CONNECT APP
Build with Ragie
Artificial Intelligence (AI)
- API key
MCP
Give your agent Ragie tools
Every Ragie 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 Ragie 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": "ragie",
},
},
},
)
const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)
const { tools } = await mcp.listTools()
// e.g. run Create Document:
const result = await mcp.callTool({
name: "ragie-create-document",
arguments: {
file: "File Path or URL",
mode: "Mode",
},
})# 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": "ragie",
}
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 Document:
result = await session.call_tool("ragie-create-document", {
"file": "File Path or URL",
"mode": "Mode",
})API PROXY
Call the Ragie API directly
For an endpoint with no pre-built tool, the Connect proxy forwards your request to the Ragie 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.ragie.ai/documents",
})
// Any allowed Ragie 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.ragie.ai/documents
curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9hcGkucmFnaWUuYWkvZG9jdW1lbnRz?external_user_id={external_user_id}&account_id=apn_xxxxxxx" \
-H "Authorization: Bearer {access_token}" \
-H "x-pd-environment: production"SDK
Run Ragie actions from your backend
Connect a user's Ragie account once, then run Create Document 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: "ragie-create-document",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
ragie: { authProvisionId: "apn_xxxxxxx" },
file: "File Path or URL",
mode: "Mode",
},
})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="ragie-create-document",
external_user_id="{external_user_id}", # any stable ID for this user in your system
configured_props={
"ragie": {"authProvisionId": "apn_xxxxxxx"},
"file": "File Path or URL",
"mode": "Mode",
},
)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": "ragie-create-document",
"configured_props": {
"ragie": { "authProvisionId": "apn_xxxxxxx" },
"file": "File Path or URL",
"mode": "Mode"
}
}'TOOLS
Ragie actions
On-demand operations your product or agent can configure and run on behalf of a connected user.
MULTI-APP
Use Ragie with other popular apps
Most products don't stop at one integration. Pair Ragie with the other apps your users rely on, and ship use cases that span both.
- App slug
- ragie
- Authentication
- API key
- Categories
- Artificial Intelligence (AI)
- Actions
- 2
- Triggers
- 2
- API proxy
- Available