Skip to main content
Glama
deenesjakoruzh
Cyreslab-AI

Burpsuite MCP Server

by Cyreslab-AI
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Burp Suite MCP Server

A Model Context Protocol (MCP) server that calls Burp Suite Professional's built-in local REST API to launch scans and retrieve scan status/issues.

Overview

This MCP server allows AI assistants to drive Burp Suite Professional's scanner for web security testing. It provides tools for:

  • Starting vulnerability scans on target URLs

  • Checking scan status

  • Retrieving vulnerability issues found by a scan

It talks to Burp Suite Professional's own local REST API — the same API surface Burp exposes for its own automation, not a separate hosted product. (Burp Suite Enterprise has a different, GraphQL-first API aimed at CI/CD; this server does not use it.)

get_proxy_history and get_site_map are kept in the tool list for interface compatibility with earlier versions of this server, but Burp Suite Professional's REST API has no endpoint for proxy history or the site map — see Known limitation below.

Related MCP server: BurpSuite MCP Server

Setting up Burp Suite's REST API

  1. Open Burp Suite Professional, go to Settings > Suite > REST API.

  2. Check "Service running".

  3. Note (or change) the service URL/port — the default is http://127.0.0.1:1337 (loopback only by default; PortSwigger advises against binding to a non-loopback interface on an untrusted network).

  4. Create an API key. The key is only shown once, at creation — copy it somewhere safe.

Burp's REST API is accessed as http://<host>:<port>/<api-key>/v0.1/.... It is also self-documenting: once the service is running, browsing to http://<host>:<port>/<api-key>/v0.1/<api-key> shows the exact request/response schema for your installed Burp version. PortSwigger does not publish a full static schema for this API, so if a tool's output looks off, that page is the source of truth.

Configuration

This server requires two environment variables — it will refuse to start without them:

Variable

Description

BURP_API_URL

Base URL of Burp's REST API service, e.g. http://localhost:1337

BURP_API_KEY

The API key generated in Settings > Suite > REST API

Features

Tools

The server exposes the following tools:

  1. start_scan: Start a new vulnerability scan on a target URL (POST /v0.1/scan). This launches a real scan against the target and generates live traffic to it.

    • Parameters:

      • target (required): Target URL to scan (e.g., https://example.com)

      • scope (optional): Passed through as-is to Burp's request body (e.g. { include: [...], exclude: [...] }). The exact shape isn't published by PortSwigger — check your instance's self-documenting API if unsure.

      • scan_configurations (optional): Passed through as-is (e.g. references to named configurations from Scanner > Scan configurations). If omitted, Burp uses its default crawl-and-audit configuration.

      • application_logins (optional): [{ username, password }, ...] for authenticated scanning, passed through as-is.

  2. get_scan_status: Check the status of a scan (GET /v0.1/scan/{task_id})

    • Parameters:

      • scan_id: Task id of the scan (returned by start_scan)

  3. get_scan_issues: Get vulnerability issues found so far by a scan. Issues come back embedded in the same GET /v0.1/scan/{task_id} response as scan status — there's no separate issues endpoint.

    • Parameters:

      • scan_id: Task id of the scan

      • severity: Filter issues by severity (high, medium, low, info, or all)

  4. get_proxy_history / get_site_map: Not supported by Burp Suite Professional's REST API. Calling either returns a clear explanatory error rather than fabricated data. See Known limitation.

Note: earlier versions of this server accepted a scan_type (passive/active/full) parameter on start_scan. That parameter had no real equivalent in Burp's REST API and has been replaced with the scope/scan_configurations/application_logins fields above, which map onto Burp's actual request body.

Known limitation: proxy history & site map

Burp Suite Professional's REST API only supports launching scans and reading scan status/issues — it has no endpoint for HTTP proxy history or the site map. That data is only reachable through:

  • Burp's separate Montoya extension API (a Java/Kotlin/Python extension you write and load into Burp, which can expose whatever data you need over its own interface), or

  • The desktop UI directly (Proxy > HTTP history, Target > Site map).

Rather than remove get_proxy_history/get_site_map outright (which could silently break existing configurations that reference them by name) or fake their output (which is the exact problem this rewrite fixes), both tools are kept and simply return an explanatory error when called.

Error handling

All tools call the real Burp REST API and surface real failures instead of falling back to mock data:

  • Connection refused / Burp not running / REST API not enabled: returns a clear message telling you to check that Burp is running with the REST API enabled and that BURP_API_URL is correct.

