MCP AbuseIPDB Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP AbuseIPDB ServerCheck the reputation of the IP address 193.201.224.225"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP AbuseIPDB Server
An MCP (Model Context Protocol) server that provides threat intelligence lookups against the AbuseIPDB database. This server enables any MCP-capable client to perform IP reputation checks, CIDR block analysis, and access curated blacklists with intelligent caching and rate limiting.
Features
IP Reputation Checks: Single IP address lookups with detailed abuse data
CIDR Block Analysis: Check entire network ranges for malicious activity
Blacklist Access: Retrieve current AbuseIPDB blacklist with configurable confidence levels
Bulk Operations: Check multiple IP addresses efficiently
Log Enrichment: Extract and analyze IP addresses from log lines
Intelligent Caching: SQLite-based caching with TTL to minimize API usage
Rate Limiting: Built-in quota management for AbuseIPDB API limits
Security Focused: Input validation, private IP filtering, and secure defaults
Related MCP server: IPLocate MCP Server
Quick Start
Prerequisites
Python 3.11 or higher
AbuseIPDB API key (get one at abuseipdb.com)
Installation
Clone the repository:
git clone <repository-url>
cd AbuseIPDB-MCPInstall the package:
pip install -e .Set up your environment:
cp .env.example .env
# Edit .env and add your ABUSEIPDB_API_KEYRun the server:
python -m mcp_abuseipdb.serverMCP Client Configuration
Option 1: Using the Enhanced Startup Script (Recommended)
Add to your MCP client configuration (e.g., mcp.json):
{
"mcpServers": {
"mcp-abuseipdb": {
"command": "python",
"args": ["scripts/start_mcp_server.py"],
"cwd": "/path/to/AbuseIPDB-MCP",
"env": {
"ABUSEIPDB_API_KEY": "your_api_key_here"
}
}
}
}Option 2: Direct Module Execution
{
"mcpServers": {
"mcp-abuseipdb": {
"command": "python",
"args": ["-m", "mcp_abuseipdb.server"],
"cwd": "/path/to/AbuseIPDB-MCP",
"env": {
"ABUSEIPDB_API_KEY": "your_api_key_here"
}
}
}
}Important Notes:
Replace
your_api_key_herewith your actual AbuseIPDB API keyUpdate
/path/to/AbuseIPDB-MCPto the actual path where you cloned this repositoryThe enhanced startup script (Option 1) provides better error diagnostics
Ensure your API key is valid and not expired on the AbuseIPDB website
Available Tools
check_ip
Check the reputation of a single IP address.
Parameters:
ip_address(required): IP address to checkmax_age_days(optional): Maximum age of reports (default: 30)verbose(optional): Include detailed reports (default: false)threshold(optional): Confidence threshold for flagging (default: 75)
check_block
Check the reputation of a CIDR network block.
Parameters:
network(required): CIDR network (e.g., "192.168.1.0/24")max_age_days(optional): Maximum age of reports (default: 30)
get_blacklist
Retrieve the AbuseIPDB blacklist.
Parameters:
confidence_minimum(optional): Minimum confidence level (default: 90)limit(optional): Maximum entries to retrieve
bulk_check
Check multiple IP addresses efficiently.
Parameters:
ip_addresses(required): List of IP addressesmax_age_days(optional): Maximum age of reports (default: 30)threshold(optional): Confidence threshold for flagging (default: 75)
enrich_log_line
Extract and analyze IP addresses from log entries.
Parameters:
log_line(required): Log line containing IP addressesthreshold(optional): Confidence threshold for flagging (default: 75)max_age_days(optional): Maximum age of reports (default: 30)
Available Resources
cache://info
Get current cache statistics and rate limiter status.
doc://usage
Complete API usage documentation and examples.
Available Prompts
triage_ip
Generate security analyst triage notes for an IP address.
