Claude, ChatGPT, Copilot and Gemini connector · AI-first
Connect your CauseComp account to Claude, ChatGPT, Copilot or Gemini once, then ask for executive compensation benchmarks and workforce salary ranges in plain English — powered by the same engine behind our web tools. 850+ workforce roles and §4958 comparability data.
The CauseComp connector works wherever you use Claude — connect it once and it follows your Claude account: claude.ai, the Claude desktop app, and Claude's integrations inside other tools where connectors are enabled. There are no API keys to copy for the one-click path — you sign in with your CauseComp account and approve access.
Fastest: add CauseComp from Claude's connector directory. Open CauseComp in the Claude directory, click Connect, sign in with your CauseComp account and allow access. No URL to paste.
In Claude, go to Settings → Connectors, click Add, then Add custom connector.
Name: CauseComp
Remote MCP server URL: https://mcp.causecomp.org/mcp
Leave everything under Advanced settings — OAuth Client ID and OAuth Client Secret — blank; sign-in comes next, no keys to paste. Then click Add.
Click Connect on the new CauseComp row, sign in with your CauseComp account, and Allow — you're benchmarking.
CauseComp is in ChatGPT's app directory.
The directory listing is available to ChatGPT accounts in the US. Elsewhere, add CauseComp as a custom MCP server using the steps below.
Open CauseComp in ChatGPT, or search for CauseComp in ChatGPT's app directory.
Click Install plugin, sign in with your CauseComp account and click Allow.
In any chat, type @ and pick CauseComp, then ask your question. Pick it again whenever a new question needs CauseComp data.
You can also add CauseComp yourself in the ChatGPT website.
In ChatGPT, open Plugins in the sidebar, click Add, then Add custom MCP server.
Name: CauseComp
Connection (Server URL): https://mcp.causecomp.org/mcp
Authentication: OAuth (already selected)
Leave the icon, description and Advanced OAuth settings as they are. Tick I understand and want to continue, then click Create as a plugin.
Sign in with your CauseComp account when asked, and click Allow.
In any chat, type @ and pick CauseComp, then ask your question. Pick it again whenever a new question needs CauseComp data.
ChatGPT changes these menus from time to time. If something looks different, OpenAI's current steps are here.
Who can add it: you can add it yourself in ChatGPT. On ChatGPT Business, only workspace admins and owners can add a custom MCP server; on Enterprise, admins can grant the permission to members.
The MCP server URL is the same one Claude uses: https://mcp.causecomp.org/mcp
In a terminal, run:
gemini mcp add --transport http --scope user causecomp https://mcp.causecomp.org/mcp
Start Gemini CLI and type /mcp auth causecomp. Your browser opens. Sign in with your CauseComp account and click Allow.
Try "Use CauseComp to benchmark CEO pay for a $20M human services nonprofit in Ohio."
Signing in needs a browser on the same computer. On a remote server, use an API key from your account page instead: add --header "Authorization: Bearer YOUR_KEY" to the command in step 1.
Gemini CLI changes these commands from time to time. If something looks different, Google's current steps are here.
In the Gemini app, open Settings, then Connected Apps, and click Add a custom app.
Enter https://mcp.causecomp.org/mcp. That is the only field you need.
Your browser opens. Sign in with your CauseComp account and click Allow.
Try "Use CauseComp to benchmark CEO pay for a $20M human services nonprofit in Ohio."
Google changes these menus from time to time. If something looks different, Google's current steps are here.
Add CauseComp to a Copilot Studio agent as a Model Context Protocol tool.
In Copilot Studio, open your agent, go to Tools, select Add a tool, then New tool, then Model Context Protocol.
Server name: CauseComp
Server description: Nonprofit executive and workforce compensation benchmarks
Server URL: https://mcp.causecomp.org/mcp
Authentication: OAuth 2.0, then Dynamic discovery. Leave the client ID and secret fields blank. Select Create, then Next.
Select Create a new connection, click Create, sign in with your CauseComp account and click Allow. Then select Add to agent.
Ask your agent a compensation question. It calls CauseComp when the question needs CauseComp data.
Microsoft changes these menus from time to time. If something looks different, Microsoft's current steps are here.
Who can add it: anyone who can edit the agent in Copilot Studio. Your organization's admins may limit who can add tools or connections.
In Claude, ChatGPT, Copilot or Gemini, the connector requires a CauseComp Professional-plan account, and you sign in with OAuth when you connect.
Ask in plain English. Claude calls CauseComp and returns the percentiles, the data vintage, and the disclaimer. When a state, sector, or role isn't recognized, the response is a correction carrying the valid labels, not a guess.
