Agency Check
Server Details
A second look before your AI agent buys, sends, books, shares, signs up, or connects an app.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- CyberStrategy1/agency-check
- GitHub Stars
- 0
- Server Listing
- Agency Check
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
The primary decision tool (agency_check) is clearly separated from the three supporting detail tools. describe_ruleset and explain_rule have some conceptual overlap, but the descriptions distinguish full ruleset metadata from a single-rule explanation well enough.
All tool names use consistent snake_case, which is readable and predictable. However, agency_check is noun_verb while the others are verb_noun, so the verb pattern is not perfectly uniform.
Four tools is well-scoped for a focused decision-review server: one main check plus three optional supporting lookups. Each tool has a clear role and does not feel padded.
The surface covers the core workflow: run a check, clarify via rule options, inspect rules, and retrieve receipts for prior checks. Minor gaps exist, such as no explicit way to list all prior checks or receipts, but the main lifecycle is covered.
Available Tools
4 toolsagency_checkCheck this firstARead-onlyIdempotentInspect
Get a second look before an agent buys, sends, books, shares, signs up, starts a trial or subscription, connects an app, or says a task is done. Call it whenever the person asks whether to go ahead with any of these, including questions like "should it go ahead?" or "is this a good idea?", before you give your own opinion. Show the card first, then add your own analysis below it. Returns one Decision Card: Ready to review, Clarify one thing, or Pause and verify, with what is supported, what is not yet supported, what is unknown, and one next step. It reviews only what is sent to it. It never contacts anyone, blocks anything, or acts. If the card asks one question, call again with the same request plus answers: {rule_id: option_key}.
Inputs: context (required), action, claims, locale, +13 more. Returns: card, receipt_id, ruleset_version
describe_rulesetDescribe the rulesetARead-onlyIdempotentInspect
Supporting detail. Show it only after the decision card, as a compact table below it, never before. Returns the ruleset version, the state-resolution order, the ten modules, and the pinned framework commits the rules trace to.
Inputs: no named parameters.
explain_ruleExplain a ruleARead-onlyIdempotentInspect
Supporting detail. Show it only after the decision card. Explains one rule by id (for example AC-R-005): what it notices, how it affects the card, and which framework controls it traces to.
Inputs: rule_id (required).
get_receiptGet a signed receiptARead-onlyIdempotentInspect
Supporting detail. Show it only after the decision card, collapsed or as a compact table below it, never before. Returns a signed NEXUS NOR v0.3 receipt for one of your own earlier checks. Receipts hold hashes and outcomes only, never what was shared.
Inputs: receipt_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Your agent asks you before it acts. You answer with one tap on your phone. Human-in-the-loop.
Give any AI agent a way to ask a person — for approval, a decision, an answer or a review.
Preventive human-approval write-gate for AI agents: writes commit only after a human approves.
Set up human approval for your AI agents' tool calls.
Related MCP Servers
AlicenseNot gradedqualityCmaintenanceEnables AI agents to request human approval before consequential actions, with policy-based routing, phone-based approver decisions, and signed audit evidence.32 npmMIT- AlicenseNot gradedqualityDmaintenanceProvides a human approval gate for AI agents, enabling interactive inline cards for approving, editing, or rejecting actions before they are executed.MIT
- AlicenseAqualityCmaintenanceThe open-source review layer for AI agents. Work done for humans is decided by humans.1810 npm1AGPL 3.0
- AlicenseNot gradedqualityCmaintenanceAI permissions layer so you don't have to give your agent keys to access your apps. Manage policies for agents and approve actions you want on your phone, watch, web or desktop app.Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.