pursestring
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LITHIC_API_KEY | No | Lithic API key. Set this to issue real Lithic virtual cards; use a sandbox key for testing or a production key for live cards. | |
| SLACK_WEBHOOK_URL | No | Slack webhook URL used to enable the human approval pause and send approval notifications. | |
| adapter.lithic.environment | No | Lithic environment setting. Set to "production" with a production LITHIC_API_KEY to issue live Lithic cards. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
PurseString governs every purchase you make. Before spending money: call submit_purchase_intent with your goal, the exact amount, the vendor domain, whether it recurs, and the free alternatives you tried. Only pay with a card from request_ephemeral_card. If a checkout hangs or errors, call request_ephemeral_card again with the same intent_id: you will get the same card, not a new charge. Never pay by any other means.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_policy_complianceA | Evaluate a purchase against the spend policy without submitting it. Returns the decision (auto_approve, require_approval or deny) and every rule that was checked. No card is issued and no human is pinged. |
| submit_purchase_intentA | Declare a purchase before making it. Policy decides: auto-approve, pause for a human (Slack/Discord), or deny. Submitting the same agent_id + task_id + vendor + amount again inside the idempotency window returns the original intent instead of creating a second one. |
| request_ephemeral_cardA | Get a single-use virtual card for an approved intent, capped at the approved amount. Calling this again for the same intent_id inside the idempotency window returns the same card: safe to retry after a hung checkout. |
| send_paymentA | Pay an approved intent through a payout rail (PayPal, Venmo, Stripe Connect, RazorpayX or Modern Treasury). The approved amount goes to the vendor's account on file in the policy; you can't choose the recipient. Each intent is paid at most once: calling again returns the existing payment, so it is safe to retry. |
| get_intent_statusB | Check an intent's status. Pass wait_seconds (up to 300) to block until a human approves or denies it, which is how the agent pauses for human-in-the-loop approval. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool maps to a distinct stage of the spend lifecycle: policy dry-run, intent submission, status polling, card issuance, and payment. The only near-overlap is check_policy_compliance versus submit_purchase_intent, but the descriptions clearly distinguish a non-submitting evaluation from an actual declaration.
All names use consistent snake_case with a clear verb_noun structure: check_policy_compliance, submit_purchase_intent, request_ephemeral_card, send_payment, get_intent_status. The pattern is predictable throughout.
Five tools is well-scoped for this narrow spending-control workflow, with each tool earning its place. There are no redundant or trivial tools.
The core lifecycle is covered: policy check, intent creation, human-in-the-loop status wait, virtual card issuance, and payment. Minor gaps exist around canceling an intent or voiding a card, but the main agent workflow has no dead ends.