cve-intelligence

get_updates

Read-only

The publication change stream: what this site published, stamped with OUR publish time (first_published, kev_added, detection_added, remediation_added, first_sighted, chain_added, and the BOD 26-04 Table 1 input changes ssvc_changed, kev_due_changed, kev_triage_flag_changed, kev_notes_changed, which fire on value changes between snapshots; a timestamp refresh alone fires none). Pass since (YYYY-MM-DD, strictly-after) on the first call, then the returned next_cursor to continue. Over MCP the stream covers the last 30 days, up to 50 events per call: since defaults to 30 days ago, and an earlier since or cursor returns an error. Optional cve scopes the stream to one CVE's change history, with no 30-day cutoff; follow next_cursor past the first 50 events. Events for withdrawn CVE ids are omitted. The keyed GET /api/updates walks the full history.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_updates"
  }
}

Input Schema

Name	Required	Description
`cve`	No	Scope to one CVE's change history, such as CVE-2024-3400
`type`	No
`limit`	No	1..50 (default 50)
`since`	No
`cursor`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 22, 2026
- addedInput schema / properties / limit / description
```
Added value: +"1..50 (default 50)"
```

Changed1 schema field changedSep 22, 2026

changedInput schema / properties / type / enum

Previous value: -[
-  "first_published",
-  "kev_added",
-  "detection_added",
-  "remediation_added",
-  "first_sighted",
-  "chain_added"
-]New value: +[
+  "first_published",
+  "kev_added",
+  "detection_added",
+  "remediation_added",
+  "first_sighted",
+  "chain_added",
+  "ssvc_changed",
+  "kev_due_changed",
+  "kev_triage_flag_changed",
+  "kev_notes_changed"
+]

Changed1 schema field changedSep 15, 2026

changedInput schema / properties / type / enum

Previous value: -[
-  "first_published",
-  "kev_added",
-  "detection_added",
-  "remediation_added",
-  "first_sighted"
-]New value: +[
+  "first_published",
+  "kev_added",
+  "detection_added",
+  "remediation_added",
+  "first_sighted",
+  "chain_added"
+]

Changed1 schema field changedSep 11, 2026

changedInput schema / properties / type / enum

Previous value: -[
-  "first_published",
-  "kev_added",
-  "detection_added",
-  "remediation_added"
-]New value: +[
+  "first_published",
+  "kev_added",
+  "detection_added",
+  "remediation_added",
+  "first_sighted"
+]

Changed1 schema field changedSep 3, 2026

changedInput schema / properties / cve / description

Previous value: -"Scope to one CVE's change history, e.g. CVE-2024-3400"New value: +"Scope to one CVE's change history, such as CVE-2024-3400"

Changed1 schema field changedSep 2, 2026

addedInput schema / properties / cve

Added value: +{
+  "description": "Scope to one CVE's change history, e.g. CVE-2024-3400",
+  "type": "string"
+}

First observedAug 3, 2026

TDQS

A4.4/5.0

Behavior5/5

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

The description discloses numerous behavioral traits beyond annotations: the 30-day window, 50-event cap, error on earlier since or cursor, no cutoff when scoped to a CVE, omission of withdrawn CVE ids, and the fact that timestamp refreshes alone fire no events. This is rich, specific context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but front-loads the core concept and then adds necessary operational details. It could be more structured (e.g., bullet points) for readability, but every sentence carries useful information for correct invocation.

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 complex streaming tool with no output schema, the description covers usage, limits, errors, and scoping well. It does not describe the structure of returned events beyond the next_cursor and event types, leaving a minor gap in what the agent should expect in the response.

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

Parameters5/5

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

With only 40% schema coverage, the description compensates well: it explains since format and semantics (strictly-after), cursor pagination, CVE scoping, the effect of limit (up to 50 events), and provides detailed meaning for each type enum value including when they fire.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource (publication change stream) and lists the exact event types it covers. It distinguishes from the full history API endpoint but does not explicitly differentiate from sibling tools like search_cves or get_cve.

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 clear instructions on how to call the tool: pass since on first call, use next_cursor, note the 30-day window and 50-event limit, and error conditions. It does not, however, state when to use this tool versus alternatives such as search_cves.

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

All cve-intelligence 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?