Provider REST API

11 actions

Connect Claude to Resend

Send transactional email and manage domains, contacts and broadcasts. Toolspoke puts 11 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: API key
Actions exposed: 11
Cost per call (typical): 1 credit
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Resend
Open the marketplace in your workspace, add Resend to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with api key. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Resend shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Resend asks for

API key. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

API keyRequired: Dashboard → API Keys → Create API Key. A key with Sending access covers send_email; the domain, contact and broadcast reads need Full access, and so do create_contact and delete_contact.; re_…

What Claude can do in Resend

11 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 8Reads
Writes: 1Writes
Destructive: 2Destructive

Reads

Fetches data and changes nothing.

get_email
Retrieve one sent email by id, with its delivery status, recipients and the body that was sent.
list_domains
List the sending domains on this account with their verification status and region. Takes no arguments and costs nothing, which is why it is what an install tests itself with - and it is also the answer to "why was that send rejected", which is usually an unverified domain.
get_domain
Retrieve one sending domain by id, including the DNS records Resend expects and whether each one is verified.
list_api_keys
List the API keys on this account by name, id and creation date. Resend never returns a key's secret after it is created, so this shows which keys exist rather than their values.
list_audiences
List the audiences on this account. Resend has superseded audiences with segments and marks these endpoints deprecated, so treat this as a way to read what already exists rather than the shape to build new work on.
list_contacts
List contacts on this account, optionally narrowed to one segment. Contacts are top-level in the current API - there is no audience id in this path.
get_contact
Retrieve one contact. The identifier may be the contact id or the email address itself - Resend accepts either in this path segment.
list_broadcasts
List broadcasts on this account with their status and send times. Reading a broadcast never sends one - this connector exposes no operation that sends a broadcast at all.

Writes

Creates or updates something on the other side.

create_contact
Add a contact. This is a write rather than destructive: it sends nothing and delete_contact undoes it. It does decide who a later broadcast reaches, so treat consent as the caller's responsibility. Only email is required.

Destructive

Deletes or permanently alters something. Worth granting on purpose.

send_email
Send one email. Classified destructive rather than write, and deliberately so: it delivers to real inboxes, it cannot be recalled once accepted, and Resend bills per send. A write grant can add and read contacts here and send nothing. Supply html, text, or both; from must be an address on a domain this account has verified. Returns the message id, which is what get_email later takes.
delete_contact
Remove a contact from this account permanently. Destructive because there is no undo and nothing recoverable behind it: the record and its segment memberships go, and re-adding the address does not restore what was there. The identifier may be the contact id or the email address.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 11 actions above are the whole of it. A call to any other name is refused before it reaches Resend rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It reaches no further than your credential: Toolspoke holds no access to Resend of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Resend: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Resend. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Resend's own rate limits. A call that Resend refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Resend?

11 named actions: 8 that only read, 1 that write and 2 that delete or permanently alter something. They include send_email, get_email and list_domains. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Resend connector need?

API key. The connector asks for api key. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Resend connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 11 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Resend connector not do?

The 11 actions above are the whole of it. A call to any other name is refused before it reaches Resend rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Toolspoke holds no access to Resend of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Resend. An agent has to ask. Toolspoke does not retry, queue or back off around Resend's own rate limits. A call that Resend refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Resend's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Resend?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and the credits spent. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More communication connectors

Browse all of them