
OpenLookup
tech.thecompoundv0.5.1Updated Oct 2, 2026
OpenLookup: eleven keyless lookups. Model pricing, dep health, stack cost, registries.
Overview
Gives an assistant eleven keyless read-only lookups for current AI model pricing, dependency health, service pricing, stack costs, and developer directories.
- What it does
- OpenLookup exposes eleven read-only tools backed by live public data. They cover current AI model pricing and which models major coding tools route to, whether a developer tool is still shipping, published pricing and free tiers for auth, database, payments, email and hosting services, and an itemised monthly stack cost estimate. Directory tools search published Claude Code skills and plugins, real agent config files from public repositories, shadcn-compatible component registries, graded starter kits, and AI mobile-app builders against App Store review. Two compliance lookups check a US local-government domain against a municipal web accessibility index and a nonprofit EIN against IRS and
- When to use it
- Use it when an assistant must answer questions that a training cutoff makes unreliable: what a model costs today, whether a library is still maintained, what a service's current free tier is, or whether a skill or component already exists. Also useful before recommending a dependency or estimating a stack bill, and for quick accessibility or nonprofit-status checks on public records.
- Requirements
- Runs locally as a stdio process; Node.js and npm are needed. Install globally with npm install -g openlookup, or run without installing via npx -y openlookup. No API key, signup, account, environment variable, or header is required. The tools read live public endpoints, so network access is needed. An optional streamable HTTP mode is available on a local port. Desktop only.
Installation
In SourceWeft
- Open OpenLookup in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
OpenLookup
MCP server from Compound Labs. Eleven read-only lookup tools backed by live public data — no API key, no signup, nothing to sign up for.
mcp-name: tech.thecompound/openlookup
OpenLookup was published on npm as compound-mcp until 2026-10-02. That package is deprecated and points here. Install openlookup instead.
Most of these answer questions that a model cannot answer correctly from a training cutoff, because the underlying fact changed after it: what a model costs today, whether a library is still maintained, whether someone has already published the skill you are about to write.
Tools
Things that go stale
Directories
Compliance
lookup_ada_report(domain)
Looks up a US local-government domain in the CivicBinder Municipal Web Accessibility Index — axe-core scans of local-government .gov websites, graded A–F against WCAG 2.1 AA ahead of the ADA Title II deadlines (April 26, 2027 for communities of 50,000+; April 26, 2028 for smaller communities and special districts).
Returns the grade, violation counts (total / serious / critical), the top failing rules, the entity's deadline, and the public report page (https://civicbinder.org/ada/<domain>). The full index is also published as an open dataset at civicbinder.org/ada/dataset.json.
lookup_nonprofit_status(ein)
Checks a nonprofit's EIN against the IRS auto-revocation list and the California Registry of Charities delinquency/suspension lists, via GoodStanding. Returns revocation and reinstatement dates, whether the streamlined 15-month reinstatement window is still open, and whether AB 488 requires charitable fundraising platforms to block the organization's donation pages. A clear: true result means the EIN is on none of the tracked lists.
Install
Or run without installing: npx -y openlookup
Run
Claude Code
Claude Desktop
Add to claude_desktop_config.json (Settings → Developer → Edit Config):
Examples
Which model should I use for a coding agent on a budget?
compare_ai_models({ board: "budget/value", limit: 3 }) →
Is the city website at 36thdistrictcourtmi.gov ADA compliant?
lookup_ada_report("36thdistrictcourtmi.gov") →
Health
Three facts, recorded separately, because a single health endpoint that ANDs them together cannot say which one broke.
--target public is the deployment check, and it is deliberately outside CI. openlookup has
no deployed HTTP endpoint, so the public path is npm: it spawns the published tarball through
npx, with a throwaway cache and from a neutral directory, so what answers is what a stranger
gets rather than this checkout. Build success and externally reachable protocol state are
different facts, and this repo has already shipped a version where they disagreed.
Every signal starts failed and is only flipped by evidence from that run. A timeout, a dead
socket and a signal that could not be attempted are all failures carrying a reason, never a
pass. A finding exits 0 so a scheduled run cannot disarm itself mid outage; --strict exits
non zero and is what ops/npm/publish.mjs runs after publishing.
Each run writes a dated receipt to ops/health/receipts/, and
ops/health/probe.test.mjs breaks each signal on its own to prove the separation is real.
Scheduled every 6 hours as compound.compound-mcp.health.
Receipts on the compliance tools
lookup_ada_report and lookup_nonprofit_status return the verdict and the lookup as separate
fields. clear and grade are the outcome. checked is the receipt: when the lookup ran,
which lists or index were consulted, and what that coverage does not include, so an agent can
explain what it verified without re-running it.
License
MIT © Compound Labs
Source: README.md at commit f7004bf
Tools
0Version history
1- v0.5.1LatestOct 2, 2026

