What can you do with this server?

A read-only MCP lookup server (OpenLookup, by Compound Labs) that answers time-sensitive questions about AI models, developer tools, services, and compliance using live public data — no API key needed. * Compare AI models — current pricing and which models major coding tools actually route to, ranked by adoption across budget bands or by tool (Claude Code, Codex CLI, Cline, Aider). * Check project maintenance — last release/commit and whether a dependency reads as dead before you recommend it. * Look up service pricing — published prices and free-tier limits for auth, database, payments, email, hosting, each with a last-verified date. * Estimate stack cost — itemised monthly bill for a named stack at a given user count, separating base-fee from metered lines. * Search agent skills — published Claude Code skills, plugins and marketplaces ranked by installs, returning the install command. * Search agent configs — real AGENTS.md/CLAUDE.md/Cursor/Copilot/etc. files from public repos, scored for quality. * Search component registries — shadcn-compatible components, blocks and hooks with dependencies. * Grade starter kits — boilerplates graded by actually installing them, not by their README. * Compare app builders — whether AI mobile-app builders' output clears App Store review, with sourced verdicts (or unknown). * ADA accessibility lookup (lookup_ada_report) — grade A–F, WCAG 2.1 AA violation counts and failing rules for a local-government .gov domain, plus its Title II deadline (Apr 2027/2028) and public report URL. * Nonprofit status lookup (lookup_nonprofit_status) — checks an EIN against IRS auto-revocation and California charity delinquency/suspension lists; returns revocation/reinstatement dates, 15-month reinstatement window, AB 488 donation-blocking status, and a checked receipt of sources and scope. * Note: the supplied schema exposes only the two compliance tools (lookup_ada_report, lookup_nonprofit_status); the README advertises eleven total, runnable via npx -y openlookup over stdio or --http.

Which integrations are available for this server?

Provides a tool for evaluating whether apps built by AI mobile-app builders will clear Apple App Store review, covering output details, source exportability, binary submission, and applicable guidelines.

How do I use compound-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@compound-mcp Is austintexas.gov ADA compliant?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

compound-mcp

by kyisaiah47

Overview Schema Source Related Servers Discussions Admin

JavaScript

Remote

A read-only MCP lookup server (OpenLookup, by Compound Labs) that answers time-sensitive questions about AI models, developer tools, services, and compliance using live public data — no API key needed.

Compare AI models — current pricing and which models major coding tools actually route to, ranked by adoption across budget bands or by tool (Claude Code, Codex CLI, Cline, Aider).
Check project maintenance — last release/commit and whether a dependency reads as dead before you recommend it.
Look up service pricing — published prices and free-tier limits for auth, database, payments, email, hosting, each with a last-verified date.
Estimate stack cost — itemised monthly bill for a named stack at a given user count, separating base-fee from metered lines.
Search agent skills — published Claude Code skills, plugins and marketplaces ranked by installs, returning the install command.
Search agent configs — real AGENTS.md/CLAUDE.md/Cursor/Copilot/etc. files from public repos, scored for quality.
Search component registries — shadcn-compatible components, blocks and hooks with dependencies.
Grade starter kits — boilerplates graded by actually installing them, not by their README.
Compare app builders — whether AI mobile-app builders' output clears App Store review, with sourced verdicts (or unknown).
ADA accessibility lookup (lookup_ada_report) — grade A–F, WCAG 2.1 AA violation counts and failing rules for a local-government .gov domain, plus its Title II deadline (Apr 2027/2028) and public report URL.
Nonprofit status lookup (lookup_nonprofit_status) — checks an EIN against IRS auto-revocation and California charity delinquency/suspension lists; returns revocation/reinstatement dates, 15-month reinstatement window, AB 488 donation-blocking status, and a checked receipt of sources and scope.
Note: the supplied schema exposes only the two compliance tools (lookup_ada_report, lookup_nonprofit_status); the README advertises eleven total, runnable via npx -y openlookup over stdio or --http.

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 OpenLookup tools answer questions that a model cannot answer correctly from its training cutoff. The underlying facts change after training, including current model costs, library maintenance, and whether someone has published a skill you plan to write.

