cyanheads avatar

Pentest Mcp Server

cyanheads/pentest-mcp-server

Built for authorized penetration testing workflows, offering six offline tools that span methodology lookup, response analysis, MITRE ATT&CK technique mapping, and payload template generation. The pentest_guide tool returns step-by-step playbooks for fifteen attack vectors (XSS, SQLi, SSRF, JWT attacks, etc.), each with detection indicators and mitigations. You can paste raw HTTP responses into pentest_analyze_response to extract version leaks, stack traces, and technology fingerprints, then feed those fingerprints to pentest_map_techniques to get ranked ATT&CK techniques scored against your target profile. The payload generator returns annotated templates with bypass rationale and encoding chains, not live exploits. Everything runs locally via stdio or against a public hosted endpoint at pentest.caseyjhand.com/mcp. Designed for red teams, CTF players, and blue teamers building detection coverage.

GitHub stars
1
tools
7
transport
STDIO, HTTP
env vars
7
last updated
Oct 30, 2026

Install

From registry metadata
$ npx add-mcp https://pentest.caseyjhand.com/mcp --name pentest

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http pentest https://pentest.caseyjhand.com/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 7 tools

Verified live against the running server on Nov 6, 2026.

pentest_get_guideReturn an authorized-testing methodology for a selected vector and optional target context. The playbook covers reconnaissance, enumeration, exploitation, and post-exploitation phases with objectives, techniques, detection signals, mitigations, common pitfalls, references, and...3 params

Return an authorized-testing methodology for a selected vector and optional target context. The playbook covers reconnaissance, enumeration, exploitation, and post-exploitation phases with objectives, techniques, detection signals, mitigations, common pitfalls, references, and...

Parameters* required
phasestring
Methodology phase selector. "all" returns the complete playbook; a named phase returns only that phase.one of all · recon · enumeration · exploitation · post_exploitationdefault: all
target_contextobject
Optional target profile for authorized engagement. Providing this narrows the playbook to what is most relevant for the specific environment.
vector*string
Attack vector to retrieve methodology for. Each vector has its own methodology branch covering recon through exploitation. Authorized testing only.one of auth_bypass · idor · ssrf · xss · sqli · xxe
pentest_analyze_responseAnalyze an HTTP response from authorized probing for information leakage, fingerprinting signals, and related exposure. Structured findings cover version disclosures, stack traces, debug headers, internal paths, authentication patterns, CORS configuration, detection signals, r...4 params

Analyze an HTTP response from authorized probing for information leakage, fingerprinting signals, and related exposure. Structured findings cover version disclosures, stack traces, debug headers, internal paths, authentication patterns, CORS configuration, detection signals, r...

Parameters* required
contextstring
Freeform context about the authorized test target — e.g., "login endpoint", "GraphQL API", "file upload handler". Narrows the pattern matching to relevant categories. Max 2,000 characters.
response_bodystring
Raw HTML, JSON, XML, or error response body text. Maximum 10,000 characters.
response_headersstring
Raw HTTP response headers, optionally including the status line. Maximum 20,000 characters.
status_codeinteger
HTTP status code (100–599). Helps classify the response type.
pentest_lookup_techniqueLook up a MITRE ATT&CK technique by exact ID or keyword. Results include tactics, platforms, description, detection data, public procedure examples, mitigations, related sub-techniques, and dataset version.2 params

Look up a MITRE ATT&CK technique by exact ID or keyword. Results include tactics, platforms, description, detection data, public procedure examples, mitigations, related sub-techniques, and dataset version.

Parameters* required
include_subtechniquesboolean
Include sub-techniques in the result. Set to false when only the parent technique summary is needed.default: true
query*string
ATT&CK technique ID (e.g., "T1190", "T1059.001") or keyword describing the technique (e.g., "sql injection", "pass the hash", "web shell upload"). ID lookup is exact; keyword lookup returns the bes...
pentest_lookup_groupLook up a MITRE ATT&CK threat group or software entry by ID, name, or keyword. Results include ATT&CK identity, aliases, type, description, and associated techniques with procedure-level context from public ATT&CK reporting.1 params

Look up a MITRE ATT&CK threat group or software entry by ID, name, or keyword. Results include ATT&CK identity, aliases, type, description, and associated techniques with procedure-level context from public ATT&CK reporting.

Parameters* required
query*string
ATT&CK threat group ID (e.g., "G0007"), software ID (e.g., "S0002"), or name/keyword (e.g., "APT28", "Mimikatz", "Lazarus Group"). ID lookup is exact and case-insensitive; name/keyword search retur...
pentest_map_techniquesRank ATT&CK techniques and OWASP test cases against an authorized target profile of technology stack, exposed services, authentication type, and operating system. Results include profile-specific relevance, detection opportunities, mitigations, and associated methodology vectors.5 params

Rank ATT&CK techniques and OWASP test cases against an authorized target profile of technology stack, exposed services, authentication type, and operating system. Results include profile-specific relevance, detection opportunities, mitigations, and associated methodology vectors.

