Connect Website Search and your agent gets 53 tools, among them aidefense_cross_map, aidefense_evaluate_program, aidefense_get_framework_alignment. It answers at https://website-mcp.zeltser.com/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
Improve security writing, score it against rubrics, plan IR, CTI, vuln, and product strategy.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
aidefense_cross_map | Get the AI Defense Matrix cross-mapping playbook for mapping product capabilities to matrix cells: coverage taxonomy (primary, secondary, partial, aspirational), differentiation guidance, disambiguation block, worked examples, and out-of-sc Inputs: framework, whitespace, include_process_shaped, include_framework_alignment |
aidefense_evaluate_program | Get the AI Defense Matrix evaluation playbook for assessing an AI security program: per-cell prompts, gap-inventory template, and a workflow that walks each asset class first and rolls findings up to the Govern column. Supports mode='gate' Inputs: asset, assets, function, mode, consumer_pattern, framework |
aidefense_get_framework_alignment | Get AI Defense Matrix cross-mappings to nine external frameworks: NIST IR 8596, CSA AI Controls Matrix, ISO 42001, Google SAIF, SANS Critical AI Security Guidelines, MITRE ATLAS, OWASP AI Exchange, OWASP LLM Top 10, OWASP Agentic Security T Inputs: framework, buyer |
aidefense_get_matrix | Get the structured AI Defense Matrix: 8 AI-specific asset rows x 6 NIST CSF 2.0 function columns. Each cell describes a control category for defending that asset class. Supports optional filtering by asset or function. This server never req Inputs: format, asset, function |
aidefense_load_context | Load Lenny Zeltser's AI Defense Matrix context: the 8-asset x 6-NIST-CSF-2.0-function matrix, nine cross-walked frameworks (NIST IR 8596, CSA AICM, ISO 42001, Google SAIF, SANS Critical AI Security Guidelines, MITRE ATLAS, OWASP AI Exchange Inputs: purpose, detail_level |
aidefense_locate_concept | Reverse-lookup a single concept ID (MITRE ATLAS technique like 'AML.T0051', OWASP LLM Top 10 risk like 'LLM01', OWASP Agentic Top 10 issue like 'ASI03', or ISO 42001 Annex A clause like 'A.6') across the AI Defense Matrix. Returns which fra Inputs: concept |
assessment_get_brief_template | Get Lenny Zeltser's Security Assessment one-page executive brief template. Standalone variant of `assessment_get_template` for callers that only want the brief without the long-form report. This server never requests your assessment notes o |
assessment_get_cross_server_routes | Get Lenny Zeltser's Security Assessment cross-server handoff routes — when this MCP server can't fulfill a request, which other MCP servers (or fallback workflows) to consult. Surfaces a compact subset of `assessment_load_context`. This ser |
assessment_get_frameworks | Get Lenny Zeltser's Security Assessment frameworks (primary frameworks the brief structurally derives from) plus optional sibling frames (adjacent frameworks that aren't the structural backbone). Pass `include_siblings: false` to skip sibli Inputs: include_siblings |
assessment_get_guidelines | Get Lenny Zeltser's expert security assessment report writing guidelines. Topics: severity (the risk-adjusted severity model — the spine), findings, remediation, methodology, scope, strengths, brief (one-page brief section guidance), execut Inputs: topic |
assessment_get_template | Get Lenny Zeltser's security assessment template. The report is a reader-first findings report: Executive Summary, Assessment Scope, Findings Summary, Detailed Findings, Remediation Priorities, optional Attack Path Narrative and Detection a Inputs: kind |
assessment_load_context | Load Lenny Zeltser's security assessment report writing context for local analysis. Returns a JSON payload with the risk-adjusted severity model (the spine), reader-first section guidance, completeness criteria, frameworks (NIST SP 800-115/ Inputs: detail_level, topics, profile, template, include_examples |
assessment_review_report | Get Lenny Zeltser's expert criteria for reviewing an existing security assessment report or brief. Surfaces the 17 info-assessment review items across five groups (Key Takeaways, Assessment Scope, Prioritized Findings, Remediation Suggestio Inputs: sections, focus |
cti_get_brief_template | Get Lenny Zeltser's CTI one-page executive brief template. Standalone variant of `cti_get_template` for callers that only want the brief without the long-form report. This server never requests your campaign or threat-intel notes and instru |
cti_get_cross_server_routes | Get Lenny Zeltser's CTI cross-server handoff routes — when this MCP server can't fulfill a request, which other MCP servers (or fallback workflows) to consult. Surfaces a compact subset of `cti_load_context`. This server never requests your |
