Connectors · CRM & sales

respond.io MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to respond.io and the rest of your systems. It gives your agent 30 respond.io actions (14 reads, 13 writes and 3 that wait for a confirmation) and holds the respond.io credential itself, so the agent never does. It paces respond.io's limits and records every call.

Connect respond.io free See pricing

100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.

claude mcp add --transport http actionlake https://connect.actionlake.com/mcp

30actionsin one signed file
14readlook, never change
13writecreate and update
3wait for a yesdestructive, confirmed first

Set up

Connect respond.io in three steps.

01
Add actionlake to Claude.
Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.
https://connect.actionlake.com/mcp
02
Connect respond.io.
Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.
- access_tokenrespond.io API access token
```
account { op: "connections.requirements", service: "respond_io" }
# free: exactly what to paste, and what is found for you
```

Make the first call. Check before a write.

Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

do    { action: "respond_io.contacts.list" }# list contacts · read · 1 upstream callcheck { action: "respond_io.contacts.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

respond.io at a glance

Sign-in: Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
You provide: access_token
Limits we pace to: 5 calls a second, per connection
API covered: Respond.io Developer API v2api.respond.io/v2
Built from: respond.io's documentation, read 23 October 2026developers.respond.io npmjs.com npmjs.com
Service file: Version 1.0.0, signed (Ed25519)
Cached reads: 14 of 14 reads, for up to 5 minutes; a write clears what it affects
Shared entities: 3, so ask can line respond.io up with your other systems
Data: Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in respond.io.

30 actions in 14 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

14readlook, never change
13writecreate and update
3destructivewait for a confirmation

Contacts
7
2 read · 3 write · 2 destructive
List contacts · Create a contact · Get a contact · Update a contact
Custom fields
3
2 read · 1 write · 0 destructive
Create a custom field · List custom fields · Get a custom field
Messages
3
2 read · 1 write · 0 destructive
List a contact's messages · Send a message · Get a message
Tags
3
0 read · 2 write · 1 destructive
Create a workspace tag · Update a workspace tag · Delete a workspace tag
Contact tags
2
0 read · 2 write · 0 destructive
Add tags to a contact · Remove tags from a contact
Conversations
2
0 read · 2 write · 0 destructive
Assign a conversation · Open or close a conversation
Message templates
2
2 read · 0 write · 0 destructive
List a channel's message templates · Get a message template
Users
2
2 read · 0 write · 0 destructive
List workspace users · Get a workspace user

6 more areas · 6 actions

Channel templates 1
Channels 1
Closing notes 1
Comments 1
Contact channels 1
Contact lifecycles 1

Top actions

The respond.io API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 16 of respond.io's 16 action names are shared with at least one other connector, so an agent learns them once.

Action	What it does	Effect	Same name in
`respond_io.contacts.list`List contacts	List contacts matching a search term and an optional filter, newest first.	read	`crm.contact.list`177 connectors
`respond_io.users.list`List workspace users	List the users in the workspace. Cheap read to test a fresh connection.	read	`identity.user.list`474 connectors
`respond_io.contacts.create`Create a contact	Create a contact identified by email or phone.	write	`crm.contact.create`161 connectors
`respond_io.channels.list`List workspace channels	List the messaging channels connected to the workspace.	read	`comm.channel.list`27 connectors
`respond_io.contacts.delete`Delete a contact	Delete a contact.	destructive	`crm.contact.delete`147 connectors
`respond_io.users.get`Get a workspace user	Fetch one workspace user.	read	`identity.user.get`399 connectors
`respond_io.tags.create`Create a workspace tag	Create a tag in the workspace.	write	`crm.tag.create`49 connectors
`respond_io.messages.send`Send a message	Send a message to a contact on a channel (or the contact's last-interacted channel when `channelId` is omitted).	write	`comm.message.send`25 connectors
`respond_io.tags.update`Update a workspace tag	Rename or restyle a workspace tag, identified by its current name.	write	`crm.tag.update`40 connectors
`respond_io.comments.create`Add a comment	Add an internal comment to a contact's conversation. Mention a user with `{{@user.<id>}}`.	write	this connector
`respond_io.contact_tags.add`Add tags to a contact	Add up to 10 tags to a contact; tags that do not exist yet are created.	write	this connector
`respond_io.contact_tags.remove`Remove tags from a contact	Remove up to 10 tags from a contact. The tags themselves stay in the workspace.	write	this connector

Try it

Prompts to paste into Claude.

Each one names the respond.io actions it will call, so you know what it reads and what it changes before you send it.

Readread
Find the respond.io contacts with no email address, so we can clean them up.
callsrespond_io.contacts.list
Writewrite
Create a contact in respond.io. Show me exactly what you will send before you save it.
callsrespond_io.contacts.create
Across systemsread
Which contacts are in both respond.io and HaloPSA, and how many are in only one of them?
callsrespond_io.contacts.listhalopsa.users.list

Across your systems

respond.io, joined to the rest of your business.

One ask fetches from respond.io and another system, joins the rows on the same customer on our side, and hands your agent the answer, not every row.