Parameters* required
auth_typestring
Authentication mechanism in use. Surfaces auth-specific attack techniques.one of jwt · session_cookie · api_key · oauth2 · basic_auth · ntlm
limitinteger
Maximum number of techniques to return (1–50, default 15). Higher values give broader coverage; lower values focus on highest-relevance items.default: 15
osstring
Target operating system. Narrows to OS-specific techniques.one of linux · windows · macos · unknown
servicesarray
Exposed services and interfaces (e.g., ["REST API", "GraphQL", "file upload", "admin panel"]). Narrows technique relevance.
stackarray
Technology stack components (e.g., ["Node.js", "Express", "PostgreSQL", "Redis"]). Each element matched against technique platform and procedure examples.
pentest_generate_payloadsGenerate context-specific payload templates for authorized systems. Each template includes its vulnerability category, context rationale, WAF/IDS detection signature, mitigation, optional WAF research note, and optional encoded variant.5 params

Generate context-specific payload templates for authorized systems. Each template includes its vulnerability category, context rationale, WAF/IDS detection signature, mitigation, optional WAF research note, and optional encoded variant.

Parameters* required
category*string
Vulnerability category for payload generation.one of xss · sqli · ssrf · xxe · path_traversal · ssti
countinteger
Number of payload variants to return (1–20, default 5). More variants cover different bypass approaches for the same context.default: 5
encodingarray
Optional encoding chain applied left to right to each returned template.
injection_context*string
Precise injection context. Critical for XSS: an HTML attribute payload differs from a JS string payload. Provide the most specific context for the best results.one of html_attribute · html_body · js_string · js_template · js_script_block · url_parameter
waf_profilestring
WAF or filter in front of the authorized test target. When a specific WAF is named, bypass variants referencing known public research are included.one of cloudflare · aws_waf · modsecurity_crs · imperva · akamai · f5_bigip_asmdefault: none
pentest_encode_payloadTransform a payload string through an ordered encoding chain for authorized filter research. Results include the final value, intermediate values, optional decode path and rationale, and detection guidance. All transforms are local; no live probing occurs.3 params

Transform a payload string through an ordered encoding chain for authorized filter research. Results include the final value, intermediate values, optional decode path and rationale, and detection guidance. All transforms are local; no live probing occurs.

Parameters* required
chain*array
Ordered list of encodings to apply (1–6 steps). Applied left to right. E.g., ["unicode", "url"] applies Unicode escape first, then URL-encodes the result.
explainboolean
Whether to include the decode path and bypass rationale.default: true
payload*string
Input payload string to encode. Max 10,000 characters.

Sponsors

Configuration

PENTEST_ENABLE_PAYLOAD_GENERATIONdefault: true

Enable payload generation and encoding. Set false to retain the five reference tools only.

MCP_LOG_LEVELdefault: info

Sets the minimum log level for output (e.g., 'debug', 'info', 'warn').

MCP_TRANSPORT_TYPEdefault: http

Selects the HTTP transport.

MCP_HTTP_HOSTdefault: 127.0.0.1

The hostname for the HTTP server.

MCP_HTTP_PORTdefault: 3010

The port to run the HTTP server on.

MCP_HTTP_ENDPOINT_PATHdefault: /mcp

The endpoint path for the MCP server.

MCP_AUTH_MODEdefault: none

Authentication mode to use: 'none', 'jwt', or 'oauth'.

Readme

@cyanheads/pentest-mcp-server

Offline methodology engine and payload workshop for authorized penetration testing, CTF, security research, and education via MCP. STDIO or Streamable HTTP.

7 Tools

Details

Repository
github.com/cyanheads/pentest-mcp-server
Category
Security & Pentesting
Package
@cyanheads/pentest-mcp-server
Transport
STDIO, HTTP
Registry
MCP registry, active
Resources
1
Tools verified
Nov 6, 2026

More from cyanheads

Related Security & Pentesting MCP servers

View all
1akhilucky avatarAI Firewall MCPakhilucky/ai-firewallMulti-agent LLM security layer detecting prompt injection and jailbreaks.0stars
2sinewaveai avatarAgent Security Scanner Mcpsinewaveai/agent-security-scanner-mcpSecurity layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.110stars
3ako2345 avatarAndroid Security Analyzerako2345/android-security-analyzerMCP server for static security analysis of Android source code2stars
4rom-baro avatarArcwall Securityrom-baro/arcwall-mcpSecurity scanning for AI coding tools. Detects secrets, threat models, and runs pre-commit checks.1stars
5csoai-org avatarOwasp Agentic Mcpcsoai-org/owasp-agentic-mcpOwasp Agentic MCP Server by MEOK AI Labs0stars
6csoai-org avatarSecurity Scanner Ai Mcpcsoai-org/security-scanner-ai-mcpSecurity Scanner Ai MCP Server by MEOK AI Labs0stars