Tools

Facts that change over time

Tool	Answers
`compare_ai_models(board?, limit?)`	Current AI model pricing and which models the major coding tools actually route to, sampled nightly. Boards by budget band (`budget/free` … `budget/premium`) or by tool (`tool/claude-code`, `tool/codex-cli`, `tool/cline`, `tool/aider`, …). Ranked on adoption, not capability — each row carries the rationale that says so.
`check_project_maintenance(q?, limit?)`	Whether a developer tool is still shipping: last release, last commit, whether it reads as dead. Run it before recommending a dependency.
`lookup_service_pricing(category?, service?)`	Published pricing and free-tier limits for auth, database, payments, email and hosting services — each plan carrying the date its published price was last verified against the vendor's own page.
`estimate_stack_cost(stack, users?)`	An itemised monthly bill for a named stack at a chosen user count, showing which lines are included in the base fee and which are metered.

Directories

Tool	Answers
`search_agent_skills(q, kind?, limit?)`	Published Claude Code skills, plugins and marketplaces, ranked by installs. Returns the install command, so the answer is directly actionable.
`search_agent_configs(stack?, format?, tag?, min_quality?, limit?)`	Real `AGENTS.md`, `CLAUDE.md`, Cursor, Copilot, Windsurf, GEMINI.md and Cline files from public repositories, scored for quality — how well-maintained projects on a given stack actually write theirs.
`search_component_registries(q, kind?, access?, limit?)`	shadcn-compatible components, blocks and hooks across dozens of public registries, with their dependencies so you can judge the cost of pulling one in.
`grade_starter_kit(q?, limit?)`	Starter kits and boilerplates, graded by installing them: what is actually wired up versus what only appears in the README.
`compare_app_builders(builder?, verdict?, limit?)`	Whether the app an AI mobile-app builder hands you clears Apple App Store review — what it outputs, whether you can export the source, who submits the binary, and which guidelines are in play. Every verdict carries the source that settles it and the date it was read; an unsettled question comes back `unknown` rather than guessed.

Compliance

`lookup_ada_report(domain)`

OpenLookup looks up a US local-government domain in the [CivicBinder Municipal Web Accessibility Index](https://civicbinder.org/ada). The index uses axe-core scans of local-government .gov websites and grades them A–F against WCAG 2.1 AA. The index applies the April 26, 2027 ADA Title II deadline to communities of 50,000+ and the April 26, 2028 deadline to smaller communities and special districts.

The tool 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](https://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.

Related MCP server: propublica-npo-mcp

Install

npm install -g openlookup

Or run without installing: npx -y openlookup

Run

openlookup                # stdio (for MCP clients)
openlookup --http 8974    # streamable HTTP on http://localhost:8974/mcp

Claude Code

claude mcp add openlookup -- npx -y openlookup

Claude Desktop

Add the server to claude_desktop_config.json in Settings → Developer → Edit Config:

{
  "mcpServers": {
    "openlookup": {
      "command": "npx",
      "args": ["-y", "openlookup"]
    }
  }
}

Examples

Which model should I use for a coding agent on a budget?

compare_ai_models({ board: "budget/value", limit: 3 }) →

{
  "board": "budget/value",
  "captured_on": "2026-08-05",
  "models": [
    {
      "rank": 1,
      "model": "z-ai/glm-5.2",
      "blended_usd_per_mtok": 1.175,
      "price_band": "$1 to $5 / M",
      "rationale": "3.05T tokens through 6 tracked coding tools · ranked on usage, which measures adoption rather than capability."
    }
  ]
}

Is the city website at 36thdistrictcourtmi.gov ADA compliant?

lookup_ada_report("36thdistrictcourtmi.gov") →

{
  "found": true,
  "domain": "36thdistrictcourtmi.gov",
  "entity_name": "36th District Court",
  "grade": "A",
  "violations_total": 0,
  "ada_title_ii_deadline": "2027-04-26",
  "report_url": "https://civicbinder.org/ada/36thdistrictcourtmi.gov"
}

Health

The health check records three facts separately. A single health endpoint that ANDs them together cannot identify which fact failed.

npm run health          # the working tree, over stdio
npm run health:public   # npx -y openlookup@latest, resolved fresh from npm

Signal	What it answers
`initialize`	The process spawns and the MCP handshake completes.
`tools_list`	The server enumerates its tools. An error and an empty list are both failures.
`reachable`	Each public endpoint the tools read answers, right now. Recorded per host.
`tool_outcome`	Calling a tool returns a usable payload. Separate from `tools_list` on purpose: a tool can be advertised and not work.

