# io.github.MCFLAMINGO/local-intel (remote · gsb-swarm-production.up.railway.app)

Hyperlocal business intelligence for AI agents. 20 MCP tools. Florida-first, Sunbelt expansion.

- Trust score: 61/100 (medium)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `gsb-swarm-production.up.railway.app`: 61/100 (this document), [markdown](https://verifymcp.io/servers/mcflamingo-local-intel/api-local-intel-mcp.md), [page](https://verifymcp.io/servers/mcflamingo-local-intel/api-local-intel-mcp)

## Channel facts

- Endpoint: `https://gsb-swarm-production.up.railway.app/api/local-intel/mcp`
- Transports: `streamable-http, sse`
- Auth: `none`
- Version: `1.2.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 27 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3672 tokens (~136/item across 27 items; 27 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### Claude

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

### Codex

```toml
[mcp_servers.mcflamingo-local-intel]
url = "https://gsb-swarm-production.up.railway.app/api/local-intel/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mcflamingo-local-intel": {
      "type": "remote",
      "url": "https://gsb-swarm-production.up.railway.app/api/local-intel/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mcflamingo-local-intel --url https://gsb-swarm-production.up.railway.app/api/local-intel/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  mcflamingo-local-intel:
    url: "https://gsb-swarm-production.up.railway.app/api/local-intel/mcp"
```

