MCP Server
Connect Cursor, Claude, Grok, ChatGPT, Codex, Gemini CLI, Antigravity, VS Code, or any MCP client to Payments AI. Your agent can provision merchants, create products, open checkout, and search these docs without leaving the chat.
Stuck connecting? The connect page shows server status, one path for your client, and the check that proves it works.
Pick a surface
Payments AI exposes more than one surface to an agent. Start here, then follow the one that matches the job.
| You want to | Use |
|---|---|
| Give an agent the Payments AI tools | MCP server — the rest of this page |
| Build and test without touching live data | Sandbox MCP server — Sandbox MCP URL |
| Let an agent answer questions from these docs | search_payments_ai_docs, shipped with the MCP server |
| Teach an agent our conventions before it writes code | Skill — Agent discovery |
| Feed these docs to an agent that cannot speak MCP | llms.txt and raw Markdown — Agent discovery |
| Script merchants and products from a terminal or CI | CLI — Payments AI CLI |
| Call the API yourself, without an agent | Public API — Public API |
OAuth is the fastest path. No User MCP Key to copy. Your client opens a browser or prints a sign-in URL (in Claude Code run /mcp → Authenticate), you sign in, approve scopes, and tools appear.
{
"mcpServers": {
"payments-ai": {
"url": "https://mor.payments.ai/api/mcp"
}
}
}Connect with OAuth
Pick your client. Every path ends the same way: approve scopes in the browser, then your agent has the tools.
Setup prompt
Not sure which client you are in, or using one that is not listed? Paste this prompt and let the agent work out its own install path.
Install the Payments AI MCP server in this environment using OAuth. Do not ask me for a pai_mcp_* token.
Server name: payments-ai
URL: https://mor.payments.ai/api/mcp
Transport: Streamable HTTP
1. Detect which client you are (Cursor, Claude Code, Codex, Gemini CLI, Antigravity, VS Code, Grok, ChatGPT, or other).
2. Install with the matching command when a CLI exists:
- Claude Code: claude mcp add --transport http payments-ai https://mor.payments.ai/api/mcp
- Codex: codex mcp add payments-ai --url https://mor.payments.ai/api/mcp && codex mcp login payments-ai
- Gemini CLI: gemini mcp add --transport http payments-ai https://mor.payments.ai/api/mcp
- Antigravity: merge this into ~/.gemini/config/mcp_config.json (project: .agents/mcp_config.json). Use serverUrl, not url or httpUrl:
{ "mcpServers": { "payments-ai": { "serverUrl": "https://mor.payments.ai/api/mcp" } } }
- VS Code: code --add-mcp '{"name":"payments-ai","type":"http","url":"https://mor.payments.ai/api/mcp"}'
- Grok CLI: grok mcp add --transport http payments-ai https://mor.payments.ai/api/mcp
- Cursor: merge this into ~/.cursor/mcp.json and, if a project is open, .cursor/mcp.json:
{ "mcpServers": { "payments-ai": { "url": "https://mor.payments.ai/api/mcp" } } }
Then tell me to click Connect in Settings → MCP, or run: agent mcp login payments-ai
3. If no CLI matches, write the client config file and tell me the path.
4. After install, call whoami if tools are available. If not, tell me to reload MCP and approve OAuth, then retry.
5. Quote userId, host and endpoint from whoami. A 401 means not connected (quote its message); any tool error means connected but the call failed.Manual configuration
Add to your client’s MCP config, then restart Any agent.
{
"mcpServers": {
"payments-ai": {
"url": "https://mor.payments.ai/api/mcp"
}
}
}Fastest path
One click installs the server and opens the OAuth prompt.
Add to CursorOpens Cursor and pre-fills the server, then approve it in Settings → MCP.
Or let your agent do it
Tailored for Cursor. Paste this into the chat.
Add the Payments AI MCP server to Cursor using OAuth. Do not ask me for a token.