Parameters:
ip_data(required): IP check data from AbuseIPDB
Configuration
All configuration is done via environment variables. Copy .env.example to .env and customize:
Required Settings
ABUSEIPDB_API_KEY: Your AbuseIPDB API key
Optional Settings
MAX_AGE_DAYS: Default report age limit (default: 30)CONFIDENCE_THRESHOLD: Default confidence threshold (default: 75)DAILY_QUOTA: API request quota (default: 1000)CACHE_DB_PATH: SQLite cache file location (default: ./cache.db)LOG_LEVEL: Logging level (default: INFO)ALLOW_PRIVATE_IPS: Allow checking private IPs (default: false)
Usage Examples
Basic IP Check
Check the reputation of 8.8.8.8Log Analysis
Analyze this log line for threats:
192.168.1.100 - - [10/Jan/2024:10:00:00 +0000] "GET /admin/login.php HTTP/1.1" 200 1234Bulk Analysis
Check these IPs for malicious activity:
- 203.0.113.100
- 198.51.100.50
- 192.0.2.25Security Investigation
I'm investigating suspicious activity from 203.0.113.100. Can you:
1. Check its reputation with detailed reports
2. Analyze the surrounding network block
3. Generate triage notes for our security teamSee examples/queries.md for more detailed examples.
Docker Deployment
Build and run with Docker:
# Build the image
docker build -f docker/Dockerfile -t mcp-abuseipdb .
# Run the container
docker run -e ABUSEIPDB_API_KEY=your_key_here mcp-abuseipdbDevelopment
Setup Development Environment
pip install -e ".[dev]"
pre-commit installRun Tests
pytestSecurity Considerations
API Key Protection: Never commit API keys to version control
Private IP Filtering: Private IPs are blocked by default
Rate Limiting: Built-in quota management prevents API abuse
Input Validation: All inputs are validated and sanitized
Caching: Reduces API calls and improves performance
Rate Limits
AbuseIPDB free tier provides 1,000 requests per day. This server:
Implements intelligent caching to minimize API usage
Provides rate limiting with configurable quotas
Gracefully handles rate limit errors with backoff
Troubleshooting
"Unauthorized API key" Error in Claude App
If you're getting unauthorized API key errors when using the MCP server with Claude:
Verify API Key Configuration:
# Test your API key with the diagnostic script python diagnostics/api_auth_diagnostic.pyCheck Claude App Configuration:
Ensure your
mcp.jsonhas the correct API key in theenvsectionVerify the
cwdpath points to your project directoryMake sure the API key value matches exactly (no extra spaces)
Use Enhanced Startup Script:
Switch to Option 1 configuration (enhanced startup script)
Check the server logs in Claude app for diagnostic messages
Look for
[MCP AbuseIPDB]prefixed messages
Environment Variable Issues:
Ensure your
.envfile is in the project root directoryVerify the API key in
.envmatches your Claude app configurationCheck that the API key is valid on the AbuseIPDB website
Debug Steps:
# Test local server startup python scripts/start_mcp_server.py # Check environment loading python -c "from mcp_abuseipdb.settings import Settings; print('API key loaded:', bool(Settings().abuseipdb_api_key))"
Common Issues
"No .env file found": Make sure
.envexists in project root or set API key in Claude app config"Settings API key: EMPTY": API key not properly loaded from environment
"Environment var: EMPTY": API key not set in Claude app MCP configuration
Connection timeouts: Check your internet connection and AbuseIPDB service status
Contributing
Fork the repository
Create a feature branch
Make your changes with tests
Run the test suite and linting
Submit a pull request
License
MIT License — see LICENSE for details.
