Skip to main content
Glama
Sign In
@cubiczan/chp-mcp

@cubiczan/chp-mcp

by Cubiczan
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

issue_approval_receipt

Records a human allow/deny decision and returns a signed approval receipt for audit and verification.

Instructions

Record a human allow/deny and return a signed approval receipt. The MAC covers actor, tool, resource, args hash (host ∪ model), policy version, risk, expiry, decision, and nonce (HMAC-SHA256 over CHP canonical JSON). Signing key from CHP_RECEIPT_KEY / AUDIT_LEDGER_KEY, or the documented insecure default.

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": {
      "actor": "<actor>",
      "call": "<call>",
      "policy": "<policy>",
      "decision": "<decision>"
    },
    "name": "issue_approval_receipt"
  }
}

Input Schema

NameRequiredDescriptionDefault
callYes
actorYesHuman approver identity (email or handle)
policyYes
reasonNoWhy the human allowed or denied
decisionYesHuman decision — logged on every issue
signing_keyNoOverride HMAC key (tests / local only)
ttl_secondsNoReceipt lifetime; must not exceed policy.max_ttl_seconds

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.5/5.0
Behavior3/5

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

The description mentions side effects like recording the decision and generating a MAC, but it does not explain the return format, verification process, or whether the tool is idempotent. It leaves out details about how host_bound and _meta affect behavior, and lacks an explicit statement about read/write nature.

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

Conciseness2/5

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

The description is verbose and highly technical, repeating details from the schema (MAC coverage, signing key source) without adding clarity. It is not concise and may overwhelm an agent with jargon, making it less effective than a shorter, more focused summary.

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

Completeness2/5

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

The description assumes prior knowledge of the CHP system (e.g., CHP canonical JSON, cubiczan.principal, host_bound) and does not explain these concepts. For a standalone agent, this is incomplete; it lacks definitions and fails to specify how to obtain required host-injected fields or interpret the receipt output.

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?

The schema provides descriptions for many parameters (e.g., actor, decision, ttl_seconds), but some fields like 'call' at the top level lack descriptions, and the tool description does not add meaning beyond what the schema already gives. The description repeats some schema details but does not clarify ambiguous parameters like 'signing_key' or 'host_bound'.

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 clearly states the tool records a human allow/deny decision and returns a signed receipt. It specifies the exact action and outcome, leaving no ambiguity about the tool's primary function.

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 implies the tool is used after a human decision, but it does not explicitly contrast with sibling tools like approve_spend or request_authorization. The intended context is inferable, though not spelled out.

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

Deploy Server

Other Tools