--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. The health check flips a signal only when that run provides evidence for it. A timeout, a dead socket, and a signal that could not be attempted all remain failures with a reason. None of them becomes a pass. A finding exits 0 so a scheduled run cannot disarm itself during an outage. --strict exits non zero, and ops/npm/publish.mjs runs it after publishing.

Each run writes a dated receipt to ops/health/receipts/. The test at ops/health/probe.test.mjs breaks each signal separately and verifies that the health check keeps them separate.

Scheduled every 6 hours as compound.compound-mcp.health.

Compliance tool receipts

lookup_ada_report and lookup_nonprofit_status return the verdict and the lookup in separate fields. clear and grade contain the outcome. checked contains the receipt. The receipt records when the lookup ran, which lists or index it consulted, and what that coverage does not include. An agent can use the receipt to explain what it verified without running the lookup again.

{
  "ein": "475262842",
  "clear": true,
  "checked": {
    "at": "2026-09-20T14:36:34.257Z",
    "sources": [
      "IRS Automatic Revocation of Exemption List",
      "California Attorney General Registry of Charities and Fundraisers"
    ],
    "via": "https://goodstanding.thecompound.tech/api/lookup",
    "scope": "Covers only the two lists named above, as GoodStanding retains them. A clear result means the EIN is absent from those lists. It is not a statement that the organization was never revoked, and no other state registry is consulted."
  }
}

License

MIT © Compound Labs

Available Tools

2 tools

lookup_ada_reportLook up an ADA Title II website accessibility reportA

Look up a US local-government (.gov) domain in the CivicBinder Municipal Web Accessibility Index. Returns the accessibility grade (A-F), WCAG 2.1 AA violation counts from an axe-core scan, the failing rules, the entity's ADA Title II compliance deadline (April 2027 or April 2028), and a link to the full public report page. Use for questions like "is cityofx.gov ADA compliant" or "how accessible is this county website".

ParametersJSON Schema

Name	Required	Description	Default
`domain`	Yes	The .gov domain to look up, e.g. "denvergov.org" or "cityofmadison.com". Protocol and paths are stripped automatically.

TDQS

A4.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the full burden. It discloses what the tool returns in detail and implies a read-only operation via the verb 'look up'. It doesn't mention error handling for domains not in the index, but this is minor for a lookup tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is tightly written: it leads with the action, summarizes the return payload, gives example questions, and includes the protocol-stripping note. Every sentence earns its place without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter lookup with no output schema, the description fully covers what the tool does, what it returns, and when to use it. It is self-contained and sufficient for an agent to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already fully documents the single parameter. The description adds valuable behavior beyond the schema, noting that protocol and paths are stripped automatically, which helps the agent construct valid input.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the specific verb 'look up' and the resource 'CivicBinder Municipal Web Accessibility Index', and lists the specific return fields (grade, violation counts, failing rules, deadline, link). It clearly differentiates from the sibling tool lookup_nonprofit_status, which is about a different subject entirely.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear usage context with example questions ('is cityofx.gov ADA compliant') and explicit scope (.gov domains). It doesn't explicitly state when not to use it, but the sibling tool is obviously different in domain, so the guidance is adequate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

lookup_nonprofit_statusLook up nonprofit IRS / California good standing by EINA

Check a US nonprofit's standing by EIN against the IRS auto-revocation list (tax-exempt status revoked for three consecutive missed Form 990 filings) and California Registry of Charities delinquency/suspension lists. Returns revocation and reinstatement dates, whether the streamlined 15-month reinstatement window is still open, and whether AB 488 requires fundraising platforms to block donations. A "clear" result means the EIN is on none of the tracked lists.

ParametersJSON Schema

Name	Required	Description	Default
`ein`	Yes	The organization's 9-digit EIN, with or without a dash, e.g. "12-3456789".