Which contacts are in both respond.io and HaloPSA, and how many are in only one of them?
respond_io.contacts.list + halopsa.users.list, on crm.contact · HaloPSA
Which contacts are in both respond.io and NetSuite, and how many are in only one of them?
respond_io.contacts.list + netsuite.views.contacts, on crm.contact · NetSuite

Also mapped by other connectorsidentity.user 517crm.contact 192comm.channel 21

ask

ask {  intent: "which contacts are in both respond.io and HaloPSA, and how many are in only one of them",  steps: [    { action: "respond_io.contacts.list", as: "people", input: {}, limit: 100, max_pages: 5 },    { action: "halopsa.users.list", as: "people2", input: {}, limit: 100, max_pages: 5 },    { join: {        left: "people",        right: "people2",        on: "crm.contact",        group_by: "people.email",        select: ["people.email", "count(people2.id) as in_halopsa"]    } }  ]}

Example. Run it through check first: it validates the steps and prices them, and it is free.

Governance for respond.io

Destructive actions wait for a yes.

3 respond.io actions are destructive. These are all of them:

Delete a contactrespond_io.contacts.delete
Merge two contactsrespond_io.contacts.merge
Delete a workspace tagrespond_io.tags.delete

A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.

dorespond_io.contacts.deleteconfirm_policy: human

Delete a contact?

intent: the user asked me to delete a contact

run suspended · waiting for a named person · key respond-io-agent cannot confirm itself

In the console, or from an emailed signed link.

a key for this connector

account {  op: "keys.create", name: "respond-io-agent",  allowed_actions: ["respond_io.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "respond_io.contacts.delete", approver: "[email protected]" },    { match: "respond_io.contacts.merge", approver: "[email protected]" },    { match: "respond_io.tags.delete", approver: "[email protected]" }  ]}

Illustrative. Scoped to respond.io only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What respond.io costs on actionlake.

Every respond.io action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call respond.io refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

1upstream call per actionall 30 respond.io actions
30actions pageeach page of a long list is one call
14reads can be cacheda cache hit costs nothing
100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every respond.io action.

30 actions by area: the id your agent calls, what it does, and its effect.

Contacts7

respond_io.contacts.createCreate a contactwrite
respond_io.contacts.deleteDelete a contactdestructive
respond_io.contacts.getGet a contactread
respond_io.contacts.listList contactsread
respond_io.contacts.mergeMerge two contactsdestructive
respond_io.contacts.updateUpdate a contactwrite
respond_io.contacts.upsertCreate or update a contactwrite

Custom fields3

respond_io.custom_fields.createCreate a custom fieldwrite
respond_io.custom_fields.getGet a custom fieldread
respond_io.custom_fields.listList custom fieldsread

Messages3

respond_io.messages.getGet a messageread
respond_io.messages.listList a contact's messagesread
respond_io.messages.sendSend a messagewrite

Tags3

respond_io.tags.createCreate a workspace tagwrite
respond_io.tags.deleteDelete a workspace tagdestructive
respond_io.tags.updateUpdate a workspace tagwrite

Contact tags2

respond_io.contact_tags.addAdd tags to a contactwrite
respond_io.contact_tags.removeRemove tags from a contactwrite

Conversations2

respond_io.conversations.assignAssign a conversationwrite
respond_io.conversations.update_statusOpen or close a conversationwrite

Message templates2

respond_io.message_templates.getGet a message templateread
respond_io.message_templates.listList a channel's message templatesread

Users2

respond_io.users.getGet a workspace userread
respond_io.users.listList workspace usersread

Channel templates1

respond_io.channel_templates.listList a channel's WhatsApp templatesread

Channels1

respond_io.channels.listList workspace channelsread

Closing notes1

respond_io.closing_notes.listList closing note categoriesread

Comments1

respond_io.comments.createAdd a commentwrite

Contact channels1

respond_io.contact_channels.listList a contact's channelsread

Contact lifecycles1

respond_io.contact_lifecycles.updateSet a contact's lifecycle stagewrite

Questions

The respond.io MCP server, answered.

Is there a respond.io MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 30 respond.io actions across contacts, custom fields, messages and tags, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by respond.io.

What do I need to connect respond.io?

Respond.io API access token. The free call account { op: "connections.requirements", service: "respond_io" } lists exactly what to paste.

Can an AI agent delete or change things in respond.io?

Only if its key allows it, and only with an explicit confirmation. 3 respond.io actions are destructive, including delete a contact, merge two contacts and delete a workspace tag. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.

Will an AI agent use up my respond.io API limit?

actionlake paces every call to the limits in the respond.io service file: 5 calls a second per connection. Repeated reads are answered from cache (14 respond.io actions can be), which never reaches respond.io.

What does a respond.io action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (30 respond.io actions page). Cache hits, searches, dry runs and calls respond.io refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

Which respond.io API does it cover?

The respond.io Developer API v2 at api.respond.io/v2. It is built from respond.io's documentation as read on 23 October 2026. 30 actions in 14 areas, each one in the signed service file (version 1.0.0).

Can I combine respond.io with my other systems?

Yes. ask joins respond.io to HaloPSA or NetSuite on the same customer and returns the answer rather than every row. respond.io maps crm.contact, which 192 other connectors also map.

Does actionlake keep my respond.io data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your respond.io credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.

Which AI clients can use it?

Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.

Give your agent respond.io today.

Connect respond.io free See pricing

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.

respond.io MCP server for AI agents.

Connect respond.io in three steps.

Add actionlake to Claude.

Connect respond.io.

Make the first call. Check before a write.

What an AI agent can do in respond.io.

Contacts

Custom fields

Messages

Tags

Contact tags

Conversations

Message templates

Users