Skip to main content
Glama
paystack-mcp

paystack-mcp

by si-essence

paystack_webhook

Read-onlyIdempotent

Verify incoming Paystack webhook signatures locally via HMAC-SHA512 over the raw body and constant-time comparison, with no network call or secret exposure.

Instructions

Verify an x-paystack-signature header locally. HMAC-SHA512 of the raw body with the configured secret key, compared in constant time. No network call. The key is never returned.

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": {
      "action": "<action>",
      "raw_body": "<raw_body>"
    },
    "name": "paystack_webhook"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
raw_bodyYes
signatureNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the description's job is to add detail, and it does: constant-time comparison, HMAC-SHA512 over the raw body, no network call, and the guarantee that the secret key is never returned. These are security-relevant traits an agent cannot infer from the annotations alone.

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

Conciseness5/5

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

Four short sentences, front-loaded with the core action and then the mechanism, with no filler. Each sentence adds distinct information (algorithm, constant-time compare, no network, key never returned).

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 single-action, local verification tool with no output schema, the definition covers the mechanism and safety profile well. The remaining gap is that it does not say what the result looks like (e.g. a validity boolean) or address the unused optional signature parameter, which matters at a 0% schema coverage.

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

Parameters3/5

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

Schema description coverage is 0%, so the description must compensate. It implicitly maps 'x-paystack-signature header' to the signature parameter and 'raw body' to raw_body, conveying that the unparsed body must be supplied, but it never mentions the action enum ('verify_signature') or the optionality and origin of the signature parameter, so compensation is only partial.

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 description opens with a specific verb and resource: 'Verify an x-paystack-signature header locally', and immediately names the algorithm (HMAC-SHA512 over the raw body) and the secret key. This is clearly distinguishable from every sibling tool, which are Paystack API read/query resources, since this one is entirely local verification.

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 context of use is clear: verifying an incoming Paystack webhook signature, done locally with 'No network call', which tells the agent this never hits the API. It does not state explicit exclusions or name alternatives, but the sibling catalog contains no comparable verification tool, so there is no plausible confusion.

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