Index / MCP servers / Archive

Archive MCP server

Archive is a remote MCP server that gives an AI agent 8 tools, among them budget_history, document, list_datasets. It answers at https://lunenburgbudgetproject.org/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 12 September 2026; the last check, on 24 October 2026, succeeded.

Status
Answering
Tools
8
Official
yes, served from lunenburgbudgetproject.org
Reliability
6 of 6 checks
Response time
228 ms
Transport
streamable HTTP
Last checked
24 October 2026

The Lunenburg, Massachusetts town and school budget, every figure traced to its source document.

Description as the publisher wrote it.

The 8 tools Archive offers

ToolWhat it does
budget_historyWhat a school budget line was in each year, AT ONE STAGE. The stage argument is required and singular on purpose: `proposed`, `settled` and `actual` are three different documents about the same year, and a growth rate measured from an actua
Inputs: label, stage
documentWhere a document came from: the publisher's URL, our copy, and its sha256 so a reader can check they have the same bytes. Use it to cite anything.
Inputs: name
list_datasetsEvery dataset in the archive, with THE YEARS EACH COVERS, its row count and its size. Call this before answering from prose: it is how you find out whether the archive holds data for the year and subject you are being asked about. 49 datase
queryAny question the other tools do not cover, as one read-only SQL statement over the archive database. SELECT or WITH only; a LIMIT is imposed if you omit one. Call `read_first` before computing anything and `list_datasets` to find table name
Inputs: sql
read_firstThe grain of every table and the specific ways to get a confident wrong answer out of this data. Read this before computing anything. It states, among others, that a budget and an actual must never be combined in one calculation; that a bud
search_meetingsWhich of the 1,422 published town meeting documents contain a word — every board, 2025 onward. Returns the board, the date and a citable URL for each. AN EMPTY RESULT MEANS THE WORD IS NOT IN THE INDEXED DOCUMENTS, which is not the same as
Inputs: word, board
staffHow many people the town PRINTED on a school staff roster, by year, school and kind of job. Uses our classification of the printed title, never the title itself, because the town has called the same job Tutor, Aide, Paraprofessional, Para,
Inputs: fy, category
worked_examples107 questions this archive can answer, each with the SQL that answers it. Every one is executed against the database on every build, so none of them is a claim. Start from the nearest one and edit it rather than writing a query from scratch

Add Archive to your AI client

Every block below points at https://lunenburgbudgetproject.org/mcp. Pick your client and copy.

Claude Code: one command in your terminal
claude mcp add --transport http archive https://lunenburgbudgetproject.org/mcp
Claude Desktop: claude_desktop_config.json
{
  "mcpServers": {
    "archive": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://lunenburgbudgetproject.org/mcp"]
    }
  }
}
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
{
  "mcpServers": {
    "archive": {
      "url": "https://lunenburgbudgetproject.org/mcp"
    }
  }
}
VS Code and GitHub Copilot: .vscode/mcp.json
{
  "servers": {
    "archive": {
      "type": "http",
      "url": "https://lunenburgbudgetproject.org/mcp"
    }
  }
}
Zed: Zed settings.json
{
  "context_servers": {
    "archive": {
      "url": "https://lunenburgbudgetproject.org/mcp"
    }
  }
}
Windsurf: ~/.codeium/mcp_config.json
{
  "mcpServers": {
    "archive": {
      "serverUrl": "https://lunenburgbudgetproject.org/mcp"
    }
  }
}
JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON
{
  "mcpServers": {
    "archive": {
      "url": "https://lunenburgbudgetproject.org/mcp"
    }
  }
}
Continue: .continue/mcpServers/neuronto.yaml
name: Archive
version: 0.0.1
schema: v1
mcpServers:
  - name: Archive
    type: streamable-http
    url: https://lunenburgbudgetproject.org/mcp
Gemini CLI: ~/.gemini/settings.json
{
  "mcpServers": {
    "archive": {
      "httpUrl": "https://lunenburgbudgetproject.org/mcp"
    }
  }
}
Codex CLI: MCP server config
{
  "mcpServers": {
    "archive": {
      "type": "http",
      "url": "https://lunenburgbudgetproject.org/mcp"
    }
  }
}
Warp: MCP servers, + Add, paste JSON
{
  "mcpServers": {
    "archive": {
      "url": "https://lunenburgbudgetproject.org/mcp"
    }
  }
}
Goose: a one-click extension link
goose://extension?url=https%3A%2F%2Flunenburgbudgetproject.org%2Fmcp&type=streamable_http&id=archive&name=Archive

Is Archive up right now?

It answered our last check on 24 October 2026 in 228 ms. Over 6 checks since 12 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to Archive

Questions about Archive

Is there an official Archive MCP server?

Yes. It is published by lunenburgbudgetproject.org and served from lunenburgbudgetproject.org, the vendor's own domain: https://lunenburgbudgetproject.org/mcp.

How many tools does Archive have?

8, as returned by the server's own tools/list on 23 September 2026: budget_history, document, list_datasets, query, read_first, search_meetings, staff, worked_examples.

Is Archive down?

It answered our last check on 24 October 2026 in 228 ms. Over 6 checks since 12 September 2026 it answered 6.

How do I add Archive to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://lunenburgbudgetproject.org/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does Archive need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: org.lunenburgbudgetproject. Endpoint host: lunenburgbudgetproject.org. ARD identifier: urn:air:org.lunenburgbudgetproject:mcp:archive. First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.