Merge this into ~/.cursor/mcp.json (and .cursor/mcp.json if a project is open):
{ "mcpServers": { "payments-ai": { "url": "https://mor.payments.ai/api/mcp" } } }
Then tell me to open Settings → MCP and click Connect.
Then call whoami and quote its userId, host and endpoint. An HTTP 401 means not connected: quote its message. A tool error means connected but the call failed: quote it.Manual configuration
Add to ~/.cursor/mcp.json, then restart Cursor.
{
"mcpServers": {
"payments-ai": {
"url": "https://mor.payments.ai/api/mcp"
}
}
}Client-side details: Cursor MCP documentation
Fastest path
One command. Claude Code opens a browser or prints a sign-in URL on first use; run `/mcp` → Authenticate.
claude mcp add --transport http payments-ai https://mor.payments.ai/api/mcpThen ask Claude Code to call whoami; it quotes your userId, host and endpoint.
Or let your agent do it
Tailored for Claude Code. Paste this into the chat.
Add the Payments AI MCP server to Claude Code using OAuth. Do not ask me for a token.
Run: claude mcp add --transport http payments-ai https://mor.payments.ai/api/mcp
If it needs authorising, run: claude mcp login payments-ai
Then call whoami and quote its userId, host and endpoint. An HTTP 401 means not connected: quote its message. A tool error means connected but the call failed: quote it.Manual configuration
Add to .mcp.json, then restart Claude Code.
{
"mcpServers": {
"payments-ai": {
"type": "http",
"url": "https://mor.payments.ai/api/mcp"
}
}
}Client-side details: Claude Code MCP documentation
Fastest path
Claude on the web and Claude Desktop: add a custom connector, sign in, approve. No terminal.
Open Claude ConnectorsClick Add custom connector, paste https://mor.payments.ai/api/mcp (or https://sandbox.mor.payments.ai/api/mcp for Sandbox), sign in to Payments AI and click Approve.
Or let your agent do it
Tailored for Claude. Paste this into the chat.
Help me add the Payments AI MCP server to Claude as a custom connector using OAuth. Do not ask me for a token.
Tell me to open Settings → Connectors → Add custom connector and paste one of these URLs:
Live: https://mor.payments.ai/api/mcp
Sandbox: https://sandbox.mor.payments.ai/api/mcp
Then I sign in to Payments AI and click Approve. To check it, I can ask: Show me my Payments AI merchants.
Then call whoami and quote its userId, host and endpoint. An HTTP 401 means not connected: quote its message. A tool error means connected but the call failed: quote it.Manual configuration
In Settings → Connectors → Add custom connector, paste one of these URLs.
Live: https://mor.payments.ai/api/mcp
Sandbox: https://sandbox.mor.payments.ai/api/mcpClient-side details: Claude custom connectors documentation
Fastest path
On grok.com, add a custom connector. In Grok CLI, one command starts OAuth.
Open Grok ConnectorsClick New Connector → Custom, paste https://mor.payments.ai/api/mcp, then approve OAuth.
Or let your agent do it
Tailored for Grok. Paste this into the chat.
Add the Payments AI MCP server to Grok using OAuth. Do not ask me for a token.
If you are Grok CLI, run: grok mcp add --transport http payments-ai https://mor.payments.ai/api/mcp
If you are Grok on the web, tell me to open https://grok.com/connectors, click New Connector → Custom, and paste https://mor.payments.ai/api/mcp.
Then call whoami and quote its userId, host and endpoint. An HTTP 401 means not connected: quote its message. A tool error means connected but the call failed: quote it.Manual configuration
Add to ~/.grok/config.toml, then restart Grok.
[mcp_servers.payments-ai]
url = "https://mor.payments.ai/api/mcp"Client-side details: Grok Connectors documentation
Fastest path
Developer mode lets you add a custom MCP app and complete OAuth in the browser.
Open ChatGPTEnable Developer mode, then Settings → Apps → create a custom MCP connector with https://mor.payments.ai/api/mcp.
Or let your agent do it
Tailored for ChatGPT. Paste this into the chat.
