Skip to main content
Glama

BitFeed top-up (Lightning or USDC)

topup

Add prepaid balance. Lightning: pass amount_sats (minimum 100) to get an invoice; pay it, then call again with payment_hash (or GET the check_url) to credit the account. USDC on Base (x402): pass amount_usd (minimum 0.10) to get the payment requirements, sign accepts[0], then call again with the same amount_usd plus x402_payment (or params._meta['x402/payment']); your USDC is settled first and the receipt is in _meta['x402/payment-response']. USDC funds pay deliveries at USDC list prices, sats funds at sats prices. Feeds paused for zero balance resume automatically after credit.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "bitfeed_token": "<bitfeed_token>"
    },
    "name": "topup"
  }
}

Input Schema

NameRequiredDescriptionDefault
amount_usdNoUSDC to add over x402 (0.10 to 50), e.g. "1.00".
amount_satsNoSats to add (100 to 1,000,000).
payment_hashNoOptional. If set, check this invoice instead of creating one.
x402_paymentNoOptional x402 payment (USDC on Base): base64 PaymentPayload (v2, or v1 X-PAYMENT format) signed for accepts[0] of this tool's payment_required result. Alternative to params._meta['x402/payment']. Omit both to receive the payment requirements.
bitfeed_tokenYesBitFeed account token (btf_…). Also accepted as Authorization: Bearer. Omit on the first create_feed to open an account; the token is returned once.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / amount_usd
      Added value: +{
      +  "description": "USDC to add over x402 (0.10 to 50), e.g. \"1.00\".",
      +  "type": "string"
      +}
    • addedInput schema / properties / x402_payment
      Added value: +{
      +  "description": "Optional x402 payment (USDC on Base): base64 PaymentPayload (v2, or v1 X-PAYMENT format) signed for accepts[0] of this tool's payment_required result. Alternative to params._meta['x402/payment']. Omit both to receive the payment requirements.",
      +  "type": "string"
      +}
  2. Added

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses the credit is prepaid and denomination-scoped: USDC funds pay deliveries at USDC list prices, sats funds at sats prices. It also reveals a real side effect an agent could not infer elsewhere — feeds paused for zero balance resume automatically after credit — and tells where the x402 receipt lands (_meta['x402/payment-response']). That is substantive behavioral context, not restatement.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core action is front-loaded in the first three words, and the rest is organized rail-by-rail (Lightning, then USDC), with the funds/price mapping and auto-resume note closing it out. It is a dense single paragraph with no filler, though the x402 sentence packs several clauses and could be broken for easier scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter balance-mutating tool with no output schema and only safety annotations, the description covers both payment flows end to end, minimums, credential placement, and the post-credit resume behavior. Gaps remain around invoice expiry, behavior on failed or already-used payments, and idempotency of a repeat call, which matter for a payment tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds sequencing meaning the schema cannot: payment_hash is the second leg of an invoice flow (or GET check_url instead), and x402_payment must be signed for accepts[0] of this tool's payment_required result and supplied alongside the same amount_usd. The minimums (100 sats, 0.10 USDC) are repeated from the schema, which is why this is not a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence, "Add prepaid balance," gives a specific verb and resource, and the description immediately splits into the two concrete funding rails (Lightning sats invoice vs USDC on Base via x402). This is unmistakably different from any sibling such as get_balance or create_feed; an agent knows exactly what capability this tool exposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives an explicit two-step invocation pattern for each rail: pass amount_sats to get an invoice, pay, then call again with payment_hash or GET check_url; pass amount_usd to get requirements, sign accepts[0], then call again with amount_usd plus x402_payment. It also states the alternative encodings (payment_hash vs check_url, x402_payment vs params._meta['x402/payment']) and "omit both to receive the payment requirements." It stops short of naming a sibling to check the resulting balance or stating when not to top up, so it is strong but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources