Approval Rules
Server Details
Auto-approve small agent actions under your rules; approval cards for the rest.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
check_action (pre-action gate) and get_decision (post-card status check) are related but clearly differentiated by their descriptions, and get_rules/set_rules form a clean read/write pair. usage_and_upgrade and weekly_report are distinct informational tools.
Five of six names are snake_case verb_noun (check_action, get_decision, get_rules, set_rules), but usage_and_upgrade and weekly_report deviate to noun-style phrasing. Still readable and predictable overall.
Six tools is well-scoped for an approval-rules server, covering checking, decision retrieval, rule read/write, usage, and reporting without redundancy.
The approval lifecycle (check action, retrieve decision, read/write rules, usage, report) is largely covered, though there is no explicit rule-delete or rule-list operation beyond get_rules/set_rules replacement. Minor gap agents can work around.
Available Tools
6 toolscheck_actionAInspect
Before a consequential action, ask whether the user's rules auto-approve it. Returns auto_approve, needs_approval (with a plain-English approval card and a link the user can tap) or deny. Free plan is watch-only: it reports what it WOULD decide and logs it for the weekly report, but nothing counts as approved, so ask your user as you normally would.
Inputs: action (required).
get_decisionBInspect
Check whether the user approved or rejected an approval card (by card_id and card_token). Only act when status is approved.
Inputs: card_id (required), card_token (required).
get_rulesBInspect
Show the rules in effect for your key (or the default starter rules).
Inputs: no named parameters.
set_rulesAInspect
Save the user's rules (needs an API key so they stay yours). Each rule: {name, when:{type:[...], max_usd, min_usd, reversible, target_ends_with:[...]}, verdict:"auto"|"ask"|"deny"}. First matching rule wins; anything unmatched needs approval. Call once without confirm to preview, then with confirm=true.
Inputs: rules (required), confirm.
usage_and_upgradeBInspect
Show today's usage for your key or IP and the $49/month All Access upgrade link (cloudforbots.com/offer). Free tier: 200 calls/day. Not metered.
Inputs: no named parameters.
weekly_reportAInspect
Draft a plain-English report of the last 7 days: actions checked, how many your rules would auto-approve, how many needed you, top kinds of asks, and rule suggestions. Read-only; sends nothing.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Deterministic allow/require_approval/deny verdicts for agent actions, before they happen.
Authorize AI agent tool calls before they run: policy-as-code, human approval, signed receipts.
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
Pre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides a human approval gate for AI agents, enabling interactive inline cards for approving, editing, or rejecting actions before they are executed.MIT
- 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
- AlicenseNot gradedqualityDmaintenanceAgentPay is the authorization layer between an AI agent and real spending. You define the rules — spending caps, allowed merchants, time windows — and every purchase attempt the agent makes is checked against them in real time. Approved transactions go through. Anything outside the mandate is blocked and logged. No more babysitting every agent action. No more runaway charges.MIT
- FlicenseNot gradedqualityDmaintenanceEnables human-in-the-loop authorization for AI agent transactions, allowing real-time approval or denial of purchases based on configurable spending limits, vendor blocklists, daily caps, and category restrictions.1-
Glama MCP Gateway
Add one secure layer between your agents and this server.