Anchorage Open Checkbook MCP
Read-only MCP server providing tools over Municipality of Anchorage's expenditure, payroll, procurement, and revenue data, with duplicates filtered by default.
README
OpenContext — Anchorage Open Checkbook fork
<p align="center"> <img src="docs/opencontext_logo.png" alt="OpenContext Logo" width="400"> </p>
This fork of OpenContext
deploys the Anchorage Open Checkbook MCP (anchorage_checkbook
plugin) — read-only tools over the Municipality of Anchorage's
unaudited expenditure, payroll, procurement, and revenue tables, with
the dataset's traps (duplicate double-loads, snapshot dates, net
amounts, unnormalized vendor names) encoded in tool behavior. See
docs/CHECKBOOK.md and
METHODOLOGY.md — this server's totals deliberately
differ from the public MOA dashboard (duplicates are filtered by
default).
Quick Start
# 1. Configure (this fork ships its config ready to go)
cp config-anchorage-checkbook.yaml config.yaml
# 2. Test locally
pip install aiohttp
python3 scripts/local_server.py
# 3. Deploy
./scripts/deploy.sh --environment staging
Connect via Claude Connectors (same steps on both Claude.ai and Claude Desktop):
- Go to Settings → Connectors (or Customize → Connectors on claude.ai)
- Click Add custom connector
- Enter a name (e.g. "Boston OpenData") and your API Gateway URL
Get the URL: cd terraform/aws && terraform output -raw api_gateway_url
See Getting Started for full setup.
Documentation
| Doc | Description |
|---|---|
| Getting Started | Setup and usage |
| Architecture | System design and plugins |
| Deployment | AWS, Terraform, monitoring |
| Testing | Local testing (Terminal, Claude, MCP Inspector) |
| Anchorage Checkbook | Open Checkbook MCP server (this fork's plugin) |
| Methodology | The dedup-by-default decision and why totals differ from the MOA dashboard |
| Anchorage Parcels | Parcel/assessment MCP server (deployed from its own fork) |
Examples
- Boston OpenData (CKAN): examples/boston-opendata/config.yaml
- Custom plugin: examples/custom-plugin/
Contributing
Pre-commit hooks (optional):
pip install pre-commit
pre-commit install
Hooks: Ruff, yamllint, gofmt. Run manually: pre-commit run --all-files.
License
MIT — see LICENSE.
Author: Srihari Raman, City of Boston Department of Innovation and Technology
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.