Name the role, sector, state and revenue in your question. To compare with specific organizations, list them by name or EIN. Ask for a board report PDF when you are ready to share.
Something not working? See Troubleshooting.
Professional The connector is a Professional feature. Through it, Claude reaches the full toolset — both engines and the compliance layer:
Officer and leadership pay from IRS Form 990 filings, by budget size, sector, state or metro, with P10–P90 and pay components (base, bonus, other, retirement and deferred, nontaxable) modelled as shares of the total from the filings that itemize them. Narrow to a 501(c) type or an NTEE subsector such as P20. Project the figures to a date you choose, at CauseComp's measured pay growth rate or one you supply — a projected figure always says that it is.
Broad-based workforce pay across 850+ roles and ~390 metros, from BLS wage data — nonprofit or private-sector, by career level and headcount, with the geography actually used (metro, state, or national) stated on every answer.
The §4958 comparables set for the same inputs as an executive benchmark, with what each reported, and a composition line on every set: how many peers, how many in your state and sector, and the size of the national pool.
Hand Claude your board's comparables by name or EIN, in any mix, and get what those organizations filed for the role in the last five years instead of a modelled cohort. Any organization without a filing in that window is flagged, with the reason, rather than silently left out. Ask for EINs on every row, and add a city to tell same-named organizations apart.
Rank the peer set across a list of sectors or all of them, one role per request. Bring your own peer list to see every officer role those organizations filed. The benchmark itself stays the sector you asked for.
Vocabulary tools that return the exact role, sector, state, and metro labels the engine accepts. An unrecognized value returns a correction; it is not mapped to a nearby label.
Ask for the board-ready §4958 PDF itself, not just the numbers: the same document the website generates, with the modeled benchmark, the comparables and their own P10–P90 ladder, the composition sentence, and the disclaimer. The result carries a download link to the PDF.
Look up nonprofits with a filing in the last five years in the comparables index and get each one's EIN, city, state, sector, revenue band and latest filing year. Up to 20 candidates, in alphabetical order with no ranking, so you choose. A peer set accepts the EINs it returns.
Ask how a number was built and Claude gets the published methodology by section, live from the same /methodology page you can read yourself. There is no second copy to drift from it.
The connector and the API are Professional features. See plans & pricing
Calling the API from your own code, or using a Model Context Protocol client that can't sign in with OAuth? Create an API key on your account page. Claude, ChatGPT, Copilot and Gemini CLI connect with OAuth sign-in and don't need one. See the API & connector docs for setup.
You connect with OAuth, in Claude, ChatGPT, Copilot or Gemini CLI. None of them sees your CauseComp password, and CauseComp never sees your account with them.
Disconnect the connector or revoke any API key from your account page whenever you want; access stops immediately.
Each account carries a daily request quota, so a shared or leaked key can't run away with your usage.
Every request checks your current plan — access always matches your subscription, nothing is baked into a token.
Questions
A connector that lets Claude answer nonprofit compensation questions using your CauseComp account — executive pay from IRS Form 990 filings and workforce pay from BLS data. Add it once in Claude's connector settings and sign in with your CauseComp account; Claude then calls the same benchmarking engine that powers the web tools.
In Claude, open Settings → Connectors, click Add, then Add custom connector. For Name enter CauseComp, and for Remote MCP server URL enter https://mcp.causecomp.org/mcp. Leave the Advanced settings fields (OAuth Client ID and OAuth Client Secret) blank, then click Add. Click Connect on the CauseComp row, sign in with your CauseComp account, and Allow — no API keys to copy for the one-click connector.
The Professional plan. The connector, the §4958 comparables data, and executive and workforce benchmarks are all included in Professional. The connector resolves your live plan on every request.
Yes. The one-click connector works in the Claude desktop app the same way as on claude.ai — connect once in Settings → Connectors and it follows your Claude account, including Claude's integrations in tools like Word and Excel where connectors are enabled. For other MCP clients, such as Gemini CLI or Copilot Studio, connect with OAuth sign-in if the client supports it (see the steps above). Otherwise create an API key on your CauseComp account page.
You sign in with OAuth, so passwords are never shared. Revoke the connection or any API key at any time from your account page, and each key has a daily request quota.
Claude is a trademark of Anthropic, PBC. CauseComp is not affiliated with or endorsed by Anthropic. ChatGPT is a trademark of OpenAI. CauseComp is not affiliated with or endorsed by OpenAI. Microsoft and Copilot are trademarks of the Microsoft group of companies. CauseComp is not affiliated with or endorsed by Microsoft. Gemini is a trademark of Google LLC. CauseComp is not affiliated with or endorsed by Google.