Support
Documentation: See
examples/directoryIssues: Please report bugs and feature requests via GitHub issues
API Documentation: AbuseIPDB API Docs
Changelog
v0.1.0
Initial release
Basic IP checking functionality
CIDR block analysis
Blacklist access
Bulk operations
Log enrichment
Caching and rate limiting
Docker support
Available Tools
5 toolsbulk_checkB
Check multiple IP addresses in batch against AbuseIPDB
| Name | Required | Description | Default |
|---|---|---|---|
| ip_addresses | Yes | List of IP addresses to check | |
| max_age_days | No | Maximum age of reports to consider in days | |
| threshold | No | Abuse confidence threshold for flagging (0-100) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the service (AbuseIPDB) and batch capability, but doesn't disclose rate limits, authentication requirements, what constitutes a 'check' (e.g., reputation scoring, blacklist lookup), error handling, or response format. For a tool with 3 parameters and no annotations, this leaves significant behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose ('Check multiple IP addresses in batch against AbuseIPDB'). Every word earns its place with no redundancy or unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 3 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., confidence scores, report details), error conditions, or behavioral constraints like rate limits. For a batch operation with external service integration, more context is needed for effective agent use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description doesn't add any parameter-specific semantics beyond what's in the schema (e.g., it doesn't explain how threshold interacts with AbuseIPDB's scoring system). Baseline 3 is appropriate when schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('check multiple IP addresses in batch') and the target resource ('against AbuseIPDB'), distinguishing it from sibling tools like 'check_ip' (likely single IP) and 'check_block' (likely IP block). It explicitly mentions the batch capability which differentiates it from single-item alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for batch checking IPs against AbuseIPDB, but doesn't explicitly state when to use this versus alternatives like 'check_ip' or 'check_block'. It provides context about the service (AbuseIPDB) but lacks explicit guidance on use cases, prerequisites, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
check_blockB
Check the reputation of a CIDR block using AbuseIPDB
| Name | Required | Description | Default |
|---|---|---|---|
| network | Yes | CIDR network to check (e.g., '192.168.1.0/24') | |
| max_age_days | No | Maximum age of reports to consider in days |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions the service (AbuseIPDB) but does not disclose behavioral traits such as rate limits, authentication requirements, error handling, or what the output looks like (e.g., reputation score, report details). This is a significant gap for a tool with external dependencies.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without any wasted words. It is appropriately sized and front-loaded with the core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of reputation checking with an external service, no annotations, and no output schema, the description is incomplete. It lacks details on behavioral aspects (e.g., rate limits, auth), output format, and error handling, which are crucial for effective tool use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents both parameters ('network' as CIDR and 'max_age_days' with constraints). The description adds no additional parameter semantics beyond what the schema provides, such as examples of valid CIDR formats or implications of the age filter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('check the reputation') and resource ('CIDR block') using a named service ('AbuseIPDB'). It distinguishes this tool from sibling tools like 'check_ip' (likely for individual IPs) and 'bulk_check' (likely for multiple checks).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for reputation checking of CIDR blocks, but does not explicitly state when to use this tool versus alternatives like 'check_ip' for single IPs or 'bulk_check' for multiple blocks. No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
check_ipA
Check the reputation of a single IP address using AbuseIPDB
| Name | Required | Description | Default |
|---|---|---|---|
| ip_address | Yes | IP address to check | |
| max_age_days | No | Maximum age of reports to consider in days | |
| verbose | No | Include detailed report information | |
| threshold | No | Abuse confidence threshold for flagging (0-100) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions the service (AbuseIPDB) but does not disclose behavioral traits such as rate limits, authentication needs, error handling, or what the output looks like. For a tool with no annotations, this leaves significant gaps in understanding its operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose without unnecessary details. Every word earns its place, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, the description is incomplete. It lacks information on behavioral aspects like rate limits, authentication, and output format. For a tool with 4 parameters and no structured output, the description should provide more context to be fully helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents all parameters. The description does not add any meaning beyond what the schema provides, such as explaining parameter interactions or usage examples. Baseline 3 is appropriate as the schema handles parameter documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Check the reputation') and resource ('a single IP address'), specifying the service provider ('using AbuseIPDB'). It distinguishes from sibling tools like 'bulk_check' (multiple IPs) and 'check_block' (IP block) by emphasizing 'single IP address'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context for checking IP reputation via AbuseIPDB, but does not explicitly state when to use this tool versus alternatives like 'bulk_check' or 'check_block'. It provides clear purpose but lacks explicit exclusions or named alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
enrich_log_lineB
Extract and enrich IP addresses from a log line with AbuseIPDB data
| Name | Required | Description | Default |
|---|---|---|---|
| log_line | Yes | Log line containing IP addresses to enrich | |
| threshold | No | Abuse confidence threshold for flagging (0-100) | |
