eip-mcp 0.2.0

MCP server for the Exploit Intelligence Platform — vulnerability and exploit intelligence for AI assistants

Exploit Intel Platform MCP Server

Package/command: eip-mcp

An MCP (Model Context Protocol) server that gives AI assistants access to the Exploit Intelligence Platform — 370K+ vulnerabilities and 105K+ exploits from NVD, CISA KEV, EPSS, ExploitDB, Metasploit, GitHub, and more.

Part of the same project family:

• eip-search — terminal client
• eip-mcp — MCP server for AI assistants

Highlights

• Give AI assistants real-time vulnerability and exploit intelligence
• Query CVEs with rich filters and ranked exploit context
• Include AI exploit analysis, MITRE ATT&CK mapping, and trojan indicators
• Generate pentest findings directly from CVE data

What This Enables

With this MCP server, your AI assistant can:

• Search vulnerabilities with 15+ filters (severity, vendor, product, EPSS, KEV, Nuclei)
• Search exploits by source, language, author, GitHub stars, or LLM classification
• Get full CVE intelligence briefs with ranked exploits and trojan warnings
• Find all exploits for a specific CVE, vendor, or product
• Look up exploit authors and their work
• Browse CWE categories and vendor threat landscapes
• Audit a tech stack for exploitable vulnerabilities
• Generate pentest report findings from real CVE data
• Retrieve exploit source code for analysis
• See MITRE ATT&CK techniques and deception indicators for trojans

Tools (14)

Tool	Description
search_vulnerabilities	Search CVEs with filters: severity, vendor, product, ecosystem, CWE, CVSS/EPSS thresholds, KEV, Nuclei
get_vulnerability	Full CVE intelligence brief with ranked exploits (with AI analysis, MITRE techniques), products, Nuclei templates, references
search_exploits	Search exploits by source, language, LLM classification, author, stars, CVE, vendor, product. Also filter by AI analysis: attack_type (RCE, SQLi, XSS, DoS, LPE, auth_bypass, info_leak), complexity (trivial, simple, moderate, complex), reliability (reliable, unreliable, untested), and requires_auth
get_exploit_code	Retrieve exploit source code by ID (auto-selects main file)
get_nuclei_templates	Nuclei scanner templates with Shodan, FOFA, and Google dork queries
list_authors	Top exploit researchers ranked by exploit count
get_author	Author profile with all their exploits and CVE context
list_cwes	CWE categories ranked by vulnerability count
get_cwe	CWE detail with description, exploit likelihood, parent hierarchy
list_vendors	Software vendors ranked by vulnerability count
audit_stack	Audit a comma-separated tech stack for exploitable CVEs, sorted by risk
generate_finding	Generate a Markdown pentest report finding from a CVE
get_platform_stats	Platform-wide counts and data freshness
check_health	API health and ingestion source timestamps

Installation

Requirements

• Python 3.10 or newer (check with python3 --version or python --version)
• pip (comes with Python on most systems)
• An MCP-compatible AI client (Cursor IDE, Claude Desktop, etc.)

macOS

# Install Python 3 via Homebrew if needed
brew install python3

# Recommended: pipx (isolated install, eip-mcp command available globally)
brew install pipx
pipx install eip-mcp

# Alternative: virtual environment
python3 -m venv ~/.venvs/eip-mcp
source ~/.venvs/eip-mcp/bin/activate
pip install eip-mcp

Kali Linux / Debian / Ubuntu

# Python 3 is pre-installed on Kali. Install pip if needed:
sudo apt update && sudo apt install -y python3-pip python3-venv

# Recommended: pipx (isolated install, eip-mcp command available globally)
sudo apt install -y pipx
pipx install eip-mcp

# Alternative: virtual environment
python3 -m venv ~/.venvs/eip-mcp
source ~/.venvs/eip-mcp/bin/activate
pip install eip-mcp

Kali users: If you see error: externally-managed-environment, use pipx or a virtual environment. Kali 2024+ enforces PEP 668 which blocks global pip installs.