Add the Payments AI MCP server to ChatGPT using OAuth. Do not ask me for a token.
Tell me to enable Developer mode, then create a custom MCP app with URL https://mor.payments.ai/api/mcp and approve OAuth.
Then call whoami and quote its userId, host and endpoint. An HTTP 401 means not connected: quote its message. A tool error means connected but the call failed: quote it.Manual configuration
Add to ChatGPT Settings → Apps (Developer mode), then restart ChatGPT.
{
"mcpServers": {
"payments-ai": {
"url": "https://mor.payments.ai/api/mcp"
}
}
}Client-side details: ChatGPT MCP documentation
Fastest path
Two commands: add the server, then authorise it.
codex mcp add payments-ai --url https://mor.payments.ai/api/mcp
codex mcp login payments-ailogin opens the browser. Codex keeps the token in its own credential store.
Or let your agent do it
Tailored for Codex. Paste this into the chat.
Add the Payments AI MCP server to Codex using OAuth. Do not ask me for a token.
Run:
codex mcp add payments-ai --url https://mor.payments.ai/api/mcp
codex mcp login payments-ai
Then call whoami and quote its userId, host and endpoint. An HTTP 401 means not connected: quote its message. A tool error means connected but the call failed: quote it.Manual configuration
Add to ~/.codex/config.toml, then restart Codex.
[mcp_servers.payments-ai]
url = "https://mor.payments.ai/api/mcp"Client-side details: Codex MCP documentation
Fastest path
One command. Gemini CLI handles the OAuth round-trip.
gemini mcp add --transport http payments-ai https://mor.payments.ai/api/mcpThen ask Gemini to call whoami; it quotes your userId, host and endpoint.
Or let your agent do it
Tailored for Gemini CLI. Paste this into the chat.
Add the Payments AI MCP server to Gemini CLI using OAuth. Do not ask me for a token.
Run: gemini mcp add --transport http payments-ai https://mor.payments.ai/api/mcp
Complete the browser OAuth prompt if one appears.
Then call whoami and quote its userId, host and endpoint. An HTTP 401 means not connected: quote its message. A tool error means connected but the call failed: quote it.Manual configuration
Add to ~/.gemini/settings.json, then restart Gemini CLI.
{
"mcpServers": {
"payments-ai": {
"httpUrl": "https://mor.payments.ai/api/mcp"
}
}
}Client-side details: Gemini CLI MCP documentation
Fastest path
Paste serverUrl into mcp_config.json, then authenticate in Agent settings.
{
"mcpServers": {
"payments-ai": {
"serverUrl": "https://mor.payments.ai/api/mcp"
}
}
}Save as ~/.gemini/config/mcp_config.json (or .agents/mcp_config.json in a project). url and httpUrl do not connect. Then Agent settings → Customizations → Authenticate.
Or let your agent do it
Tailored for Antigravity. Paste this into the chat.
Add the Payments AI MCP server to Antigravity using OAuth. Do not ask me for a token.
Merge this into ~/.gemini/config/mcp_config.json (or .agents/mcp_config.json in a project). Use serverUrl, not url or httpUrl:
{ "mcpServers": { "payments-ai": { "serverUrl": "https://mor.payments.ai/api/mcp" } } }
Then open Agent settings → Customizations and click Authenticate next to the server.
Then call whoami and quote its userId, host and endpoint. An HTTP 401 means not connected: quote its message. A tool error means connected but the call failed: quote it.Manual configuration
Add to ~/.gemini/config/mcp_config.json, then restart Antigravity.
{
"mcpServers": {
"payments-ai": {
"serverUrl": "https://mor.payments.ai/api/mcp"
}
}
}Client-side details: Antigravity MCP documentation
Fastest path
One command from any terminal. VS Code registers the server for Copilot agent mode.
code --add-mcp '{"name":"payments-ai","type":"http","url":"https://mor.payments.ai/api/mcp"}'Then open the Copilot chat Agent picker and approve the OAuth prompt.
Or let your agent do it
Tailored for VS Code. Paste this into the chat.