cti_get_frameworks | Get Lenny Zeltser's CTI frameworks (primary frameworks the brief structurally derives from) plus optional sibling frames (adjacent frameworks that aren't the structural backbone). Pass `include_siblings: false` to skip sibling blocks. This Inputs: include_siblings |
cti_get_guidelines | Get Lenny Zeltser's expert CTI writing guidelines. Topics include tone, words, structure, executive_summary, voice, articles, summary, brief (one-page brief section guidance), handoffs (cross-server routing), methodology (the three subsecti Inputs: topic, field_id |
cti_get_template | Get Lenny Zeltser's cyber threat intel template. The long report covers Executive Summary, Actor Snapshot, Methodology, Activity Overview, Representative Adversary Techniques, Indicators of Compromise, Defensive Implications, Attribution An Inputs: template |
cti_load_context | Load Lenny Zeltser's CTI writing context for local analysis. Returns a JSON payload with section guidance, completeness criteria, framework grounding (12 frameworks), the six attribution signals, ICD-203 confidence levels and ladder, and th Inputs: detail_level, topics, profile, template, include_examples |
cti_review_report | Get Lenny Zeltser's expert criteria for reviewing an existing CTI report or brief. Surfaces per-theme review criteria (framework, confidence, attribution, defense, distribution, etc.), cross-cutting criteria, the six anti-patterns to watch Inputs: sections, focus |
get_article | Get the full content of a specific article from Lenny Zeltser's Website by URL path. Security articles on malware analysis, incident response, and security leadership. Returns title, date, topics, summary, and full body text. Inputs: url |
get_capabilities | List all capabilities and tools available from the Lenny Zeltser's Website MCP server, including search tools and any specialized features like IR report writing assistance. |
get_index_info | Get statistics about the Lenny Zeltser's Website search index including total pages indexed, last update time, and available tools. |
get_security_writing_guidelines | Get Lenny Zeltser's expert writing guidelines for security reports and assessments. Provides guidance on tone, structure, clarity, executive summaries, and avoiding common writing mistakes. Includes rating-sheet items (the four lens sheets: Inputs: focus, include_examples |
ir_get_brief_template | Get Lenny Zeltser's IR one-page executive brief template. Standalone variant of `ir_get_template` for callers that only want the brief without the long-form report. This server never requests your incident notes and instructs your AI to kee |
ir_get_cross_server_routes | Get Lenny Zeltser's IR cross-server handoff routes — when this MCP server can't fulfill a request, which other MCP servers (or fallback workflows) to consult. Surfaces a compact subset of `ir_load_context`. This server never requests your i |
ir_get_frameworks | Get Lenny Zeltser's IR frameworks (primary frameworks the brief structurally derives from) plus optional sibling frames (adjacent frameworks that aren't the structural backbone). Pass `include_siblings: false` to skip sibling blocks. This s Inputs: include_siblings |
ir_get_guidelines | Get Lenny Zeltser's expert writing guidelines for incident response reports. Topics: tone, words, structure, executive_summary, voice, articles, summary, brief (one-page brief section guidance, IR 1.5.0+), frameworks (regulatory + maturity Inputs: topic |
ir_get_template | Get Lenny Zeltser's structured incident response template. Covers all critical IR sections with field-by-field guidance. Pass kind: "report" (default — full incident-response report) or "brief" (one-page executive brief, IR 1.5.0+). This se Inputs: kind |
ir_load_context | Load Lenny Zeltser's IR report writing context for local analysis. Returns expert guidelines for field completeness, incident identification, notification triggers, and writing quality. Includes rating-sheet items (lens taxonomy plus the IR Inputs: detail_level, topics, incident_type, include_examples |
ir_review_report | Get Lenny Zeltser's expert criteria for reviewing an existing IR report. Returns focused guidance for constructive critique — what to check in each section, writing quality issues to identify, and how to frame feedback collaboratively. Incl Inputs: sections, focus |
malware_get_cross_server_routes | Get Lenny Zeltser's Malware cross-server handoff routes — when this MCP server can't fulfill a request, which other MCP servers (or fallback workflows) to consult. Surfaces a compact subset of `malware_load_context`. This server never reque |
