For Agents
Programmatically get the authorised user, get user. Covers 56 operations with apiKey, oauth2 authentication.
Use for: I need to the authorised user, I want to user, Search for user, Find all institution
Not supported: Does not handle payments, communications, or crm - use for developer tools only.
PocketSmith provides programmatic access to developer tools functionality. The API exposes 56 endpoints secured with apiKey, oauth2 authentication.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the PocketSmith, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fpocketsmith.com%2Fpocketsmith" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fpocketsmith.com%2Fpocketsmith" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with PocketSmith API.
Get the authorised user
Update user
Delete institution
Create institution in user
Patterns agents use PocketSmith API for, with concrete tasks.
★ Developer Tools Operations
Use the PocketSmith to perform developer tools operations programmatically. The API provides 56 endpoints covering core functionality including get the authorised user, get user, update user.
Call GET /me to get the authorised user
Automated Accounts Management
Automate accounts operations by combining multiple PocketSmith endpoints. Agents can get user and then update user in a single workflow.
Call GET /users/{id} to get user, then verify the result
AI Agent Integration via Jentic
AI agents discover and call PocketSmith endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey, oauth2 tokens manually.
Search Jentic for 'get the authorised user', load the operation schema, and execute with Jentic-managed credentials
56 endpoints — pocketsmith provides programmatic access to developer tools functionality.
METHOD
PATH
DESCRIPTION
/me
Get the authorised user
/users/{id}
Get user
/users/{id}
Update user
/institutions/{id}
Get institution
/institutions/{id}
Update institution
/institutions/{id}
Delete institution
/users/{id}/institutions
Create institution in user
/users/{id}/institutions
List institutions in user
/me
Get the authorised user
/users/{id}
Get user
/users/{id}
Update user
/institutions/{id}
Get institution
/institutions/{id}
Update institution
/institutions/{id}
Delete institution
/users/{id}/institutions
Create institution in user
/users/{id}/institutions
List institutions in user
What agents get from Jentic-routed access to this vendor.
Setup
Wiring PocketSmith by hand means choosing between an X-Developer-Key header and OAuth2, then threading user and institution ids through the api.pocketsmith.com/v2 paths yourself. Through Jentic you install once, import PocketSmith from the API Directory, store the credential once, and your agent calls it.
Permission scoping
PocketSmith puts the user and institution id in the URL path (/users/{id}, /institutions/{id}), so a rule can pin your agent to one user's records. You choose the operations it may call, so destructive ones like institution deletion are not included unless you add them.
Credential isolation
Your PocketSmith developer key or OAuth token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'get the authorised user' or 'add an institution', and Jentic returns the matching PocketSmith operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using PocketSmith API through Jentic.
What authentication does the PocketSmith use?
The PocketSmith uses apiKey, oauth2 authentication. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.
Can I get the authorised user with the PocketSmith?
Yes. Use the GET /me endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the PocketSmith?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I get the authorised user through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'get the authorised user'. Jentic returns the matching PocketSmith operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the PocketSmith have?
The PocketSmith exposes 56 endpoints covering accounts, attachments, categories operations.
Can I limit what my agent is allowed to do with the PocketSmith API?
Yes. Because you run Jentic One yourself, your own rules decide which PocketSmith operations and credentials the agent may use. PocketSmith puts the user and institution id in the URL path, such as /users/{id} and /institutions/{id}, so a rule can pin the agent to a single user's records. You also choose exactly which operations it may call, so destructive ones like DELETE /institutions/{id} stay off limits unless you explicitly add them.
GET STARTED