Vigil — an outside witness for AI agents

vigil_set_watchdog

Arm a dead-man switch. Register an interval and an https webhook; then call vigil_heartbeat before each interval elapses. Miss one and Vigil POSTs a signed 'absence' payload to your webhook once. Free tier: 1 watchdog.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes	A name for this watchdog, 1-64 chars.
`message`	No	Optional note included in the absence payload, <=2000 chars.
`vigil_key`	No	Legacy credential argument. Prefer the HTTP Authorization: Bearer header; omit this argument when that header authenticates the request.
`interval_s`	Yes	Seconds allowed between heartbeats, 60..604800.
`webhook_url`	Yes	An https URL resolving to a public address; fired once on a missed heartbeat.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedSep 6, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations provided, the description carries the full burden and discloses important behavior: a missed heartbeat causes exactly one signed 'absence' POST to the webhook, and the free tier allows one watchdog. It does not mention auth requirements, idempotency, or response details, but the core behavioral contract is clear.

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?

Three short sentences, front-loaded with the action and followed by the operational consequence. No filler or repetition.

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 tool with no output schema and no annotations, the description adequately covers the lifecycle, the trigger condition, and the free-tier limit. It leaves out return-value and error semantics, but those are minor for a straightforward watchdog-creation operation.

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 100%, so the schema already documents all parameters. The description adds workflow context for interval_s and webhook_url but does not need to explain each parameter further.

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 uses specific verbs ('Arm', 'Register') and defines the exact artifact: a dead-man switch with an interval and webhook, plus the required follow-up call to vigil_heartbeat. This clearly differentiates it from sibling heartbeat, status, and deletion tools.

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?

It gives a clear usage sequence: register interval and webhook first, then call vigil_heartbeat before each interval elapses. It does not explicitly say when not to use this tool versus alternatives, but the intended workflow is evident.

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

All Vigil — an outside witness for AI agents tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.3/5.0

Disambiguation4/5

The tools are organized into clear domains—receipts/notarization, leases, journals, watchdogs, and account management—and each tool has a distinct resource or action. Minor confusion is possible between vigil_anchor and vigil_anchors, or between the various verification tools, but the descriptions generally make the boundaries clear.

Naming Consistency3/5

All tools share the vigil_ prefix and use snake_case, but the verb/noun ordering is inconsistent: vigil_get_receipt and vigil_delete_watchdog use verb-first, while vigil_journal_get and vigil_journal_delete use resource-first. Several tools are also pure nouns (vigil_chain, vigil_usage, vigil_lease_status), making the overall pattern mixed but still readable.

Tool Count2/5

At 26 tools, this exceeds the 25+ threshold and feels heavy for a single MCP server, even though the tools cluster into several subsystems. Some status, info, and lease-listing tools could plausibly be consolidated without losing much capability.

Completeness4/5

The core lifecycle coverage is strong: receipts can be created, read, verified, and audited via the chain; leases have grant/renew/revoke/status/verify; journals have full CRUD; watchdogs have set/delete/status/heartbeat. Minor gaps exist, such as no direct way to update a watchdog without deleting and recreating it, but these are workable.

Resources

Need Help?