malware_get_frameworks | Get Lenny Zeltser's Malware frameworks (primary frameworks the brief structurally derives from) plus optional sibling frames (adjacent frameworks that aren't the structural backbone). Pass `include_siblings: false` to skip sibling blocks. T Inputs: include_siblings |
malware_get_guidelines | Get Lenny Zeltser's expert malware analysis report writing guidelines. Topics include capabilities, confidence, pyramid_of_pain, anti_patterns, methodology, fields, handoffs, frameworks, plus tone, words, structure, and executive_summary to Inputs: topic, field_id |
malware_get_template | Get Lenny Zeltser's malware analysis report template. The report covers Executive Summary, Sample Snapshot, Malware Family Identification, Component Inventory, Runtime Requirements, Sources, Capabilities, Indicators of Compromise, Analysis |
malware_load_context | Load Lenny Zeltser's malware analysis report writing context for local analysis. Returns a JSON payload with section guidance, the MBC capability model, ICD-203 confidence scoped to the family call, Pyramid-of-Pain IOC tiering, and a briefP Inputs: detail_level, topics, profile, include_examples |
malware_review_report | Get Lenny Zeltser's expert criteria for reviewing an existing malware analysis report. Surfaces per-theme review criteria for identification, capabilities, indicators, evidence, ecosystem, detection, reproducibility, and distribution; cross Inputs: sections, focus |
product_compare_context | Load Lenny Zeltser's comparative analysis framework for evaluating multiple security companies side by side. Returns structured scoring rubric, evaluation dimensions, evidence tiering guidance, and comparison-type-specific instructions. Req Inputs: comparison_type, company_count, include_scoring_rubric |
product_get_guidelines | Get Lenny Zeltser's expert strategic guidelines for a specific product strategy topic. Topics: market (segmentation), capabilities (AI, agents, MVP, positioning), sales (GTM, channels, distribution, POCs), pricing (models, retention), deliv Inputs: topic |
product_get_template | Get Lenny Zeltser's fill-in-the-blank template for planning a security product strategy. Includes strategic questions organized by section with evidence columns. This server never requests your product plans and instructs your AI to keep th |
product_load_context, product_review_plan, rating_get_sheet, rating_load_context, rating_score_writing, search_zeltser, vuln_get_brief_template, vuln_get_cross_server_routes, vuln_get_frameworks, vuln_get_guidelines, vuln_get_template, vuln_load_context, vuln_review_brief
Every block below points at https://website-mcp.zeltser.com/mcp. Pick your client and copy.
claude mcp add --transport http website-search https://website-mcp.zeltser.com/mcp
{
"mcpServers": {
"website-search": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://website-mcp.zeltser.com/mcp"]
}
}
}{
"mcpServers": {
"website-search": {
"url": "https://website-mcp.zeltser.com/mcp"
}
}
}{
"servers": {
"website-search": {
"type": "http",
"url": "https://website-mcp.zeltser.com/mcp"
}
}
}{
"context_servers": {
"website-search": {
"url": "https://website-mcp.zeltser.com/mcp"
}
}
}{
"mcpServers": {
"website-search": {
"serverUrl": "https://website-mcp.zeltser.com/mcp"
}
}
}{
"mcpServers": {
"website-search": {
"url": "https://website-mcp.zeltser.com/mcp"
}
}
}name: website-search
version: 0.0.1
schema: v1
mcpServers:
- name: website-search
type: streamable-http
url: https://website-mcp.zeltser.com/mcp{
"mcpServers": {
"website-search": {
"httpUrl": "https://website-mcp.zeltser.com/mcp"
}
}
}{
"mcpServers": {
"website-search": {
"type": "http",
"url": "https://website-mcp.zeltser.com/mcp"
}
}
}{
"mcpServers": {
"website-search": {
"url": "https://website-mcp.zeltser.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fwebsite-mcp.zeltser.com%2Fmcp&type=streamable_http&id=website-search&name=website-search
It answered our last check on 18 October 2026 in 563 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by zeltser.com and served from website-mcp.zeltser.com, the vendor's own domain: https://website-mcp.zeltser.com/mcp.
53, as returned by the server's own tools/list on 31 August 2026: aidefense_cross_map, aidefense_evaluate_program, aidefense_get_framework_alignment, aidefense_get_matrix, aidefense_load_context, aidefense_locate_concept, assessment_get_brief_template, assessment_get_cross_server_routes, and 45 more.
It answered our last check on 18 October 2026 in 563 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://website-mcp.zeltser.com/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.zeltser. Endpoint host: website-mcp.zeltser.com. ARD identifier: urn:air:com.zeltser:mcp:website-search.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.