Add the Payments AI MCP server to VS Code using OAuth. Do not ask me for a token.
Run: code --add-mcp '{"name":"payments-ai","type":"http","url":"https://mor.payments.ai/api/mcp"}'
Then open the Copilot chat Agent picker and approve the OAuth prompt.
Then call whoami and quote its userId, host and endpoint. An HTTP 401 means not connected: quote its message. A tool error means connected but the call failed: quote it.Manual configuration
Add to .vscode/mcp.json, then restart VS Code.
{
"servers": {
"payments-ai": {
"type": "http",
"url": "https://mor.payments.ai/api/mcp"
}
}
}Client-side details: VS Code MCP documentation
Claude Connectors (no terminal)
In Claude on the web or Claude Desktop, open Settings → Connectors and click Add custom connector. Paste https://mor.payments.ai/api/mcp (or https://sandbox.mor.payments.ai/api/mcp for Sandbox), sign in to Payments AI, and click Approve. Then ask Claude: "Show me my Payments AI merchants."
Grok Connectors (no terminal)
In Grok, open Connectors, click New Connector → Custom, and paste https://mor.payments.ai/api/mcp. Sign in on the dashboard, approve scopes, and return to Grok.
ChatGPT (developer mode)
In ChatGPT, enable Developer mode, then add a custom MCP app with the same URL and complete OAuth.
No terminal or browser
If nothing in your setup can open a browser or answer a terminal prompt, the OAuth steps above cannot finish. The agent runs the OAuth device authorization grant itself over HTTP, shows you a short code, and you approve it on any device with a browser. The connect page has the steps and the calls; the agent auth guide has every error and polling rule.
Your client then takes the resulting pai_mcp_* token as an Authorization: Bearer header:
| Client | Path with no terminal |
|---|---|
| Any agent | Device grant, then your client's own way of sending a bearer header. If it cannot send one, use the connect page on a device with a browser. |
| Cursor | Device grant, then headers in ~/.cursor/mcp.json. |
| Claude Code | Device grant, then claude mcp add --transport http payments-ai <url> --header "Authorization: Bearer <token>". /mcp → Authenticate and claude mcp login need a terminal. |
| Claude (web, Desktop) | No shell, so no device grant. Use the connector's own browser sign-in (Claude Connectors): no terminal, 90-day credential. Fallback: a User MCP Key under Request headers, which lasts at most 7 days. On Team and Enterprise the Owner sets the headers, so every member then acts as the key owner's account. |
| Grok | The connector's browser sign-in (Grok Connectors). No shell, so no device grant; a header path is not verified. Fallback: the connect page on a device with a browser. |
| ChatGPT | The app's browser sign-in (ChatGPT developer mode). No shell, so no device grant; a header path is not verified. Fallback: the connect page on a device with a browser. |
| Codex | Device grant, then codex mcp add payments-ai --url <url> --bearer-token-env-var PAI_MCP_TOKEN. Codex reads the variable from its environment at startup: set it in the environment Codex starts from (shell profile or launch environment) and restart Codex. |
| Gemini CLI | Device grant, then gemini mcp add --transport http --header "Authorization: Bearer <token>" payments-ai <url>. |
| Antigravity | Device grant, then headers next to serverUrl in mcp_config.json. |
| VS Code | Device grant, then headers in .vscode/mcp.json, with the token entered through an input. |
Verify the connection
Do not rely on the client's "connected" label. Ask your agent: "Call whoami and quote accountName, userId, host and endpoint." whoami needs no scope, so it works for every valid token.
