Provider REST API

11 actions

Connect Claude to Slack

Search conversations and send messages to your workspace. 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: Bot token
Actions exposed: 11
Cost per call (typical): 1 credit
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Slack
Open the marketplace in your workspace, add Slack to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with bot token. 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. Slack 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 Slack asks for

Bot token. 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.

Bot tokenRequired: api.slack.com/apps → your app → OAuth & Permissions → Bot User OAuth Token. Add the channels:read, channels:history, groups:read, groups:history, chat:write, reactions:write, and users:read scopes, then invite the bot to the channels it should reach.; xoxb-…
User tokenOptional: Only needed for the search action: Slack's search.messages endpoint rejects bot tokens. Use the User OAuth Token from the same app with the search:read scope.; xoxp-…

What Claude can do in Slack

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: 7Reads
Writes: 4Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

list_channels
List channels in the workspace so you can turn a channel name into the channel ID every other action needs. Only channels the bot can see are returned; private channels additionally require the bot to be a member.
read_channel_history
Read recent messages from a channel or DM, newest first. Use this to catch up on a conversation; Slack caps newer apps at 15 messages per call and one call per minute, so keep the limit small and page with cursor when you need more.
read_thread
Read a threaded conversation: pass the parent message's ts as thread_ts to get the parent plus every reply, oldest first. Use after read_channel_history shows a message with reply_count above zero.
search
Search messages across the workspace with Slack search syntax, e.g. "deploy in:#engineering from:@ana after:2026-01-01". This requires the optional user token credential - Slack's search endpoint rejects bot tokens - so fall back to read_channel_history when only a bot token is configured.
list_users
List workspace members so you can map user IDs seen in messages to real names. Emails are only present when the token carries the users:read.email scope.
find_user_by_email
Look up a single workspace member by their email address and return their user ID, which you need to mention them (<@ID>) or open a DM. Requires the users:read.email scope.
get_permalink
Build the shareable https://…slack.com/archives/… link for a specific message, so it can be quoted elsewhere.

Writes

Creates or updates something on the other side.

send_message
Post a message to a channel, DM, or thread as the bot. Pass thread_ts to reply inside an existing thread instead of starting a new top-level message. Returns the ts of the new message, which update_message and add_reaction need.
update_message
Edit a message the bot previously posted. Identify it by the channel ID and the ts returned from send_message. The bot can only edit its own messages.
schedule_message
Queue a message to be posted later. post_at is a Unix timestamp in seconds and must be in the future and within 120 days. Returns a scheduled_message_id.
add_reaction
Add an emoji reaction to a message - the lightweight way to acknowledge something without posting. Use the emoji's short name without colons, e.g. "white_check_mark".

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 Slack 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.
Nothing here deletes: This connector writes to Slack, but nothing in it deletes or permanently alters anything.
It reaches no further than your credential: Toolspoke holds no access to Slack 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 Slack: 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 Slack. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Slack's own rate limits. A call that Slack refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Slack?

11 named actions: 7 that only read and 4 that write. They include list_channels, read_channel_history and read_thread. 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 Slack connector need?

Bot token. The connector asks for bot token, and optionally user token. 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 Slack 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 Slack connector not do?

The 11 actions above are the whole of it. A call to any other name is refused before it reaches Slack 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. This connector writes to Slack, but nothing in it deletes or permanently alters anything. Toolspoke holds no access to Slack 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 Slack. An agent has to ask. Toolspoke does not retry, queue or back off around Slack's own rate limits. A call that Slack 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 Slack'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 Slack?

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