Todd Schiller - Bostonhttps://toddschiller.com/2026-05-30T00:00:00-04:00Human ✘ Artificial IntelligenceLetting OpenClaw loose on Boston's open data2026-05-30T00:00:00-04:002026-05-30T00:00:00-04:00Todd Schillertag:toddschiller.com,2026-05-30:/blog/openclaw-boston-open-data.htmlAt the Boston OpenClaw 2026 hackathon, I let an agent autonomously connect to the city's open-data MCP server, devise its own corruption-signal queries on contract data, and package the workflow as a reusable Claude skill.<p>Today was
the <a href="https://partiful.com/e/eBd91pZJpdTRp8V3FJFJ">Boston OpenClaw Hackathon</a>,
which had a theme of using the <a href="https://data.boston.gov/">Boston open data hub</a>.</p>
<p>For my project, I wanted to see how far OpenClaw could get on its own in
analyzing the data (with Claude Sonnet 4.6 as a backing model).</p>
<p>First, I had OpenClaw connect itself to the MCP server, starting from the press
release about the launch of
the <a href="https://data.boston.gov/showcase/opencontext-democratizing-the-city-of-boston-s-open-data-currently-in-beta">MCP server</a>.</p>
<p>Once connected, I asked it to analyze contracts for signs of corruption. It was
able to come up with its own approach for signals and queries. For example:
"Departments Using the Most Limited Competition", "Top Vendors by Limited
Competition Value", and "Bid Threshold Clustering (near $10K)".</p>
<!-- markdownlint-disable MD013 -->
<img loading="lazy" decoding="async" src="https://toddschiller.com/assets/openclaw-boston-open-data/boston-limited-competition-table.png" alt="OpenClaw output: a table of Boston departments ranked by share of limited-competition contracts (FY2019–FY2026 Q3, departments with 10+ contracts). Law Department 95.1% (155 of 163), Labor Relations 87.2%, Mandatory Appropriations 83.3%, Assessing Department 74.4%, Budget Management 66.7%, Snow & Winter Management 55.2%.">
<!-- markdownlint-enable MD013 -->
<p>After flagging companies, I had it analyze those companies' connections to city
officials.</p>
<p>There were some interesting nuggets! For example, Capitol Waste Services was
flagged as high
risk for having $285M in historic contracts, of which $136M were awarded with
limited competition.</p>
<p>The connection research flagged a 2015 fine of $120,000 by the Office of
Campaign and Political Financing (OCPF)
<a href="https://valleypatriot.com/capitol-waste-services-fined-120k-for-illegal-secret-donations-to-candidates/">for illegal campaign donations</a>.</p>
<p>From there, I had OpenClaw create and package a skill for flagging corruption
signals. The skill encodes the queries and data analysis scripts it developed.
That skill is available here:
<a href="https://toddschiller.com/assets/openclaw-boston-open-data/boston-contract-corruption.skill">boston-contract-corruption.skill</a>.</p>
<p>Some other interesting questions OpenClaw was able to answer from the data:</p>
<ul>
<li>Which restaurants are the worst health code offenders but haven't been shut
down yet?</li>
<li>Which roads/intersections are the worst for biking, based on pothole reports
and accidents?</li>
</ul>
<p>Overall, it was a fun experiment to see how AI agents might impact civic tech. A
big thanks to the hackathon organizers, everyone who demoed, and the city of
Boston for making this data available!</p>