| Result | What it means |
|---|---|
| Success | Connected as accountName (the business name of the account you are connected to, never an email; null when no label is known), userId, on host (sandbox or live) at endpoint. Confirm accountName together with host (live or sandbox) and check it is your own business account. scopes: null means every scope except transaction:read. |
| HTTP 401 | Not connected. The agent quotes the 401 message, which says how to recover (for example, how to renew an expired connection). |
| Any tool error | Connected, but the server could not prove the connection. Quote the error; do not reconnect. |
whoami also returns merchantIds (the merchants this credential is a member of), credentialExpiresAt (when it stops working, ISO 8601 UTC) and credentialExpiresInSeconds. In the last 14 days of an OAuth connection it adds credentialExpiryWarning with the link to re-approve. Every tool result carries the same warning under _meta["ai.payments/credentialExpiryWarning"] and in a closing text block; only whoami has a credentialExpiryWarning field. The link opens the connect page. Tokens you generate in the dashboard never warn. An agent that sees the warning tells you and shares the link; if you connected with the device grant, run it again and replace the Authorization header instead (steps).
host is the kind of MCP URL your client is connected to: live for the main MCP URL, sandbox for the sandbox-only URL. It is not the environment and not your merchant's deployment. On a live host, a merchant that has not gone live still shows deployment: "sandbox" in get_my_merchant.
Try it
Copy this into your agent after the server is connected:
Show me my Payments AI merchants. If none, create a sandbox merchant named Quickstart Demo, then create a $19.99/month product and give me the checkout URL.You should see tool names (get_my_merchant, create_merchant_account, create_product) before each call runs.
Create a merchant
Create a sandbox merchant named "Quickstart Demo" with my email <your email>.
Use your own real, deliverable email address — create_merchant_account rejects example, disposable, and other reserved or undeliverable addresses. Phone is optional. If you add one, use your own mobile number, starting with + and your country code, with no spaces or dashes (for example, +14155552671 is a US number, but not yours): after go-live the identity-verification link is sent to it by SMS. Without a phone, the link goes by email.
The tool returns { "merchantId": "<uuid>", "existing": false } for a new merchant. existing: true means this account already owns a merchant and the tool returned that one instead of creating a second. Either way, use that merchantId for the steps below.
Create a product and plan, then open checkout
Create a sandbox product called "Starter Plan" with a $19.99/month recurring plan for merchant <merchantId>, then give me the hosted checkout URL to open in a browser.
The agent sends create_product arguments shaped like this. A plan's type is recurring, one-time, or free-access; amount is in major units (19.99 is $19.99, not cents); currency is lowercase; the billing interval is billingPeriod (week, month, year) times periodLength.
{
"merchantId": "<merchantId>",
"name": "Starter Plan",
"plans": [
{
"name": "Monthly",
"type": "recurring",
"amount": 19.99,
"currency": "usd",
"billingPeriod": "month",
"periodLength": 1
}
]
}
Checkout branding
Show my checkout customization for merchant <merchantId> and update the button color to #2563EB.
The agent sends update_checkout_customization arguments shaped like this. The fields to change go inside a nested customization object, never at the top level; fields you leave out keep their current value. Colors are 6-digit hex with the leading #.
{
"merchantId": "<merchantId>",
"customization": {
"buttonColor": "#2563EB"
}
}
Use sandbox merchant data for exploration. Mutating tools target sandbox until go-live.
Test card (Sandbox): pay a sandbox checkout link with 4242 4242 4242 4242, any future expiry, and any CVC. To test a refused payment, use 4000 0000 0000 0002. Test cards never work on Live: live checkout links take real cards only.
Available tools
| Tool | What it does |
|---|---|
whoami | accountName, userId, scopes, host, endpoint, merchantIds, credentialExpiresAt, credentialExpiresInSeconds, credentialExpiryWarning (verify the connection; any valid token) |
get_my_merchant | Owned merchants (first call after verify) |
create_merchant_account | Dual-provision live + sandbox merchant |
get_merchant_activation_status | Activation status: pending, verification_pending, active |
go_live | Promote to live; a repeat call returns the current status |
search_payments_ai_docs | Search PAI Managed documentation |
create_product | Create product + pricing plans (sandbox until go-live) |
create_order | Payable multi-item or caller-priced checkout (checkout:write) |
update_product | Merge-update a product's name, description or status (product:create) |
update_plan | Merge-update a plan's name, description, price, billing period or free trial (product:create) |
list_products | List products and pricing plans for a merchant |
list_transactions | Look up a merchant's transactions (transaction:read) |
get_transaction | One transaction's details and line items |
get_product_image_upload_url | Mint presigned POST for product image |
confirm_product_image | Attach uploaded product image |
get_checkout_customization | Read checkout theme and branding |
update_checkout_customization | Merge-update checkout branding |
set_checkout_logo | Mint → PUT → confirm checkout logo |
The checkoutUrl returned by create_product and list_products is ready to open — use it verbatim. It already targets the right environment (sandbox URLs carry ?isSandbox=true; live URLs have no query param).
