no | Extra note for the business (allergies, ETA, pickup vs delivery) |
| pickup_address | string | no | Pickup address (delivery jobs) |
| dropoff_address | string | no | Drop-off address (delivery jobs) |
| budget_usd | number | no | Max budget in USD (optional) |
| deadline_minutes | number | no | Minutes until deadline (for urgent delivery jobs) |
| autonomy | string | no | full=agent books automatically; approve=agent picks best, human confirms; human=human picks from list |
| notify_email | string | no | Email to notify for approve/human autonomy levels |
| dry_run | boolean | no | 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. |
Poll the status of an RFQ. Returns the original request, all responses received so far, and booking details if booked.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rfq_id | string | yes | UUID returned by local_intel_rfq |
Book a specific response to an RFQ — confirms the job with that business. Use after reviewing local_intel_rfq_status responses.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rfq_id | string | yes | UUID of the RFQ |
| response_id | string | yes | UUID of the response to accept |
| note | string | no | Optional note to the business |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rfq_id | string | yes | UUID of the RFQ |
| response_id | string | yes | UUID of the response to decline |
| reason | string | no | Optional reason for declining (e.g. price too high, too far) |
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).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| booking_id | string | yes | UUID returned by local_intel_book |
| note | string | no | Completion note or rating |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Local Intel or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 96 / 100
Release 1.2.0 · scanned 20 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digestabe6f8fd8e1f040da0d7e39d4c1c7c364af7768feaf200d5ce5e1f7e2c280081
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| local_intel_query | no tags | |
| local_intel_context | no tags | |
| local_intel_search | no tags | |
| local_intel_nearby | no tags | |
| local_intel_zone | no tags | |
| local_intel_corridor | no tags | |
| local_intel_changes | no tags | |
| local_intel_stats | no tags | |
| local_intel_tide | no tags | |
| local_intel_signal | no tags | |
| local_intel_bedrock | no tags | |
| local_intel_for_agent | no tags | |
| local_intel_oracle | no tags | |
| local_intel_sector_gap | no tags | |
| local_intel_realtor | no tags | |
| local_intel_healthcare | no tags | |
| local_intel_retail | no tags | |
| local_intel_construction | no tags | |
| local_intel_restaurant | no tags | |
| local_intel_ask | no tags | |
| local_intel_compare | no tags | |
| local_intel_project | no tags | |
| local_intel_rfq | no tags | |
| local_intel_rfq_status | no tags | |
| local_intel_book | no tags | |
| local_intel_decline_response | no tags | |
| local_intel_complete | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestabe6f8fd8e1f040d
Scanned2026-10-20
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.2.0.
1.2.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Local Intel can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.