Windows

# Install Python 3 from https://python.org (check "Add to PATH" during install)

# Option 1: pipx
pip install pipx
pipx install eip-mcp

# Option 2: virtual environment
python -m venv %USERPROFILE%\.venvs\eip-mcp
%USERPROFILE%\.venvs\eip-mcp\Scripts\activate
pip install eip-mcp

Arch Linux / Manjaro

sudo pacman -S python python-pip python-pipx
pipx install eip-mcp

From Source (all platforms)

git clone [e-mail]:exploit-intel/eip-mcp.git
cd eip-mcp
python3 -m venv .venv
source .venv/bin/activate      # Linux/macOS
# .venv\Scripts\activate       # Windows
pip install -e .

Connecting to Your AI Client

Cursor IDE

Add to .cursor/mcp.json in your workspace (or globally at ~/.cursor/mcp.json):

If installed with pipx (recommended):

{
  "mcpServers": {
    "eip": {
      "command": "eip-mcp",
      "args": [],
      "env": {}
    }
  }
}

If installed in a virtual environment:

{
  "mcpServers": {
    "eip": {
      "command": "/absolute/path/to/.venvs/eip-mcp/bin/eip-mcp",
      "args": [],
      "env": {}
    }
  }
}

Note: When using a virtual environment, use the absolute path to the eip-mcp binary inside it. On macOS/Linux: ~/.venvs/eip-mcp/bin/eip-mcp. On Windows: %USERPROFILE%\.venvs\eip-mcp\Scripts\eip-mcp.exe.

Claude Desktop

macOS — add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "eip": {
      "command": "eip-mcp",
      "args": [],
      "env": {}
    }
  }
}

Windows — add to %APPDATA%\Claude\claude_desktop_config.json:

{
  "mcpServers": {
    "eip": {
      "command": "eip-mcp",
      "args": [],
      "env": {}
    }
  }
}

If your AI client can't find eip-mcp, use the full path to the binary (see virtual environment note above).

Verify

After restarting your AI client, you should see 14 tools available. Try asking:

"Show me all trojan exploits"

Troubleshooting

Problem	Solution
MCP server not showing up	If using a venv, use the full absolute path to the eip-mcp binary
command not found: eip-mcp	Make sure your venv is activated, or use pipx which manages PATH automatically
externally-managed-environment	Use pipx or a virtual environment (see install instructions above)
Connection timeout errors	Check that you can reach https://exploit-intel.com from your machine
0 tools showing	Restart Cursor/Claude Desktop after editing the MCP config

Demo

What Questions Can You Ask?

Below are real questions tested against the live platform, with actual output.

---

"Show me all the backdoored/trojan exploits"

Uses search_exploits with llm_classification=trojan:

Found 21 exploits (page 1/7):

      ★0  github       hn1e13/test-mcp
         CVE-2025-54135  HIGH  CVSS:8.5  [markdown] trojan
         AI: RCE | trivial | theoretical
         !! Embedded AI automation commands disguised as configuration
         !! Decoy Python script unrelated to the vulnerability

      ★0  github       Rosemary1337/CVE-2025-6934
         CVE-2025-6934  CRITICAL  CVSS:9.8  [python] trojan
         AI: other | moderate | theoretical
         !! Obfuscated code execution
         !! External payload decryption

      ★1  github       Markusino488/cve-2025-8088
         CVE-2025-8088  HIGH  CVSS:8.8  [python] trojan
         AI: other | moderate | reliable
         !! Misleading README describing a security tool while the code drops malicious payloads
         !! Suspicious download links in README pointing to the same ZIP file

21 exploits flagged as trojans by AI analysis. Each shows deception indicators explaining exactly how the trojan deceives users.