Transaction lookup
list_transactions answers "did this customer pay?": filter by customerEmail, orderId or orderNumber, status, dateFrom / dateTo and deployment (sandbox or live; omitted means where the merchant's checkouts run now). get_transaction returns one transaction's details: the same fields plus the refunded amount and the order's line items.
- Only
succeededmeans paid.pendingis not yet confirmed and must never be reported as paid.partially_refundedmeans part of the amount was refunded. - Each transaction returns customer email, first and last name, and card brand and last 4 only.
- Both tools need the
transaction:readscope. It is never granted by default or by a token whosescopesisnull, so existing connections must re-authorize with it and tick it on the consent screen, where it always starts unticked (or mint a token with it ticked). - There is no refund tool. Send the merchant to the transaction's
transactionDetailsUrland tell them to select its deployment (Sandbox or Live) in the dashboard.
Going live
go_live promotes the merchant to live routing only — it does not copy products, plans, or checkout customization. The live side starts with an empty catalog: call create_product again for every product and plan you want live, and re-apply any branding with update_checkout_customization on the same merchantId (after go_live it writes to live). set_checkout_logo always writes to sandbox, so the live logo cannot be set over MCP yet: upload it in the dashboard checkout builder (https://mor.payments.ai/checkout-builder) with Live selected. A sandbox checkout link stays sandbox-only forever (it always carries ?isSandbox=true) and never turns into a live link — read the new checkoutUrl from create_product or list_products on live instead of reusing the one you already showed.
The Sandbox Deployment needs no identity verification: products, checkout links and test transactions all work while KYC/KYB status stays not_started. On the Live Deployment, the merchant can process up to $5,000 in card transactions before identity verification is required — but payouts (withdrawing funds) always require completed KYC/KYB, independent of that $5,000 threshold, before a payout method can be added and before the first live payout.
Sandbox MCP URL
For staging agents (build and test only in sandbox), connect to the sandbox MCP endpoint instead of the live URL:
https://sandbox.mor.payments.ai/api/mcp
Generate a pai_mcp_* token in Developer Tools → MCP Tokens while the dashboard is on Sandbox, or complete OAuth through the sandbox MCP server (its authorization server redirects to the dashboard with deployment=sandbox so consent calls the sandbox API). Live MCP tokens and live OAuth consent do not work on this URL. Merchant, product, and checkout writes stay on the sandbox schema. The go_live tool is not available here — promote merchants on the live MCP URL when you are ready.
The client snippets above default to the live URL; swap in the Sandbox URL to build and test.
Manual: User MCP Key
Use this only if your client cannot do OAuth, or you can't sign in through your client's browser window.
- Sign in to the Payments AI dashboard.
- Open Developer Tools → MCP Tokens and pick the Sandbox or Live tab.
- Click Generate MCP Token, enter a name and duration, choose the tool scopes the token may use, then click Generate Token. Copy your token (
pai_mcp_*). It is shown only once. - Paste the config below into your client (
~/.cursor/mcp.json, Claude Desktop config, or equivalent), or run the Claude Code command.
A token belongs to the tab it was generated on. A Sandbox token works only with the sandbox MCP URL (https://sandbox.mor.payments.ai/api/mcp); a Live token works only with the live MCP URL (https://mor.payments.ai/api/mcp). The success dialog in the dashboard shows the matching URL. The examples below use the live URL.
