mild-run
Description
Human approval gate for AI agents. Intercepts Stripe, Gmail, and Slack actions — sends a Telegram tap to approve or block before anything executes. No code, no webhook, no SDK. Free tier: 30 approvals/month.
What our measurements say
mild-run is a remote MCP server published at mcp.mild.run. It has been probed 6 times since 9/10/2026. It answered in 6 of them (100.0%), a near-uninterrupted record. Median response time is 549 ms, a delay an agent will notice. It offers a narrow, focused set of 7 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Agent readability score
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Agent readability score
Strengths
- Tool names are clear and action-specific (e.g., stripe_refund, gmail_send_email).
- Descriptions explain use cases (e.g., 'triggers human approval flow') and constraints (e.g., 'irreversible actions').
Weaknesses
- Some parameter definitions are incomplete or ambiguous (e.g., 'c' in stripe_refund, truncated fields in stripe_payout).
- No explicit error handling or failure scenarios documented for approval flows.
- Descriptions for 'get_approval_status' are overly verbose and lack focus on when to use it.
get_approval_status— Description lacks clarity on specific use cases beyond polling.stripe_refund— Argument 'c' is undefined and unclear.stripe_payout— Description is cut off mid-parameter (e.g., 'description: Optional description for the ').gmail_send_email— No explicit error handling for failed email sends.
Verdict
Event narrative
Risk: medium
- 2026-09-10T21:16:35.016Z — era changed from auth-gated to legacy · server now operates under legacy compliance framework
- 2026-09-11T05:44:28.819Z — complianceScore changed from null to 100 · full compliance achieved with no smoke test failures reported
Advice
Schema compliance
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
- tools/list schema valid
- inputSchema is valid JSON Schema
- Smoke test not run this round
- Cold-start: cold 201ms → warm 179ms (penalty 22ms)
Availability history
Event log
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
- Server build: — → 1.29.0
- Supported versions: — → 2025-11-25
- Era changed: Auth-gated → Legacy
- Added to watch — era: Auth-gated
Get your badge
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/dev-mild-run-mild-run)<a href="https://mcpmetrics.io/servers/dev-mild-run-mild-run"><img src="https://mcpmetrics.io/badge/dev-mild-run/mild-run/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to see