turva-mcp

Web-security scan evidence

get_security_evidence

Read-onlyIdempotent

Returns the latest public web-security scan results for turva.dev's own domain (Hardenize, Internet.nl site and mail), each with its scan date. Use this when a user asks about turva.dev's own security posture or wants evidence beyond agent-readiness scores. For the agent-readiness score itself, which is a separate measurement, use get_agent_readiness instead. Read-only: returns static JSON that is compiled into the Worker, so it changes nothing and updates only on deploy.

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description
`note`	Yes	Why turva.dev publishes the scan results of its own domain.
`scans`	Yes	Web-security scan results, one per provider and test.
`domain`	Yes	The domain the scans are about.
`measured_at`	Yes	Date of the scans, YYYY-MM-DD.

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedOct 15, 2026

addedOutput schema / properties / domain / description
```
Added value: +"The domain the scans are about."
```

addedOutput schema / properties / note / description

Added value: +"Why turva.dev publishes the scan results of its own domain."

addedOutput schema / properties / scans / description

Added value: +"Web-security scan results, one per provider and test."

changedOutput schema / properties / scans / items / properties / measured_at / description

Previous value: -"Date of this reading, YYYY-MM-DD, when it differs from the top-level date."New value: +"Date of this reading, YYYY-MM-DD, on a reading that carries its own date. It can equal the top-level date."

addedOutput schema / properties / scans / items / properties / note / description

Added value: +"What passed in full and where the points were lost. Absent when the provider adds no note."

addedOutput schema / properties / scans / items / properties / provider / description
```
Added value: +"The name of the scan provider."
```

addedOutput schema / properties / scans / items / properties / result / description

Added value: +"The overall result as text, for a provider that reports passed categories instead of a number. Absent when a numeric score is given."

addedOutput schema / properties / scans / items / properties / scale / description

Added value: +"The range of the score, written as low-high. Absent when there is no numeric score."

addedOutput schema / properties / scans / items / properties / score / description

Added value: +"The numeric score, on the range given in scale. Absent when the provider reports a text result."

addedOutput schema / properties / scans / items / properties / url / description
```
Added value: +"The provider's public report page for the domain."
```

Changed2 schema fields changedOct 2, 2026

addedOutput schema / properties / scans / items / properties / measured_at

Added value: +{
+  "description": "Date of this reading, YYYY-MM-DD, when it differs from the top-level date.",
+  "type": "string"
+}

changedOutput schema / properties / scans / items / required

Previous value: -[
-  "provider"
-]New value: +[
+  "provider",
+  "url"
+]

Changed1 schema field changedOct 2, 2026
- changedOutput schema / properties / scans / items / required
```
Previous value: -[
-  "provider",
-  "url"
-]New value: +[
+  "provider"
+]
```

Changed3 schema fields changedSep 23, 2026

addedInput schema / $schema

Added value: +"https://json-schema.org/draft/2020-12/schema"

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

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "domain": {
+      "type": "string"
+    },
+    "measured_at": {
+      "description": "Date of the scans, YYYY-MM-DD.",
+      "type": "string"
+    },
+    "note": {
+      "type": "string"
+    },
+    "scans": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "note": {
+            "type": "string"
+          },
+          "provider": {
+            "type": "string"
+          },
+          "result": {
+            "type": "string"
+          },
+          "scale": {
+            "type": "string"
+          },
+          "score": {
+            "type": "number"
+          },
+          "url": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "provider",
+          "url"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "domain",
+    "measured_at",
+    "scans",
+    "note"
+  ],
+  "type": "object"
+}

Changed1 schema field changedJul 29, 2026
- removedInput schema / $schema
```
Removed value: -"http://json-schema.org/draft-07/schema#"
```
First observedJun 24, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description reinforces that while adding a trait the annotations cannot express: the data is static JSON compiled into the Worker, changes nothing, and refreshes only on deploy. That freshness/provenance caveat is genuinely useful for an agent deciding whether to present the results as current.

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 sentences, front-loaded with what is returned and scoped before the routing guidance. Every sentence carries load: purpose, when-to-use/alternative, and the read-only/static-data note.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no prose explanation, and the description still names the three sources and the scan-date field. For a zero-parameter, read-only lookup tool, an agent has everything needed to select and call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the baseline is 4 and there is no argument syntax the description could clarify. It does implicitly bound the output by naming the three scan sources and the included scan date, which adds a little orientation for a no-arg call.

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?

States a specific verb and resource ('Returns the latest public web-security scan results'), names the domain scope (turva.dev's own domain), and enumerates the three underlying sources (Hardenize, Internet.nl site and mail). It explicitly distinguishes itself from the sibling get_agent_readiness, so an agent can route between them without opening either schema.

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

Usage Guidelines5/5

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

Gives an explicit when-to-use condition ('when a user asks about turva.dev's own security posture or wants evidence beyond agent-readiness scores') and names the alternative plus the condition that selects it ('For the agent-readiness score itself ... use get_agent_readiness instead'). Both the use case and the exclusion are stated, leaving nothing to inference.

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

All turva-mcp tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?