| max_age_days | No | Maximum age of reports to consider in days |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions enrichment with AbuseIPDB data but lacks details on rate limits, authentication requirements, error handling, or what the output looks like (e.g., structured data vs. raw text). This is inadequate for a tool that likely involves external API calls and data processing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core purpose without unnecessary words. Every part of the sentence contributes directly to explaining what the tool does, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (involving external API data enrichment) and lack of annotations and output schema, the description is insufficient. It doesn't cover behavioral aspects like rate limits or output format, leaving critical gaps for an AI agent to use it effectively in context with sibling tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents all parameters. The description adds no additional meaning beyond implying that 'log_line' contains IP addresses and 'threshold'/'max_age_days' relate to AbuseIPDB filtering. This meets the baseline for high schema coverage but doesn't enhance understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Extract and enrich'), the target resource ('IP addresses from a log line'), and the data source ('with AbuseIPDB data'). It distinguishes itself from sibling tools like 'check_ip' or 'bulk_check' by focusing on log line processing rather than direct IP checking or bulk operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'check_ip' for single IPs or 'bulk_check' for multiple IPs. It doesn't mention prerequisites, such as needing AbuseIPDB access, or exclusions, like whether it handles IPv6 addresses or specific log formats.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_blacklistB
Retrieve the AbuseIPDB blacklist of malicious IP addresses
| Name | Required | Description | Default |
|---|---|---|---|
| confidence_minimum | No | Minimum confidence level (0-100) | |
| limit | No | Maximum number of entries to retrieve |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. While 'Retrieve' implies a read operation, it doesn't specify whether this is a real-time query or cached data, what format the results come in, whether there are rate limits, or any authentication requirements. The description is too minimal for a tool that presumably accesses external threat intelligence data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that gets straight to the point with zero wasted words. It's appropriately sized for a simple retrieval tool and front-loads the essential information about what the tool does.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool that retrieves threat intelligence data with no annotations and no output schema, the description is insufficient. It doesn't explain what format the blacklist returns (e.g., list of IPs with metadata), whether results are paginated, or any behavioral characteristics. The agent would be left guessing about important operational aspects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage with clear documentation of both parameters. The description adds no additional parameter information beyond what's already in the schema. Since schema coverage is high, the baseline score of 3 is appropriate - the description doesn't add value but doesn't need to compensate for schema gaps either.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Retrieve') and the specific resource ('AbuseIPDB blacklist of malicious IP addresses'), making the purpose immediately understandable. It distinguishes this tool from its siblings by focusing on retrieving a blacklist rather than checking individual IPs or performing bulk operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus its siblings like 'check_ip' or 'bulk_check'. It doesn't mention any prerequisites, alternatives, or contextual factors that would help an agent decide between this retrieval operation and other available tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
5 tool updates
v0.1.0- First observed
bulk_check - First observed
check_block - First observed
check_ip - First observed
enrich_log_line - First observed
get_blacklist
TDQS
Each tool has a clearly distinct purpose: bulk_check handles multiple IPs, check_block covers CIDR blocks, check_ip is for single IPs, enrich_log_line processes log lines, and get_blacklist retrieves a blacklist. There is no overlap or ambiguity between these functions.
All tools follow a consistent verb_noun pattern (e.g., check_ip, get_blacklist) with clear, descriptive names. There are no deviations in style or convention across the set.
With 5 tools, the server is well-scoped for AbuseIPDB functionality, covering key operations like single/bulk IP checks, block analysis, log enrichment, and blacklist retrieval. Each tool earns its place without feeling excessive or insufficient.
The tool set provides comprehensive coverage for the AbuseIPDB domain, including reputation checks at different scales (single, bulk, block), log enrichment, and blacklist access. There are no obvious gaps in the core workflows for this purpose.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
AbuseIPDB MCP — wraps AbuseIPDB v2 API (api.abuseipdb.com/api/v2)
Free no-key IP intelligence: geolocation, VPN detection, DNS, WHOIS, blacklists, breach checks
Free IPv4 lookups against a distributed attacker-observation corpus.
Breach intelligence API: email search, domain monitoring, passwords and stealer logs.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceIntegrates with the AbuseIPDB API to check IP addresses for abuse reports and report abusive IP addresses.2MIT
- AlicenseNot gradedqualityDmaintenanceEnables IP address intelligence lookup including geolocation, network information, privacy detection (VPN/proxy/Tor), company data, and abuse contacts using IPLocate.io API. Supports both IPv4 and IPv6 addresses with comprehensive analysis tools and security assessment capabilities.107MIT
- AlicenseNot gradedqualityDmaintenanceProvides comprehensive IP and domain security intelligence, enabling analysis of IP addresses and domains for threat and reputation information.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to check IP reputation and abuse reports via AbuseIPDB, including abuse confidence scores, report details, and bulk IP triage.201MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/alephnan/AbuseIPDB-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server