CONNECT APP
Build with Devin
Artificial Intelligence (AI)
- API key
MCP
Give your agent Devin tools
Every Devin action is exposed as an MCP tool on Pipedream's remote server. Point a client at it with your end user's ID and Connect resolves that user's Devin account for each tool call — you store no tokens.
// 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": "devin",
},
},
},
)
const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)
const { tools } = await mcp.listTools()
// e.g. run Create Knowledge:
const result = await mcp.callTool({
name: "devin-create-knowledge",
arguments: {
body: "Body",
name: "Name",
},
})# access_token: mint a short-lived token with the Connect SDK — see the MCP guide
headers = {
"Authorization": f"Bearer {access_token}",
"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": "devin",
}
async with streamablehttp_client("https://remote.mcp.pipedream.net/v3", headers=headers) as (read, write, _):
async with ClientSession(read, write) as session:
await session.initialize()
tools = await session.list_tools()
# e.g. run Create Knowledge:
result = await session.call_tool("devin-create-knowledge", {
"body": "Body",
"name": "Name",
})API PROXY
Call the Devin API directly
For an endpoint with no pre-built tool, the Connect proxy forwards your request to the Devin API with the connected user's credentials attached. You store no tokens and write no refresh logic.
const resp = await pd.proxy.get({
externalUserId: "{external_user_id}", // any stable ID for this user in your system
accountId: "apn_xxxxxxx",
url: "https://api.devin.ai/v1/sessions",
})
// Any allowed Devin endpoint works here. Pipedream attaches the
// connected account's credentials to the outgoing request.# The path segment is the target URL, URL-safe base64 encoded:
# https://api.devin.ai/v1/sessions
curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9hcGkuZGV2aW4uYWkvdjEvc2Vzc2lvbnM?external_user_id={external_user_id}&account_id=apn_xxxxxxx" \
-H "Authorization: Bearer {access_token}" \
-H "x-pd-environment: production"SDK
Run Devin actions from your backend
Connect a user's Devin account once, then run Create Knowledge on their behalf from your own code — TypeScript, Python, or plain HTTP.
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: "devin-create-knowledge",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
devin: { authProvisionId: "apn_xxxxxxx" },
body: "Body",
name: "Name",
},
})from pipedream import Pipedream
pd = Pipedream(
client_id="{oauth_client_id}",
client_secret="{oauth_client_secret}",
project_id="{project_id}",
project_environment="production",
)
result = pd.actions.run(
id="devin-create-knowledge",
external_user_id="{external_user_id}", # any stable ID for this user in your system
configured_props={
"devin": {"authProvisionId": "apn_xxxxxxx"},
"body": "Body",
"name": "Name",
},
)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": "devin-create-knowledge",
"configured_props": {
"devin": { "authProvisionId": "apn_xxxxxxx" },
"body": "Body",
"name": "Name"
}
}'TOOLS
Devin actions
On-demand operations your product or agent can configure and run on behalf of a connected user.
-
Create Knowledge
actionCreate a new knowledge object to share information with Devin. See the documentationWritev0.0.2 -
Create Session
actionCreate a new session with Devin. See the documentationWritev0.0.2 -
Delete Knowledge
actionDelete an existing knowledge object. See the documentationWritev0.0.2 -
Get Session
actionRetrieve details about an existing session. See the documentationRead-onlyv0.0.2 -
List Folder ID Options
actionRetrieves available options for the Folder ID field.Read-onlyv0.0.1 -
List Knowledge
actionRetrieve a list of all knowledge objects. See the documentationRead-onlyv0.0.2 -
List Secret IDs Options
actionRetrieves available options for the Secret IDs field.Read-onlyv0.0.1 -
List Session ID Options
actionRetrieves available options for the Session ID field.Read-onlyv0.0.1 -
List Sessions
actionRetrieve a list of all sessions. See the documentationRead-onlyv0.0.2 -
Send Message to Session
actionSend a message to an existing Devin session. See the documentationWritev0.0.2 -
Update Knowledge
actionUpdate an existing knowledge object. See the documentationWritev0.0.2 -
Update Session Tags
actionUpdate the tags for an existing session. See the documentationWritev0.0.2 -
Upload File
actionUpload files for Devin to use in sessions. See the documentationWritev0.0.3
No Devin triggers are available yet.
MULTI-APP
Use Devin with other popular apps
Most products don't stop at one integration. Pair Devin with the other apps your users rely on, and ship use cases that span both.
- App slug
- devin
- Authentication
- API key
- Categories
- Artificial Intelligence (AI)
- Actions
- 13
- Triggers
- 0
- API proxy
- Available