{
"mcpServers": {
"payments-ai": {
"type": "streamableHttp",
"url": "https://mor.payments.ai/api/mcp",
"headers": {
"Authorization": "Bearer pai_mcp_<your-token>"
}
}
}
}| Client | Where |
|---|---|
| Cursor | Settings → MCP → edit config (or ~/.cursor/mcp.json) → paste under mcpServers |
| Claude Desktop | ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows) |
| Claude Code | Run the Claude Code command above |
| Grok CLI | ~/.grok/config.toml |
Restart your client after saving.
When the MCP endpoint answers 401
The response body carries a machine-readable code and a docUrl to its Fix-It page. The WWW-Authenticate header keeps the OAuth discovery challenge.
code | Meaning | Fix |
|---|---|---|
missing_token | No Authorization: Bearer header | Missing MCP token |
invalid_token | Unknown, revoked or malformed token | Invalid MCP token |
token_expired | The credential expired: a token's duration passed, or the 90-day OAuth connection ran out; re-approve it in your client (OAuth), run the device grant again (no terminal), or generate a new token (MCP key) | MCP token expired |
token_validation_unavailable | The token could not be checked right now; retry, do not generate a new one | Error catalog |
When a stored credential keeps getting 401
Some clients keep an OAuth credential saved without an issuer stamp (upstream MCP issue SEP-2352). That stored credential wins over every new authorization, so signing in again changes nothing.
Signature: your client shows Payments AI as connected or holds a stored credential, but every MCP call answers 401, and running OAuth again does not fix it.
Recovery:
- Clear the stored Payments AI credential in your client, then reconnect and approve scopes in the browser again. In Claude Code, run
claude mcp remove payments-aiand add the server again with the OAuth command above. In other clients, sign out of the server or remove it from the MCP settings, then add it again. - If your client offers no way to clear the stored credential, generate a new token in Developer Tools → MCP Tokens and connect with the
Authorization: Bearerheader instead (see Manual: User MCP Key). A bearer token does not use the client's OAuth credential store.
Report it: agents report this case with the code stale_credential_no_issuer, so the upstream problem can be sized. Send POST https://mor.payments.ai/api/mcp/connect-diagnostics (or the sandbox MCP URL plus /connect-diagnostics) with Content-Type: application/json and only these fields. The endpoint needs no token and always answers 204 with an empty body. Never put a token in the report: a body containing a pai_ token is discarded whole, and any field not listed here is dropped.
{
"client": "claude-code",
"stage": "false_connected_state",
"code": "stale_credential_no_issuer",
"mcpServerVersion": "1.4.0",
"clientVersion": "2.0.14",
"deployment": "live",
"reportedAt": "2026-10-12T09:30:00Z"
}
client is one of claude-code, claude, cursor, codex, grok, chatgpt, gemini, vscode or other. mcpServerVersion is the serverInfo.version the MCP server returned on initialize, and both versions are plain semver.
Agent discovery
Agents can fetch these without a key:
| File | URL |
|---|---|
| Skill | https://doc.mor.payments.ai/SKILL.md |
| Auth | https://doc.mor.payments.ai/auth.md |
| Concise index | https://doc.mor.payments.ai/llms.txt |
| Full index | https://doc.mor.payments.ai/llms-full.txt |
| Agent Skills index | https://doc.mor.payments.ai/.well-known/agent-skills/index.json |
| MCP Server Card | https://mor.payments.ai/.well-known/mcp/server-card.json |
mkdir -p "$HOME/.payments-ai" && curl --fail --show-error --location \
--output "$HOME/.payments-ai/SKILL.md" \
"https://doc.mor.payments.ai/SKILL.md"
Host plugins still install from paymentsai/Payments-AI-skills (npx skills add paymentsai/Payments-AI-skills).
Privacy and support
- Privacy policy: payments.ai/mor/privacy-policy
- Product & technical support: merchants@payments.ai (see Getting help)
Next steps
- Quickstart: first sandbox API call
- Webhooks: signed events sent to your server
- API Reference: OpenAPI contracts