Skip to content

AI Buildout Permits MCP server

io.github.2016judea/ai-buildout-permits2016judeastreamable-httpv0.1.0Scanned

US AI data-center projects from public records: tenants, air permits, turbines, resolved to tickers

7 tools: 5 change things and 2 only read.

Tools: 0 delete, 0 irreversible, 5 write, 2 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

5 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the AI Buildout Permits MCP server can do

The AI Buildout Permits MCP server is published by the GitHub account 2016judea. It has 7 tools. It can create or change data (5 tools: whats_new, project_detail, company_exposure, equipment_tracker and 1 more), but cannot delete data. 2 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 21, 2026, version 0.1.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

7 tools

Changes things 5Claude Code: ask
  • company_exposureEvery data-center project in the ledger that resolves to one ticker or company, in any role (tenant, operator, owner, permittee, equipment maker): status, place, first record date,…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Every data-center project in the ledger that resolves to one ticker or company, in any role (tenant, operator, owner, permittee, equipment maker): status, place, first record date, first-seen date, stated on-site MW, plus counts by role, state and first-record year, and the link methods used. Requires a subscription. Example questions: - "Which data-center projects resolve to ORCL, and since when?" - "How many Texas certifications name Amazon by year?" - "Where does Anthropic show up as a tenant?"

    Annotations the server declares

    • title: Company Exposure
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • equipment_trackerOn-site generation at data-center campuses as the records state it: turbine or engine maker, model, unit count, unit and total MW, status and planned online date, each with its quo…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    On-site generation at data-center campuses as the records state it: turbine or engine maker, model, unit count, unit and total MW, status and planned online date, each with its quoted source line; summarized by maker and model. Rows whose record names no maker say so. Requires a subscription. Example questions: - "Which turbine makers appear in data-center air permits?" - "How many Siemens SGT-800s are permitted?" - "Planned gas generation at data-center campuses in Texas"

    Annotations the server declares

    • title: Equipment Tracker
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • exportA download link (valid 24 hours) for ledger rows with record dates, first-seen dates and source hashes: a CSV of events filtered by state, ticker, event type, start date or project…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    A download link (valid 24 hours) for ledger rows with record dates, first-seen dates and source hashes: a CSV of events filtered by state, ticker, event type, start date or project, or the full ledger as Parquet files (events, projects, and every value each field has held with the days it was first and last seen). Requires a subscription. Example questions: - "Export every Texas certification with first-seen dates as CSV" - "Give me the full ledger as Parquet for a backtest"

    Annotations the server declares

    • title: Export
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • project_detailOne data-center project in full: every named party and role with its ticker link (parent, method, confidence, evidence), on-site power (technology, maker, model, unit count, MW, wi…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    One data-center project in full: every named party and role with its ticker link (parent, method, confidence, evidence), on-site power (technology, maker, model, unit count, MW, with the quoted source line), the dated timeline of records, coordinates where stated, and each source's publisher, URL, retrieval time and file hash. Takes a project id from another tool, or a name. Example questions: - "Who is behind Cipher's Barber Lake site?" - "What turbines are permitted at Project Matador?" - "Show the record for TX4"

    Annotations the server declares

    • title: Project Detail
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • whats_newDated events on US data-center projects, newest first: Texas certifications, air-permit filings and listings, planned on-site generators, rezonings, moratoria, abatements and other…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Dated events on US data-center projects, newest first: Texas certifications, air-permit filings and listings, planned on-site generators, rezonings, moratoria, abatements and other city/county agenda items, and changes this ledger detected (status, tenant, delisting). Each event has its project, place, tenant or operator, tickers, the record link and a project page link. Returns the true total. Example questions: - "What data centers got certified in Texas this month?" - "Which counties voted on data-center moratoria lately?" - "Any new data-center air permits in Virginia?"

    Annotations the server declares

    • title: What's New
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 2Show 2 read-only tools
  • find_projectsSearches US data-center projects in the public record by state, county, city, tenant (Texas occupant), operator or permittee, any named party, ticker, status, on-site gas generatio…No findings

    Why it is in this group

    • The name "find_projects" says "find": a word for reading.
    Description, as the server wrote it
    Searches US data-center projects in the public record by state, county, city, tenant (Texas occupant), operator or permittee, any named party, ticker, status, on-site gas generation, source or name. Each row gives status, tenant, operator, resolved tickers, private parents, stated on-site MW, the record link and a page link, plus the true total of matches. Example questions: - "Which Texas data centers list Amazon as the tenant?" - "Planned data centers in Loudoun County with air permits" - "Data-center campuses with on-site gas turbines"

    Annotations the server declares

    • title: Find Projects
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • pipeline_seriesCounts of data-center events or projects over time (by month, quarter or year), grouped by state, ticker, event type or source, dated by the record's own date or by first-seen date…No findings

    Why it is in this group

    • The description's first verb is "count": a word for reading.
    Description, as the server wrote it
    Counts of data-center events or projects over time (by month, quarter or year), grouped by state, ticker, event type or source, dated by the record's own date or by first-seen date. Requires a subscription. Example questions: - "Texas data-center certifications per quarter since 2023" - "Monthly moratorium and rezoning items by state this year" - "Certifications by tenant ticker per year"

    Annotations the server declares

    • title: Pipeline Series
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 21, 2026, 19:19 UTC, unchanged since Nov 21, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
5
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://aibuildoutpermits.vercel.app/.well-known/oauth-protected-resource/mcp
Authorization servers
https://aibuildoutpermits.vercel.app
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
yes
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://aibuildoutpermits.vercel.app/mcp: tools/list returned 7 tools to an anonymous client, including whats_new (write), project_detail (write), company_exposure (write), equipment_tracker (write), export (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http ai-buildout-permits https://aibuildoutpermits.vercel.app/mcp
claude mcp add --transport http ai-buildout-permits https://aibuildoutpermits.vercel.app/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__ai-buildout-permits__find_projects",
      "mcp__ai-buildout-permits__pipeline_series"
    ],
    "ask": [
      "mcp__ai-buildout-permits__whats_new",
      "mcp__ai-buildout-permits__project_detail",
      "mcp__ai-buildout-permits__company_exposure",
      "mcp__ai-buildout-permits__equipment_tracker",
      "mcp__ai-buildout-permits__export"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as ai-buildout-permits. Review it before you use it.

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.2016judea/ai-buildout-permits/verify?hash=bec4bb9ef14e1de32d2a31cbad889dcde00fcfcfa07867946013fbbbe27ff058" | jq -e '.changed == false'

Pinned hash bec4bb9ef14e, from Nov 21, 2026, 00:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.2016judea/ai-buildout-permits/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.2016judea/ai-buildout-permits
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.2016judea/ai-buildout-permits.svg)](https://radar.anlyon.com/servers/io.github.2016judea/ai-buildout-permits)

Source: MCP Registry · repository. Synced Nov 21, 2026, 00:17 UTC.

AI Buildout Permits MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the AI Buildout Permits MCP server safe?

No scan can promise that. What its definitions show: 7 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the AI Buildout Permits MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the AI Buildout Permits MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the AI Buildout Permits MCP server have?

7 tools: 5 write, 2 read. whats_new, project_detail, company_exposure, equipment_tracker, export, find_projects and pipeline_series.

Does the AI Buildout Permits MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the AI Buildout Permits MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the AI Buildout Permits MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.