greynoise-mcp-server

Official

by GreyNoise-Intelligence

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

Search Sessions

search-sessions

Read-only

Query and filter GreyNoise sensor network sessions by time range and Lucene syntax to retrieve paginated session details, including IPs, ports, timestamps, traffic volume, and classification.

Instructions

Query and filter GreyNoise sensor network sessions over a time range. Returns a paginated list with source/destination IPs and ports, timestamps, byte/packet counts, and classification. Use Lucene query syntax (e.g. destination.port:443).

Input Schema

Name	Required	Description
`page`	No	Page number (default: 1)
`query`	No	Lucene query string to filter sessions
`scope`	No	Data scope: workspace (default) or demo
`sort_by`	No	Field to sort by (default: lastPacket)
`end_time`	Yes	End time, ISO 8601 (e.g. 2025-01-07T23:59:59Z)
`page_size`	No	Results per page, 1-100 (default: 25)
`sort_desc`	No	Sort descending (default: true)
`start_time`	Yes	Start time, ISO 8601 (e.g. 2025-01-01T00:00:00Z)

Output Schema

Name	Required	Description	Default
`total`	No
`sessions`	No
`pagination`	No
`request_metadata`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.5.5Nov 2, 2026
- removedOutput schema / properties / sessions / items / properties / firstPacket / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "number"
-  }
-]
```
- addedOutput schema / properties / sessions / items / properties / firstPacket / type
```
Added value: +[
+  "string",
+  "number"
+]
```
- removedOutput schema / properties / sessions / items / properties / lastPacket / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "number"
-  }
-]
```
- addedOutput schema / properties / sessions / items / properties / lastPacket / type
```
Added value: +[
+  "string",
+  "number"
+]
```
Addedv0.5.3Jul 21, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds the paginated result shape and the Lucene-syntax requirement, which is genuinely useful behavior context, but says nothing about time-range limits, rate limits, or result caps beyond what the schema states.

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?

Three sentences, front-loaded with purpose, then return shape, then the query-syntax hint. The field enumeration in sentence two overlaps with the output schema, so it earns slightly less than a perfect score, but nothing is padded.

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?

With an output schema, 100% parameter coverage, and annotations present, the description covers the remaining gaps (purpose, query syntax, result nature). Minor omissions such as scope=workspace vs demo and sort behavior are already handled by the schema, so the description is complete enough to call the tool 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?

Schema coverage is 100%, so the baseline is 3. The description goes beyond the schema by specifying Lucene query syntax and giving a concrete example ('destination.port:443'), which meaningfully constrains how the `query` parameter should be formed.

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?

States a specific verb and resource — 'Query and filter GreyNoise sensor network sessions over a time range' — plus what a result contains (IPs, ports, timestamps, byte/packet counts, classification). That is enough to distinguish it from single-session or export siblings, though no sibling is named explicitly.

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?

Usage is implied by 'over a time range' and 'paginated list', which suggests exploratory/browsing use rather than fetching one session or exporting. However, the description never says when to prefer this over get-session, session-counts, gnql-query, or export-session-data, all of which sit adjacent in the tool list.

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

Deploy Server