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses key behavioral details: the data sources checked, the types of returned information, and the meaning of 'clear'. It does not mention any limitations, caching, or error conditions, but for a lookup tool this is quite transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded: two sentences, the first stating the main action and data sources, the second defining the key result. Every sentence adds value, with no fluff or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with one parameter, no output schema, and no annotations, the description is complete: it identifies the exact lists, the return values, and the meaning of a clear result. It gives the user sufficient understanding without needing to guess return structure or side effects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers 100% of the parameter 'ein' with a description and example. The tool description mentions 'by EIN' but adds no new meaning beyond the schema. Thus the baseline score of 3 applies; the description does not need to compensate for schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool checks a US nonprofit's standing by EIN against specific IRS and California lists, enumerating exactly what is checked (auto-revocation, delinquency/suspension) and what is returned (dates, reinstatement window, AB 488 effect). This distinguishes it from the sibling lookup_ada_report and uses a specific verb ('Check') with a well-defined resource.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context about the tool's scope (IRS and California lists) and what constitutes a 'clear' result, but it does not explicitly state when to use this tool versus alternatives or any exclusions. Since the sibling tool is not referenced, it lacks explicit when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

2 tool updatesv0.1.2Aug 1, 2026
- First observedlookup_ada_report
- First observedlookup_nonprofit_status

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.4/5.0

Scored 2026-08-01 18:35 across 2 tools

Disambiguation5/5

The two tools are completely distinct: one checks government website accessibility, the other checks nonprofit tax status. There is no overlap or ambiguity between them.

Naming Consistency5/5

Both tools follow the exact same 'lookup_*' pattern with a clear noun, making the naming consistent and predictable.

Tool Count4/5

With only two tools, the server is slightly under the typical range, but each tool addresses a specific, well-defined lookup need, so the count is reasonable for a niche server.

Completeness4/5

Each tool fully covers its intended lookup scenario (accessibility report and nonprofit status). No obvious missing operations exist for the stated purpose, though the overall scope is limited.

Maintenance

ActivityActive

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Related MCP Connectors

Propublica Nonprofit A
io.github.pipeworx-io
ProPublica Nonprofit MCP — ProPublica Nonprofit Explorer API (free, no auth)
Open Data Government Data
392
Vett Compliance MCP Server
io.github.Gorp405
Sanctions, PEP, watchlist, recall, business, and contract screening. Free tier, no auth required.
Legal & Compliance Finance
1
CyberMax Data A
io.github.shawmena-dotcom
Free US data lookups: ZIP demographics, CISA KEV/EPSS CVEs, domain rank, county spending, recalls.
Government Data Open Data
71
CyberMax Data A
io.github.CyberMax-tools
Free US data lookups: ZIP demographics, CISA KEV/EPSS CVEs, domain rank, county spending, recalls.
Government Data Open Data Research & Data
71

Related MCP Servers

Charity MCP Server
Government Data Search Open Data
briancasteel
F
license
A
quality
D
maintenance
Enables AI assistants to look up IRS nonprofit data, verify tax-deductible charity status, and search for organizations by name or location using the CharityAPI database.
Updated a year ago (2025-06-20 19:38 UTC)
4
3
-
propublica-npo-mcp
Government Data Open Data Research & Data
2b3pro
A
license
A
quality
D
maintenance
Provides tools to search and retrieve nonprofit organization data and IRS filing summaries from ProPublica's Nonprofit Explorer, including side-by-side comparisons.
Updated 5 months ago (2026-04-27 01:42 UTC)
4
MIT
DataNexus MCPofficial
Government Data Legal & Compliance Security
datanexusmcp
A
license
A
quality
B
maintenance
Provides AI-ready access to US/UK nonprofit data and OSS vulnerability intelligence via MCP, with 10 tools and no API key required.
Updated 7 days ago (2026-09-26 06:21 UTC)
55
108 npm
3
Business Source 1.1
gocreative-mcp
Government Data Finance Cryptocurrency
ColinHughes2121
F
license
Not graded
quality
B
maintenance
Keyless, pay-per-call compliance & regulated-data tools for AI agents: OFAC wallet + sanctions/PEP + KYB screening, SEC filings, FRED economics, FDA recalls, federal awards, and continuous monitoring (watch a wallet/company/brand for status changes). USDC via x402 on Base/Solana, no API key, no signup.
Updated 3 months ago (2026-06-25 15:22 UTC)
-

OpenLookup

Tools

Facts that change over time

Directories

Compliance

lookup_ada_report(domain)

lookup_nonprofit_status(ein)

Install

Run

Claude Code

Claude Desktop

Examples

Health

Compliance tool receipts

License

Available Tools

TDQS

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Charity MCP Server

propublica-npo-mcp

DataNexus MCPofficial

gocreative-mcp

`lookup_ada_report(domain)`

`lookup_nonprofit_status(ein)`