muni-dev-cost
Provides aggregated municipal development costs for US jurisdictions, including impact fees and utility connection charges, enabling AI agents to assess building feasibility quickly.
README
muni-dev-cost ποΈ
What will the city and utility charge me to build here?
muni-dev-cost is an MCP server (and a pay-per-call x402 API) that gives an AI
agent the municipal development cost for a US jurisdiction β the
impact/development fees, water & sewer tap (connection) fees and
capital-recovery charges a real-estate developer must pay before breaking
ground β aggregated and normalized from public, government-published fee
schedules into one comparable number.
For a real-estate development-feasibility / pro-forma agent, this number is load-bearing and, today, costs weeks of manual digging across municipal ordinances, utility fee schedules and county portals. We do the aggregation so your agent doesn't have to.
// add to your MCP client config
{ "mcpServers": { "muni-dev-cost": { "command": "npx", "args": ["-y", "muni-dev-cost-mcp"] } } }
Tools
| Tool | Tier | What you get |
|---|---|---|
get_dev_costs |
Free | The aggregated municipal development cost for a jurisdiction (single-family home), split into water+sewer vs other impact, with a per-fee summary and an honest coverage label. |
get_fee_breakdown |
Premium | Every fee line by line, grouped (Water / Sewer / Transportation / Parks / Drainage), with the per-meter-size schedule and each source + effective date. |
compare_jurisdictions |
Premium | Rank 2β12 markets side by side for site selection β total, water+sewer split, the dollar/% spread and what it costs on a 100-unit project. |
get_water_sewer_detail |
Premium | Water & sewer connection cost by meter size (5/8" β 12") β the single biggest swing in a utility connection budget. |
estimate_dev_cost |
Premium | Whole-project fees (fees Γ units) with per-unit and extended line items, dev-type aware, explicit about exclusions. |
list_jurisdictions |
Premium | The full coverage map β every jurisdiction, its depth and data freshness, which publish a per-meter schedule, plus the benchmark states. |
get_fee_schedule_source |
Premium | The published source document + per-fee provenance (published vs estimated) behind a jurisdiction's number β defensible trazabilidad for a pro-forma. |
get_cost_trend |
Premium | The real dated revision history of a jurisdiction's headline fee (prior years + adopted future steps) with YoY delta and CAGR β never a projection. |
compare_by_meter_size |
Premium | One jurisdiction's water/sewer cost across every published meter size, ratioed to the 5/8" residential base. |
estimate_by_units |
Premium | Multifamily/mixed fee estimate by LUE (units Γ LUE-per-unit) β the way cities actually bill MF, so it doesn't overstate fees. |
get_total_dev_cost |
Premium | The grand total across every fee category (water/sewer, transportation, parks, drainage, public-safety, other), bucketed β with honest $0 buckets where a city simply doesn't charge that category. |
breakdown_by_fee_category |
Premium | Every line item within one category (e.g. all of a city's parks fees) with per-meter detail β errors honestly if the city doesn't levy that category. |
rank_jurisdictions_by_cost |
Premium | Rank the entire covered KB cheapestβpriciest by water+sewer or total, with cheapest/median/priciest, the spread, and a site-selection insight β filterable by state/coverage. |
summarize_by_state |
Premium | A state-level roll-up over the whole KB: per state, the city count, min/median/max cost, cheapest/priciest city, and which fee categories are assessed β the map for "which states are cheap/expensive to build in." |
1 free + 13 premium tools. The free
get_dev_costsis the hook; the 13 premium tools are the depth a feasibility agent can't assemble itself.
Example (free)
POST https://muni-dev-cost-mcp.vercel.app/dev-costs
{ "jurisdiction": "Phoenix, AZ" }
ποΈ Phoenix, AZ Β· coverage π’ deep
Municipal development cost, single-family home: $29,322
β’ Water + sewer (impact + tap): $29,322
Fees included (one line each):
β’ Wastewater Collection impact fee: $5,127 (per dwelling)
β’ Wastewater Treatment impact fee: $3,753 (per dwelling)
β’ Water Transmission impact fee: $14,046 (per dwelling)
β’ Water Treatment impact fee: $4,387 (per dwelling)
β’ Water Resource Acquisition fee: $2,009 (per dwelling)
Coverage (honest β regla 7)
We never pass off an estimate as a city's published number.
- π’ deep β the city's own water/sewer fee schedule was ingested, including
the per-meter table. Figures are
published. - π‘ partial β headline impact figures from public schedules; some categories estimated.
- π estimated β the exact city isn't in our deep KB yet, so figures are a regional benchmark, clearly marked. Use as order-of-magnitude only.
Coverage today: 130 jurisdictions across 38 states β 109 deep (own per-meter/per-LUE schedule ingested) + 21 partial. Dense in the high-growth markets a feasibility agent actually screens: TX (18), CO (18), FL (18), NC (16), CA (11), plus AZ, GA, WA, OR and more. From the cheapest covered market (Mobile, AL ~$1,000) to the priciest (Erie, CO ~$78,350), ranked and queryable. Any US city not yet ingested returns an honest state benchmark estimate β and the deep KB grows every iteration.
All fee data is sourced from public, government-published fee schedules (works of US municipal government β public domain). Each jurisdiction carries its source URL and effective date. Indicative β verify the exact amount with the jurisdiction. Not legal or fee-certification advice.
Two ways to pay for the premium tools
- π³ Card (Stripe) β buy a prepaid API key at
/pro/checkout, then set"env": { "MUNI_DEV_COST_KEY": "<key>" }. - πͺ x402 (USDC on Base) β AI agents pay per call automatically; no signup.
The free get_dev_costs works with no key.
How it stays a moat
The aggregation engine, the normalized fee knowledge base and the accumulating
per-jurisdiction cache run server-side. The npm package is a thin client:
it forwards your call to the hosted server and renders the response. The fee data
and the premium logic never ship in the tarball β a moat verified on every build
by npm run test:moat.
License
MIT. Source: https://github.com/Baneado98/muni-dev-cost
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.