Slack ACTION
Find Message
Find a Slack message by keyword or natural-language query across public and private channels. Returns matching messages with channel context, timestamps, and permalinks. Pass the returned
message_ts to Reply to a Message to answer in thread, or to Get Thread Replies to read the rest of that conversation. Use Search instead when you need file results or want to restrict channelTypes; use this action when you want to order results with sort / sortDirection. User mentions come back in the canonical <@U123> form; echo it verbatim to post a real mention. Display names are returned separately as mentions, an array of { id, name } objects, omitted when no mention carried a name. Do NOT splice a name back inline: Slack renders <@U123|Name> as literal text, not a mention. See the documentation- Action
- Read only
- OAuth
- SDK
- MCP
IMPLEMENTATION
Call this tool
Connect a user's Slack account once, then configure and run Find Message from your backend or agent.
import { PipedreamClient } from "@pipedream/sdk"
const pd = new PipedreamClient({
projectId: process.env.PIPEDREAM_PROJECT_ID!,
clientId: process.env.PIPEDREAM_CLIENT_ID!,
clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
projectEnvironment: "production",
})
const result = await pd.actions.run({
id: "slack_v2-find-message",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
slack_v2: { authProvisionId: "apn_xxxxxxx" },
query: "Query",
maxResults: 10,
},
})
console.log(result)curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
-H "Content-Type: application/json" \
-H "X-PD-Environment: production" \
-H "Authorization: Bearer {access_token}" \
-d '{
"external_user_id": "{external_user_id}",
"id": "slack_v2-find-message",
"configured_props": {
"slack_v2": { "authProvisionId": "apn_xxxxxxx" },
"query": "Query",
"maxResults": 10
}
}'// accessToken: mint a short-lived token with the Connect SDK — see the MCP guide
const transport = new StreamableHTTPClientTransport(
new URL("https://remote.mcp.pipedream.net/v3"),
{
requestInit: {
headers: {
Authorization: `Bearer ${accessToken}`,
"x-pd-project-id": "{project_id}",
"x-pd-environment": "production",
"x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
"x-pd-app-slug": "slack_v2",
},
},
},
)
const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)
const { tools } = await mcp.listTools()
// listTools() hands your model this tool's input schema, so it can
// fill the arguments itself:
const result = await mcp.callTool({
name: "slack_v2-find-message",
arguments: {
query: "Query",
maxResults: 10,
},
})SCHEMA
Inputs
Pipedream supplies the connected account. Your application provides the operation-specific values below. Dynamic inputs are resolved against that user's account.
| Property | Type | Description |
|---|---|---|
query Query | string | The search query. Supports Slack search modifiers, e.g. from:@user, in:#channel, before:2025-01-01, has:link. Combine terms and modifiers as needed, e.g. budget in:#finance from:@jane. Required |
maxResults Max Results | integer | The maximum number of messages to return Optional |
sort Sort | string | Return matches sorted by either score or timestamp Optional |
sortDirection Sort Direction | string | Sort ascending (asc) or descending (desc) Optional |
REFERENCE
Tool details
Behavior hints are published with the component in the Pipedream registry and surface as MCP tool annotations, so an agent can reason about a tool before it calls it.
- Registry key
- slack_v2-find-message
- Version
- 0.2.3
- App
- Slack
- Authentication
- OAuth
- Read-only
- Yes
- Destructive
- No
- Open world
- Yes
- Source
- View on GitHub ↗