---

"Find all reliable RCE exploits"

Uses search_exploits with attack_type=RCE, reliability=reliable, sort=stars_desc:

Found 17,720 exploits (page 1/3544):

   ★4275  nomisec      zhzyker/exphub
         CVE-2020-14882  CRITICAL  CVSS:9.8  [] working_poc
         AI: RCE | moderate | reliable

   ★3436  nomisec      fullhunt/log4j-scan
         CVE-2021-44228  CRITICAL  CVSS:10.0  [] scanner
         AI: RCE | moderate | reliable

   ★1848  nomisec      kozmer/log4j-shell-poc
         CVE-2021-44228  CRITICAL  CVSS:10.0  [] working_poc
         AI: RCE | moderate | reliable

   ★1835  github       neex/phuip-fpizdam
         CVE-2019-11043  HIGH  CVSS:8.7  [] working_poc
         AI: RCE | moderate | reliable

17,720 reliable RCE exploits. Filter further with complexity=trivial for easy wins or requires_auth=false for unauthenticated attacks.

---

"Show me trivial SQL injection exploits that don't require auth"

Uses search_exploits with attack_type=SQLi, complexity=trivial, requires_auth=false:

Found 6,979 exploits (page 1/1396):

      ★0  github       pwnpwnpur1n/CVE-2024-22983
         CVE-2024-22983  HIGH  CVSS:8.1  [php] writeup
         AI: SQLi | trivial | reliable

      ★0  github       security-n/CVE-2021-39379
         CVE-2021-39379  CRITICAL  CVSS:9.8  [] writeup
         AI: SQLi | trivial | reliable
      ...

---

"Give me all exploits for CVE-2024-3400"

Uses search_exploits with cve=CVE-2024-3400, sort=stars_desc:

Found 43 exploits (page 1/9):

    ★161  github       h4x0r-dz/CVE-2024-3400
         CVE-2024-3400  CRITICAL  CVSS:10.0  [http] working_poc

     ★90  github       W01fh4cker/CVE-2024-3400-RCE-Scan
         CVE-2024-3400  CRITICAL  CVSS:10.0  [python] working_poc

     ★72  github       0x0d3ad/CVE-2024-3400
         CVE-2024-3400  CRITICAL  CVSS:10.0  [python] working_poc

     ★30  github       ihebski/CVE-2024-3400
         CVE-2024-3400  CRITICAL  CVSS:10.0  [http/network] working_poc

     ★14  github       Chocapikk/CVE-2024-3400
         CVE-2024-3400  CRITICAL  CVSS:10.0  [python] working_poc

43 exploits, ranked by GitHub stars, with LLM quality classification.

---

"How many Mitel exploits are there?"

Uses search_exploits with vendor=mitel, has_code=true:

Found 783 exploits (page 1/157):

          exploitdb    EDB-46666
         CVE-2019-9591  MEDIUM  CVSS:6.1  []

          exploitdb    EDB-32745
         CVE-2014-0160  HIGH  CVSS:7.5  [python]

      ★0  github       lu4m575/CVE-2024-35286_scan.nse
         CVE-2024-35286  CRITICAL  CVSS:9.8  []

      ★17  github       Chocapikk/CVE-2024-41713
         CVE-2024-41713  CRITICAL  CVSS:9.1  [python] working_poc
      ...

783 Mitel exploits with downloadable code, across all affected CVEs.

---

"Who are the top exploit authors?"

Uses list_authors:

Exploit Authors (23,144 total):

  metasploit                      2098 exploits
  Ihsan Sencan                    1658 exploits
  Google Security Research        1355 exploits
  LiquidWorm                      1336 exploits
  Luigi Auriemma                   629 exploits
  High-Tech Bridge SA              613 exploits
  Vulnerability-Lab                596 exploits
  Gjoko 'LiquidWorm' Krstic        567 exploits
  rgod                             531 exploits
  indoushka                        517 exploits

---

"Show me all exploits by Chocapikk"

Uses get_author with author_name=Chocapikk:

Author: Chocapikk
Exploits: 60  |  Active since: 2017-04-25

Exploits:
    ★244  CVE-2026-21858  Chocapikk/CVE-2026-21858  working_poc
    ★179  CVE-2024-25600  Chocapikk/CVE-2024-25600  working_poc
    ★134  CVE-2024-45519  Chocapikk/CVE-2024-45519  working_poc
     ★99  CVE-2024-3273  Chocapikk/CVE-2024-3273  working_poc
     ★49  CVE-2024-56145  Chocapikk/CVE-2024-56145  working_poc
     ★47  CVE-2024-9474  Chocapikk/CVE-2024-9474  working_poc
     ★41  CVE-2025-55182  Chocapikk/CVE-2025-55182  working_poc
     ★41  CVE-2024-8504  Chocapikk/CVE-2024-8504  working_poc
     ★36  CVE-2024-27198  Chocapikk/CVE-2024-27198  working_poc
      ...

