Skip to main content
Glama

Search disclosed reports

search_reports
Read-onlyIdempotent

Search publicly disclosed HackerOne vulnerability reports to find prior art by technique, technology, target, bug class, or CVE. Filter results and page through disclosures.

Instructions

Search the archive of publicly disclosed HackerOne vulnerability reports (real bugs found in real programs). Use it to find prior art for a technique, a technology, a target or a bug class: e.g. "ssrf pdf generator", "graphql idor", "oauth redirect_uri", "cache poisoning", "jwt none algorithm", "CVE-2021-44228". Full-text BM25 over titles, weakness, class, program and the Hacktivity summary; acronyms (xss, sqli, ssrf, idor, rce, ato…) are expanded. Combine with filters. Leave query empty and sort by "newest" for the latest disclosures, or by "votes"/"bounty" for the most notable ones. Each result has an id: pass it to get_report for the full write-up (steps to reproduce, payloads, impact) or to find_similar.

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": "search_reports"
  }
}

Input Schema

NameRequiredDescriptionDefault
cveNoExact CVE id, e.g. "CVE-2023-38545".
sortNoDefault: "relevance" when there is a query, otherwise "newest".
limitNoResults to return (default 10, max 50).
queryNoFree-text search, e.g. "blind ssrf via webhook" or "stored xss svg upload". Optional when filters are given.
stateNoReport outcome. Most disclosed reports are "resolved".
topicNoCross-cutting topic id, e.g. account-takeover, oauth, saml-sso, 2fa, password-reset, jwt, graphql, cors, cache, postmessage, ssti, deserialization, prototype-pollution, android, ios, cloud, secrets, ai, supply-chain.
offsetNoSkip this many results, for paging.
programNoHackerOne program handle or name, e.g. "gitlab", "shopify", "Internet Bug Bounty".
categoryNoBug class id, e.g. xss, sqli, rce, ssrf, csrf, idor, access-control, auth, info-disclosure, path-traversal, open-redirect, business-logic, race, request-smuggling, xxe, upload, subdomain-takeover. See list_categories.
min_cvssNoMinimum CVSS score.
reporterNoHackerOne username of the researcher.
severityNoOnly these severities, e.g. ["critical","high"].
weaknessNoCWE id (e.g. "CWE-918") or part of the HackerOne weakness name (e.g. "Stored").
min_bountyNoMinimum disclosed bounty in USD.
has_summaryNoOnly reports that have a Hacktivity summary.
disclosed_afterNoEarliest disclosure date, inclusive: "2023", "2023-06" or "2023-06-30".
disclosed_beforeNoLatest disclosure date, inclusive.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so safety is covered; the description goes further by disclosing the retrieval mechanics (BM25 full-text over titles, weakness, class, program, and the Hacktivity summary) and the acronym-expansion behavior that silently broadens matching. It doesn't discuss result count limits beyond what the schema states, but for a read-only search that gap is minor.

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?

Front-loaded with the resource and the primary use case, then examples, then the query-less escape hatch, then the handoff to sibling tools — a logical order with no filler sentences. It runs slightly long in the example enumerations (the acronym list and sample queries), which is useful but denser than strictly necessary.

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?

For a 17-parameter, zero-required read tool with no output schema, the description supplies the missing connective tissue: the ranking model, acronym handling, the default-sort rule, and what the id in each result is for. An agent can compose a correct call and a correct next step from this text alone.

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 earns above that by explaining parameter interaction rather than restating fields — notably that `query` may be left empty and that `sort` semantics depend on whether a query is present, and that filters can be combined with full-text. The acronym expansion also changes how an agent should phrase `query` values.

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 (full-text search over the archive of publicly disclosed HackerOne reports) and adds the scope detail that matters: 'real bugs found in real programs'. It also separates itself from sibling tools by naming get_report and find_similar as the follow-up paths, so an agent knows this is the discovery step, not the retrieval step.

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 concrete when-to-use scenarios (prior art for a technique, technology, target, or bug class) with worked query examples, plus an explicit alternative workflow: empty `query` sorted by 'newest' for the latest, or 'votes'/'bounty' for the most notable. It then routes the agent onward via the result id to get_report or find_similar, which is exactly the when/when-not/alternatives pattern.

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