Vigil — an outside witness for AI agents

vigil_journal_put

Destructive

Store an opaque blob under a slug (overwrites). Encrypt client-side: the server stores exactly the bytes supplied and cannot enforce client encryption. Send bytes as base64. Free tier: 4 slots, 64KB each. Destructive when the slug exists: previous bytes are replaced with no version history or undo.

Input Schema

TableJSON Schema

Name	Required	Description
`slug`	Yes	1-64 alnum/-/_ chars.
`vigil_key`	No	DEPRECATED legacy account-wide credential, including deletion and permission issuance. Prefer the client-injected HTTP Authorization: Bearer header; omit this argument when that header authenticates the request. This is not a scoped agent token.
`data_base64`	Yes	The (already-encrypted) bytes, base64-encoded.

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedSep 14, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / examples

Added value: +[
+  {
+    "data_base64": "ZW5jcnlwdGVkLWJ5dGVz",
+    "slug": "encrypted-state"
+  }
+]

addedInput schema / properties / data_base64 / maxLength
```
Added value: +100000
```
addedInput schema / properties / slug / maxLength
```
Added value: +64
```
addedInput schema / properties / slug / minLength
```
Added value: +1
```
addedInput schema / properties / slug / pattern
```
Added value: +"^[A-Za-z0-9_-]{1,64}$"
```
addedInput schema / properties / vigil_key / deprecated
```
Added value: +true
```

changedInput schema / properties / vigil_key / description

Previous value: -"Legacy credential argument. Prefer the HTTP Authorization: Bearer header; omit this argument when that header authenticates the request."New value: +"DEPRECATED legacy account-wide credential, including deletion and permission issuance. Prefer the client-injected HTTP Authorization: Bearer header; omit this argument when that header authenticates the request. This is not a scoped agent token."

addedInput schema / properties / vigil_key / maxLength
```
Added value: +256
```
addedInput schema / properties / vigil_key / minLength
```
Added value: +1
```

First observedSep 6, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, but the description adds valuable specifics: previous bytes are replaced with no version history or undo, the server stores exactly the supplied bytes, and client-side encryption is the caller's responsibility. This goes beyond the annotation and helps the agent anticipate real consequences.

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 tight sentences front-load the core action and overwrite behavior, then cover encryption expectations, size limits, and destructiveness. Every sentence earns its place with 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 write tool with no output schema, the description adequately covers the destructive nature, storage limits, encoding requirement, and encryption responsibility. It does not describe the response format, but that is not essential for correct invocation. Minor ambiguity remains between the 64KB stated limit and the schema's 100000-character base64 maxLength, but this does not block usage.

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 slug, data_base64, and vigil_key fully. The description reinforces the base64 requirement and the opaque-blob semantics, but adds little meaning beyond the schema, so the baseline of 3 is appropriate.

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 opens with a specific verb and resource: 'Store an opaque blob under a slug (overwrites).' It clearly identifies the write operation and the key behavioral feature (overwriting), which differentiates it from sibling journal operations like vigil_journal_get and vigil_journal_delete without needing to inspect schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies appropriate use for storing client-side encrypted blobs and explicitly warns about the free tier limits and base64 encoding requirements. However, it does not name alternatives or state when not to use this tool, leaving the differentiation from sibling tools implicit rather than explicit.

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

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?