60 exploits by Chocapikk, ranked by GitHub stars, all classified as working PoCs.

---

"What are the most common vulnerability types?"

Uses list_cwes:

CWE Categories (200 with vulnerabilities):

    CWE-79   41774 vulns  XSS
    CWE-89   17788 vulns  SQL Injection
   CWE-787   13374 vulns  Out-of-Bounds Write
   CWE-119   13344 vulns  Memory Corruption
    CWE-20   11770 vulns  Improper Input Validation
   CWE-200    9555 vulns  Information Disclosure
   CWE-352    8710 vulns  CSRF
   CWE-125    8163 vulns  Out-of-Bounds Read
    CWE-22    8141 vulns  Path Traversal
   CWE-862    6683 vulns  Missing Authorization
      ...

---

"Tell me about SQL Injection (CWE-89)"

Uses get_cwe with cwe_id=CWE-89:

CWE-89: Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection')
Short label: SQL Injection
Exploit likelihood: High
Vulnerabilities: 17,788
Parent: CWE-943 (Improper Neutralization of Special Elements in Data Query Logic)

Description:
The product constructs all or part of an SQL command using externally-influenced
input from an upstream component, but it does not neutralize or incorrectly
neutralizes special elements that could modify the intended SQL command when it
is sent to a downstream component...

---

"Which vendors have the most vulnerabilities?"

Uses list_vendors:

Top Vendors (200 total):

  microsoft                       13697 vulns
  google                          12451 vulns
  linux                           12096 vulns
  oracle                          10107 vulns
  debian                          10072 vulns
  apple                            8426 vulns
  ibm                              7981 vulns
  adobe                            6960 vulns
  cisco                            6526 vulns
  redhat                           5505 vulns
      ...

---

"What critical Fortinet vulns are being actively exploited?"

Uses search_vulnerabilities with vendor=fortinet, severity=critical, is_kev=true, sort=epss_desc:

Found 24 vulnerabilities (page 1/5):

  CVE-2018-13379  CRITICAL  CVSS:9.1  EPSS:94.5%  Exploits:14 [KEV]
    Fortinet FortiProxy < 1.2.9 - Path Traversal

  CVE-2022-40684  CRITICAL  CVSS:9.8  EPSS:94.4%  Exploits:30 [KEV]
    Fortinet FortiProxy < 7.0.7 - Authentication Bypass

  CVE-2023-48788  CRITICAL  CVSS:9.8  EPSS:94.2%  Exploits:1 [KEV] [NUCLEI]
    Fortinet FortiClient Endpoint Management Server - SQL Injection

  CVE-2024-55591  CRITICAL  CVSS:9.8  EPSS:94.2%  Exploits:8 [KEV]
    Fortinet FortiProxy < 7.0.20 - Authentication Bypass

  CVE-2022-42475  CRITICAL  CVSS:9.8  EPSS:94.0%  Exploits:7 [KEV]
    Fortinet FortiOS < 5.0.14 - Buffer Overflow

---

"Tell me about CVE-2019-0708 (BlueKeep)"

Uses get_vulnerability with cve_id=CVE-2019-0708:

============================================================
CVE-2019-0708  [CRITICAL]  [KEV]
============================================================
Title: BlueKeep RDP Remote Windows Kernel Use After Free

CVSS: 9.8  EPSS: 94.5% (100.0th percentile)
Attack Vector: NETWORK | CWE: CWE-416 | Published: 2019-05-16 | KEV Added: 2021-11-03