### Other

```json
{
  "mcpServers": {
    "mcflamingo-local-intel": {
      "type": "http",
      "url": "https://gsb-swarm-production.up.railway.app/api/local-intel/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 59, −2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 61, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 59, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 58)

First indexed and scored.

## MCP tools (27)

### `local_intel_query` (~221 tokens)

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 market intel: "Is 32082 oversaturated with dentists?" ZIP is always required for routing — pass it explicitly or include it in the query.

Input parameters:

- `lat` (number): Optional latitude (WGS84). Resolves to nearest FL ZIP. Use instead of zip for coordinate-based queries.
- `lon` (number): Optional longitude (WGS84). Required if lat is provided.
- `query` (string, required): Any plain-English market question. ZIP can be in the query or passed separately.
- `zip` (string): Optional ZIP override. If omitted, ZIP is detected from the query or resolved from lat/lon.

### `local_intel_context` (~130 tokens)

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.

Input parameters:

- `lat` (number): Latitude (WGS84) — resolves to nearest FL ZIP
- `lon` (number): Longitude (WGS84) — required if lat is provided
- `radius_miles` (number): Search radius in miles (default 1.0)
- `zip` (string): Any FL ZIP code

### `local_intel_search` (~112 tokens)

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

Input parameters:

- `category` (string): Exact OSM category (restaurant, bank, dentist...)
- `group` (string): Semantic group: food | retail | health | finance | civic | services
- `limit` (integer): Max results (default 20, max 50)
- `query` (string): Text search on name/category/address
- `zip` (string): Filter by ZIP code

### `local_intel_nearby` (~108 tokens)

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

Input parameters:

- `category` (string): Filter by OSM category
- `group` (string): Filter by semantic group
- `lat` (number, required): Latitude of center point
- `limit` (integer): Max results (default 15)
- `lon` (number, required): Longitude of center point
- `radius_miles` (number): Search radius in miles (default 0.5)

### `local_intel_zone` (~90 tokens)

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

Input parameters:

- `lat` (number): Latitude (WGS84) — resolves to nearest FL ZIP
- `lon` (number): Longitude (WGS84) — required if lat is provided
- `zip` (string): FL ZIP code

### `local_intel_corridor` (~87 tokens)

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

Input parameters:

- `limit` (integer): Max results (default 20)
- `street` (string, required): Street name (e.g. "A1A", "Palm Valley", "Crosswater")
- `zip` (string): Optional ZIP filter

### `local_intel_changes` (~51 tokens)

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

Input parameters:

- `limit` (integer): Max results (default 20)
- `zip` (string): Optional ZIP filter

### `local_intel_stats` (~26 tokens)

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

### `local_intel_tide` (~118 tokens)

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.

Input parameters:

- `include_layers` (array): Layers to include: bedrock, ocean_floor, surface_current, wave_surface (default: all)
- `query_context` (object): Optional: { agent_type, agent_id, purpose }
- `zip` (string, required): ZIP code to read tidal state for

### `local_intel_signal` (~102 tokens)

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.

Input parameters:

- `agent_type` (string): real_estate | financial | ad_placement | logistics | business_owner | civic
- `query_context` (object): Optional: { agent_id, purpose }
- `zip` (string, required): ZIP code

### `local_intel_bedrock` (~88 tokens)

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.'

Input parameters:

- `query_context` (object): Optional: { agent_type, agent_id }
- `zip` (string, required): ZIP code

### `local_intel_for_agent` (~202 tokens)

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.

Input parameters:

- `agent_id` (string): Your agent UUID for memory + delta computation
- `agent_type` (string): real_estate | financial | ad_placement | logistics | business_owner | civic
- `budget` (number): Agent budget in pathUSD (optional, for signal prioritization)
- `depth` (string): quick (top 5 signals) | full (top 10 + context blocks)
- `intent` (string): Plain-language description of what you are trying to decide or do
- `lat` (number): Latitude (if no ZIP)
- `lon` (number): Longitude (if no ZIP)
- `zip` (string): Target ZIP code

### `local_intel_oracle` (~106 tokens)

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.

Input parameters:

- `zip` (string, required): ZIP code to analyze (e.g. 32081)

### `local_intel_sector_gap` (~199 tokens)

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 — always current. Example: "NAICS 62 Health Care: Jacksonville MSA 136k healthcare employees, ZIP 32082 has no OSM healthcare listings. 28,697 residents, $121k median HHI, retiree index 1.5x. Demand: 7–10 providers." Chain into vertical agents via oracle_vertical. Cost: $0.03 pathUSD.

Input parameters:

- `zip` (string, required): ZIP code to analyze (e.g. 32081, 32082, 32259)

### `local_intel_realtor` (~129 tokens)

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.

Input parameters:

- `lat` (number): Latitude (WGS84) — resolves to nearest FL ZIP
- `lon` (number): Longitude (WGS84)
- `query` (string, required): Natural language question (e.g. "What is the flood risk for this ZIP?", "What commercial gaps exist?")
- `zip` (string): ZIP code to analyze

### `local_intel_healthcare` (~103 tokens)

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.

Input parameters:

- `lat` (number): Latitude (WGS84) — resolves to nearest FL ZIP
- `lon` (number): Longitude (WGS84)
- `query` (string, required): Natural language question about healthcare market
- `zip` (string): ZIP code to analyze

### `local_intel_retail` (~106 tokens)

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.

Input parameters:

- `lat` (number): Latitude (WGS84) — resolves to nearest FL ZIP
- `lon` (number): Longitude (WGS84)
- `query` (string, required): Natural language question about retail market
- `zip` (string): ZIP code to analyze

### `local_intel_construction` (~108 tokens)

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.

Input parameters:

- `lat` (number): Latitude (WGS84) — resolves to nearest FL ZIP
- `lon` (number): Longitude (WGS84)
- `query` (string, required): Natural language question about construction market
- `zip` (string): ZIP code to analyze

### `local_intel_restaurant` (~110 tokens)

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.

Input parameters:

- `lat` (number): Latitude (WGS84) — resolves to nearest FL ZIP
- `lon` (number): Longitude (WGS84)
- `query` (string, required): Natural language question about restaurant market
- `zip` (string): ZIP code to analyze

### `local_intel_ask` (~130 tokens)

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.

Input parameters:

- `question` (string, required): Plain English question, e.g. "What restaurant categories are missing in 32082?"
- `zip` (string): ZIP code (optional — will be extracted from question if present, defaults to 32082)

### `local_intel_compare` (~150 tokens)

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.

Input parameters:

- `focus` (string): Ranking focus: "opportunity" (default), "hhi", "saturation", "growth", or "population".
- `limit` (number): Max rows to return (default 10).
- `zips` (array, required): Array of ZIP codes to compare, e.g. ["32082","32081","32084"]. Max 10.

### `local_intel_project` (~202 tokens)

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 selection and franchise expansion when you know the business type but not the ZIP.

Input parameters:

- `limit` (number): Number of L1 ZIPs to return (default 5, max 10).
- `project_type` (string, required): Business type or project category. Examples: restaurant, clinic, banking, construction, real_estate, residential_development, fitness, legal, retail, grocery, auto, beauty, pets.
- `zip` (string): Optional. Filter L2 businesses to a specific ZIP. If omitted, returns top ZIPs ranked by score.

### `local_intel_rfq` (~487 tokens)

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.

Input parameters:

- `autonomy` (string): full=agent books automatically; approve=agent picks best, human confirms; human=human picks from list
- `budget_usd` (number): Max budget in USD (optional)
- `business_id` (string): Target a specific LocalIntel business (required when ordering from a named restaurant)
- `business_name` (string): Human business name, e.g. McFlamingo — shown on the Jobs card
- `category` (string): Business category to match, e.g. "restaurant", "food", "delivery", "landscaping", "florist", "handyman", "plumber"
- `customer_note` (string): Extra note for the business (allergies, ETA, pickup vs delivery)
- `deadline_minutes` (number): Minutes until deadline (for urgent delivery jobs)
- `description` (string, required): 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_address` (string): Drop-off address (delivery jobs)
- `dry_run` (boolean): 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.
- `items` (array): Structured line items, e.g. [{ "name": "chicken and broccoli", "qty": 1 }]
- `job_type` (string): delivery = first-to-accept wins (food orders, pickups); proposal = collect quotes, pick best (services, construction)
- `notify_email` (string): Email to notify for approve/human autonomy levels
- `pickup_address` (string): Pickup address (delivery jobs)
- `task` (string): Alias for description (same meaning)
- `zip` (string): ZIP code to search businesses in

### `local_intel_rfq_status` (~54 tokens)

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

Input parameters:

- `rfq_id` (string, required): UUID returned by local_intel_rfq

### `local_intel_book` (~77 tokens)

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

Input parameters:

- `note` (string): Optional note to the business
- `response_id` (string, required): UUID of the response to accept
- `rfq_id` (string, required): UUID of the RFQ

### `local_intel_decline_response` (~99 tokens)

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.

Input parameters:

- `reason` (string): Optional reason for declining (e.g. price too high, too far)
- `response_id` (string, required): UUID of the response to decline
- `rfq_id` (string, required): UUID of the RFQ

### `local_intel_complete` (~72 tokens)

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).

Input parameters:

- `booking_id` (string, required): UUID returned by local_intel_book
- `note` (string): Completion note or rating

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/mcflamingo-local-intel/api-local-intel-mcp#diagnostics

## Score history

- 2026-08-03: 61
- 2026-08-02: 60
- 2026-08-01: 60
- 2026-07-31: 59
- 2026-07-30: 61
- 2026-07-29: 60
- 2026-07-28: 60
- 2026-07-27: 59
- 2026-07-26: 58

## Links

- Remote endpoint: https://gsb-swarm-production.up.railway.app/api/local-intel/mcp
- Repository: https://github.com/MCFLAMINGO/gsb-swarm
- Changelog RSS feed: https://verifymcp.io/servers/mcflamingo-local-intel/api-local-intel-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/mcflamingo-local-intel/api-local-intel-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/mcflamingo-local-intel/api-local-intel-mcp