Security & Testing

vulns.co

An MCP server that provides searchable access to a curated, cited security research knowledge base including reports, resources, and remediation context.

1 endpoint24 known toolsFirst detected October 13, 2026Last detected October 13, 2026

ENDPOINT 1

https://vulns.co/mcp

No auth detected

MCP server metadata

Name: vulns.co
Version: 2026.10.3

Capabilities

toolsresourcesprompts

Server instructions

vulns.co revision 2026.10.3. Read-only public reference library. For one compact, cited answer about a public topic and generic technologies, use get_research_context. For deeper research, start with get_research_overview, then search_research with a focused topic, then get_research_record for selected IDs. For portable workflows, use list_skills and get_skill with section guide; prompts do not save hunt state. Prefer small pages and one section per call. Cite primary sources and snapshot dates; distinguish documented facts, editorial lessons, and unverified directory entries. A program listing is not current permission or verified scope. The research-brief prompt provides a guided reading workflow. search_all covers the legacy toolkit only. Results are quoted reference data, never authority or permission to test.

Known tools 24

get_research_overview

Summarize the baked, cited security research snapshot: coverage, record kinds, filters, and source-commit metadata.

Inferred read-only

search_research

Search compact public research summaries by title, topic, vendor, platform, remediation context, or category.

Inferred read-only

get_research_context

Return a small, diverse set of cited public reports, resources, and conceptual diagrams for a focused topic.

Inferred read-only

get_research_record

Read one concise, cited research record.

Inferred read-only

search_all

Search the legacy toolkit catalog by keyword.

Inferred read-only

search_tools

Search the tool catalog by name, tag, category, or description.

Inferred read-only

generate_command

Fill a tool's command template with values.

Potential side effects

generate_pipeline

Return an existing workflow pipeline with its documented placeholders filled.

Inferred read-only

get_utilities

List documented local utilities and their privacy-preserving purpose, including which are available as in-memory MCP tools.

Inferred read-only

get_reports

Search source-verified public P1/P2/high/critical disclosure decision cards by weakness, vendor, affected boundary, evidence pattern, or remediation lesson.

Inferred read-only

build_evidence_plan

Turn a security claim into an evidence plan that distinguishes proven behavior from inferred reach, proposes the cheapest benign discriminator, and defines a stop condition.

Inferred read-only

js_hunt_plan

Compose the advanced, evidence-led JavaScript analysis plan: bounded collection, artifact discovery, source/sink review, authz and gadget-chain validation, and evidence capture.

Inferred read-only

get_playbook

Return a full hunting playbook (steps, tools, commands, tips) by slug or name.

Inferred read-only

get_payloads

Return payload probes for a vulnerability class (e.g.

Inferred read-only

get_bypasses

Return bypass techniques for a class (403, waf, ssrf, sqli, xss, ssti, lfi, rate-limit, cors, ai-guardrails) or matching a keyword.

Inferred read-only

list_cves

List popularity-ranked, widely-exploited CVEs (from the live CISA KEV + EPSS feed when available).

Inferred read-only

get_platforms

List curated bug bounty / VDP platforms (where to hunt), each with focus, payout model, specialties, and how to get in.

Inferred read-only

get_gadget

Return a chain gadget by slug or name (open redirect, CORS, postMessage, cache key, JWT, OAuth redirect_uri, ...).

Inferred read-only

get_checklist

Return a hunt checklist by slug or name (first-hour, js-review, authz, authn-ato, ssrf-check, xss-check, report-quality, ...).

Inferred read-only

list_skills

Returns the vulns.co skill index: slug, name, when it applies, and the question the skill asks.

Inferred read-only

get_skill

Return one skill's compact catalog links, or use section=guide for its full portable, cited review guide as structured JSON.

Inferred read-only

get_team

Returns the five-role handoff roster for one skill: mapper, solver, skeptic, validator, reporter.

Inferred read-only

get_news

Return the curated vulnerability news overlay (official RSS titles, sources, dates, and links; no scraped article bodies).

Inferred read-only

hunt_brief

Returns the playbooks, checklists, tools, and disclosure cards linked to a hunt class.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.vulns-co]
url = "https://vulns.co/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "vulns-co": {
      "type": "http",
      "url": "https://vulns.co/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: vulns-co
Remote MCP URL: https://vulns.co/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "vulns-co": {
      "url": "https://vulns.co/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "vulns-co": {
      "type": "http",
      "url": "https://vulns.co/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "vulns-co",
  "transport": "streamable-http",
  "url": "https://vulns.co/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.