EXPLOITS (127 total):
  METASPLOIT MODULES:
    - cve_2019_0708_bluekeep_rce.rb  [ruby]  Rank: manual
      AI: RCE | complexity:complex | reliability:racy | target:Microsoft Windows 7 SP1
      MITRE: T1059 - Command and Scripting Interpreter, T1068 - Exploitation for Privilege Escalation
  VERIFIED (ExploitDB):
    - EDB-47416  [ruby]  verified
      AI: RCE | complexity:complex | reliability:racy | target:Microsoft Windows RDP (7 SP1 / 2008 R2)
      MITRE: T1068, T1210 - Exploitation of Remote Services
  PROOF OF CONCEPT:
    - ★1187  nomisec  Ekultek/BlueKeep  working_poc
      AI: RCE | complexity:moderate | reliability:reliable | target:Windows RDP
      MITRE: T1189 - Drive-by Compromise, T1068
    - ★914   nomisec  robertdavidgraham/rdpscan  scanner
      AI: info_leak | complexity:moderate | reliability:reliable
      MITRE: T1046 - Network Service Scanning
      ...and 113 more PoCs
  *** SUSPICIOUS / TROJAN ***:
    - WARNING: ttsite/CVE-2019-0708-  [TROJAN] — flagged by AI analysis
      Summary: The repository is a scam and does not contain any exploit code.
      Deception indicators:
        - False claims about exploit availability
        - Deceptive contact information
        - No actual exploit code or technical details

Every exploit now shows AI analysis: attack type, complexity, reliability, target software, and MITRE ATT&CK techniques. Trojans show deception indicators explaining exactly how they deceive users.

---

"Audit our stack: nginx, postgresql, redis"

Uses audit_stack with technologies=nginx, postgresql, redis:

STACK AUDIT RESULTS
========================================

--- NGINX (66 exploitable CVEs) ---
  CVE-2023-44487  HIGH  CVSS:7.5  EPSS:94.4%  Exploits:22 [KEV]
    HTTP/2 Rapid Reset DoS
  CVE-2013-2028  CVSS:--  EPSS:92.8%  Exploits:25
    Nginx < 1.4.0 - Out-of-Bounds Write
  CVE-2017-7529  HIGH  CVSS:7.5  EPSS:91.9%  Exploits:54
    Nginx <1.14 - Info Disclosure
      ...and 56 more

--- POSTGRESQL (56 exploitable CVEs) ---
  CVE-2019-9193  HIGH  CVSS:7.2  EPSS:93.4%  Exploits:41
    PostgreSQL < 11.2 - OS Command Injection
  CVE-2018-1058  HIGH  CVSS:8.8  EPSS:82.7%  Exploits:13
    PostgreSQL < 9.3.22 - Improper Input Validation
      ...and 46 more

--- REDIS (39 exploitable CVEs) ---
  CVE-2022-0543  CRITICAL  CVSS:10.0  EPSS:94.4%  Exploits:32 [KEV]
    Redis Lua Sandbox Escape
  CVE-2018-11218  CRITICAL  CVSS:9.8  EPSS:80.3%  Exploits:3
    Redis < 3.2.12 - Out-of-Bounds Write
      ...and 29 more

Total: 30 findings shown across 3 technologies

---

"Get me the Nuclei dorks for TeamCity"

Uses get_nuclei_templates with cve_id=CVE-2024-27198:

NUCLEI TEMPLATES (1):
  Template: CVE-2024-27198  [critical] [verified]
  Name: TeamCity < 2023.11.4 - Authentication Bypass
  Author: DhiyaneshDk
  Tags: cve, cve2024, teamcity, jetbrains, auth-bypass, kev

  Recon Queries:
    Shodan:  http.component:"TeamCity" || http.title:teamcity
    FOFA:    title=teamcity
    Google:  intitle:teamcity

  Run: nuclei -t CVE-2024-27198 -u https://target.com

---

"Write a pentest finding for CVE-2024-3400"

Uses generate_finding with cve_id=CVE-2024-3400, target=fw.corp.example.com, notes=Confirmed RCE via GlobalProtect:

