Skip to main content
Glama

Malwarebazaar

by io.github.pipeworx-io

Recent Samples

recent_samples
Read-onlyIdempotent

Most recent samples in MalwareBazaar. Use the selector to pick a chunk size.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
selectorNo"time" (1h window) or "100" (last 100 samples). Default "100".

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countYesNumber of recent samples returned
queryYesQuery type used (get_recent)
statusYesQuery status (ok, no_results, or null)
samplesYesArray of most recent samples

Schema Changelog

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

  1. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "selector": "100"
+  },
+  {
+    "selector": "time"
+  }
+]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "count": {
+      "description": "Number of recent samples returned",
+      "type": "number"
+    },
+    "query": {
+      "description": "Query type used (get_recent)",
+      "type": "string"
+    },
+    "samples": {
+      "description": "Array of most recent samples",
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "status": {
+      "description": "Query status (ok, no_results, or null)",
+      "enum": [
+        "ok",
+        "no_results",
+        null
+      ],
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "query",
+    "status",
+    "count",
+    "samples"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, so the description's claim of retrieving recent samples is consistent. It adds minor behavioral context (chunk size via selector) but does not disclose details like ordering or time window interpretation, which are partially in schema.

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?

Two concise sentences with front-loaded purpose and no extraneous words. Every sentence provides value.

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

Completeness3/5

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

Given an output schema exists and annotations cover safety, the description is minimally adequate but lacks context about how recent samples are ordered or when to prefer this over siblings like 'get_sample_info' or 'search_tag'.

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% with clear enum and default. The description adds only 'pick a chunk size', which adds minimal value beyond the schema. Baseline 3 is appropriate.

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?

Description clearly states the tool provides 'most recent samples in MalwareBazaar', but does not explicitly use a verb like 'retrieves' or 'lists'. It is distinguishable from sibling tools like 'get_sample_info' or 'search_family' only by context; no differentiation is provided.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus alternatives. The description only mentions using a selector for chunk size, without stating when not to use it or referring to sibling tools.

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

All Malwarebazaar toolsInspect
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
Disambiguation1/5

The server is named Malwarebazaar, yet 28 of 36 tools have nothing to do with malware—they cover general data lookup, SEC filings, Polymarket betting, memory, and npm scanning. Even within the malware tools, search_family, search_signature, search_tag, recent_samples, and get_sample_info overlap heavily, and the Pipeworx tools include near-duplicates like ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded. An agent cannot reliably pick between these without reading lengthy descriptions.

Naming Consistency2/5

A few tools follow verb_noun patterns (search_family, search_tag, get_sample_info, list_subscriptions), but the set mixes styles: ask_pipeworx vs deep_research vs entity_profile vs polymarket_arbitrage vs generate_llms_txt vs scan_dependency. Prefixes are inconsistent (ask_*, polymarket_*, pipeworx_*, search_*, scan_*, get_*, list_*, recent_*), and there is no predictable convention tying names to their domain.

Tool Count2/5

36 tools is far beyond what a MalwareBazaar MCP server should expose; most of the tools actually belong to a separate Pipeworx data platform, with only 5-6 malware-specific tools. The count is heavy and unfocused, especially for a server whose name implies a single malware-intel corpus.

Completeness2/5

For the malware domain, the set covers lookup by hash, family, signature, tag, and recent samples, but lacks obvious operations like submitting a sample, downloading a sample, or getting detailed YARA rule hits. For the broader Pipeworx domain, the surface is sprawling and overlaps heavily (ask_pipeworx vs deep_research vs validate_claim vs bet_research), so the completeness is uneven—deep in some niches, missing core malware workflow actions.

Resources