# CVE-2024-3400: Palo Alto Networks PAN-OS Unauthenticated Remote Code Execution

**Severity:** CRITICAL
**CVSS v3 Score:** 10.0  (CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H)
**EPSS Score:** 94.3% probability of exploitation
**CISA KEV:** Yes — confirmed actively exploited in the wild
**CWE:** CWE-77, CWE-20

**Affected Target:** fw.corp.example.com

## Description
A command injection vulnerability in the GlobalProtect feature of PAN-OS...

## Exploit Availability (43 public exploits)
- **Metasploit:** panos_telemetry_cmd_exec.rb  (rank: excellent)

## References
- https://security.paloaltonetworks.com/CVE-2024-3400

## Tester Notes
Confirmed RCE via GlobalProtect

---

"List all Metasploit modules"

Uses search_exploits with source=metasploit:

Found 3,350 exploits (page 1/670):

          metasploit   modules/auxiliary/gather/ni8mare_cve_2026_21858.rb
         CVE-2026-21858  CRITICAL  CVSS:10.0  [ruby] working_poc

          metasploit   modules/exploits/multi/handler.rb
         no-CVE  ?  [ruby]

          metasploit   modules/exploits/example_linux_priv_esc.rb
         no-CVE  ?  [ruby]
      ...

3,350 Metasploit modules indexed.

---

Security Model

This MCP server runs locally and proxies requests to the public EIP API over HTTPS.

Input Validation

Every parameter passes through strict validation:

• CVE IDs: Regex ^CVE-\d{4}-\d{4,7}$
• Exploit IDs: Positive integers, capped at 2^31
• Strings: Max 200 chars, null bytes rejected, control characters stripped
• Numerics: CVSS 0-10, EPSS 0-1, per_page 1-25
• Enums: Severity, sort, ecosystem validated against allowlists
• File paths: .., absolute paths, null bytes all blocked
• Technology names: Alphanumeric + dots/hyphens/spaces, max 5 items

Response Safety

• Exploit code capped at 50KB
• All responses are plain text (no executable content)
• Error messages are generic (no internal API leakage)
• Trojan exploits are explicitly flagged

Network Safety

• API base URL hardcoded to https://exploit-intel.com
• TLS verification enabled
• 30-second timeout on all calls
• Optional API key via EIP_API_KEY environment variable

API Key (Optional)

For higher rate limits, set an API key in the MCP config:

{
  "mcpServers": {
    "eip": {
      "command": "eip-mcp",
      "args": [],
      "env": {
        "EIP_API_KEY": "your-key-here"
      }
    }
  }
}

No API key is required. The public API allows 60 requests/minute.

Building Packages

Build Dependencies

Target	Requirements
make build	Python 3, build module (pip install build)
make check / make pypi	twine (pip install twine)
make deb	Docker
make tag-release	Python 3 (version bump only — Codeberg Actions handles the rest)
make release	All of the above + tea CLI (codeberg.org/gitea/tea)

Install everything at once:

pip install build twine
# Docker: https://docs.docker.com/get-docker/
# tea CLI: https://codeberg.org/gitea/tea

PyPI (wheel + sdist)

make build          # build dist/*.whl and dist/*.tar.gz
make check          # validate with twine
make pypi           # upload to PyPI

.deb Packages

Build for a single distro or all four supported targets:

make deb DISTRO=ubuntu-jammy      # Ubuntu 22.04
make deb DISTRO=ubuntu-noble      # Ubuntu 24.04
make deb DISTRO=debian-bookworm   # Debian 12
make deb DISTRO=kali              # Kali Rolling
make deb                          # all four

Releasing

One-time setup: add PYPI_API_TOKEN and RELEASE_TOKEN as repository secrets in Codeberg (Settings → Actions → Secrets).

Automated release (recommended) — bumps version, commits, tags, and pushes. Codeberg Actions builds PyPI packages + all 4 .debs, uploads to PyPI, and creates a release with artifacts attached:

make tag-release VERSION=0.2.0

Local release (alternative) — does everything locally without CI:

make release VERSION=0.2.0

Dependencies

• mcp>=1.2.0 — Official MCP Python SDK
• httpx>=0.27.0 — HTTP client
• Python 3.10+

License

MIT