  • 401/403 (bad API key): returns a message telling you to check BURP_API_KEY.

  • 404: returns a message covering the two likely causes — an unknown/expired scan id, or a BURP_API_URL/BURP_API_KEY mismatch.

  • Any other non-2xx response is surfaced with the HTTP status and response body.

Installation

Installing via Smithery

To install Burp Suite Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @Cyreslab-AI/burpsuite-mcp-server --client claude

Manual Installation

  1. Build the server:

    cd /path/to/burpsuite-server
npm install
npm run build

  2. Add the server to your MCP settings configuration file:

    {
  "mcpServers": {
    "burpsuite": {
      "command": "node",
      "args": ["/path/to/burpsuite-server/build/index.js"],
      "env": {
        "BURP_API_URL": "http://localhost:1337",
        "BURP_API_KEY": "your-api-key-here"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Example Usage

Here are some examples of how to use the Burp Suite MCP server with an AI assistant:

Starting a Scan

Use the Burp Suite MCP server to scan example.com for vulnerabilities.

Checking Scan Status

What's the status of scan <scan_id>?

Analyzing Vulnerabilities

What high severity vulnerabilities were found in scan <scan_id>?

Available Tools

5 tools
get_proxy_historyC

Get HTTP/HTTPS traffic captured by Burp Proxy

ParametersJSON Schema
NameRequiredDescriptionDefault
hostNoFilter by host (optional)
limitNoMaximum number of items to return (default: 10)
methodNoFilter by HTTP method (optional)
status_codeNoFilter by HTTP status code (optional)

TDQS

C2.9/5.0
Behavior2/5

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 states what the tool does but lacks details on permissions needed, rate limits, whether it returns real-time or historical data, or the format of the returned traffic. For a tool that retrieves potentially sensitive proxy data, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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 with zero wasted words. It's appropriately sized and front-loaded, making it easy to understand at a glance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of retrieving proxy traffic (which could involve large datasets or sensitive information), no annotations, and no output schema, the description is incomplete. It doesn't explain what the returned data looks like, any limitations, or how it integrates with the sibling tools, leaving gaps for an AI agent to use it effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, with clear descriptions for all four parameters (host, limit, method, status_code). The description adds no additional parameter semantics beyond what the schema provides, so it meets the baseline score of 3 without compensating for any gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Get') and resource ('HTTP/HTTPS traffic captured by Burp Proxy'), making the tool's purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'get_site_map' or 'get_scan_issues', which might also retrieve related data, so it doesn't reach the highest score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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. It doesn't mention any prerequisites, context for filtering traffic, or how it differs from siblings like 'get_site_map' (which might retrieve site structure) or 'get_scan_issues' (which might retrieve security findings).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_scan_issuesC

Get vulnerability issues found in a scan

ParametersJSON Schema
NameRequiredDescriptionDefault
scan_idYesID of the scan
severityNoFilter issues by severity

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but only states what the tool does without behavioral details. It lacks information on permissions, rate limits, pagination, or what happens if the scan_id is invalid, which is critical for a tool accessing vulnerability data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It's appropriately sized and front-loaded, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of vulnerability scanning, lack of annotations, and no output schema, the description is insufficient. It doesn't explain return values, error handling, or behavioral constraints, leaving gaps that could hinder correct tool invocation by an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description mentions 'vulnerability issues' and 'scan', which aligns with the 'scan_id' parameter, but adds no meaning beyond the schema's 100% coverage. Since the schema fully describes both parameters, the baseline score of 3 is appropriate as the description doesn't enhance parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Get') and resource ('vulnerability issues found in a scan'), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'get_scan_status' or 'get_proxy_history', which prevents a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. For example, it doesn't clarify if this should be used after 'start_scan' or alongside 'get_scan_status', leaving the agent without context for selection among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_scan_statusC

Check the status of a running scan

ParametersJSON Schema
NameRequiredDescriptionDefault
scan_idYesID of the scan to check

TDQS

C2.9/5.0
Behavior2/5

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 states the tool checks status but doesn't describe what the status includes (e.g., progress percentage, state like 'running'/'completed'), whether it's read-only (implied but not explicit), or any rate limits or authentication needs. This leaves significant gaps for an agent to understand the tool's behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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 earns its place, making it highly concise and well-structured for quick comprehension.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a scanning tool with no annotations and no output schema, the description is insufficient. It doesn't explain what status information is returned (e.g., progress, errors) or behavioral aspects like idempotency or error handling, leaving the agent with incomplete context for effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, with the 'scan_id' parameter clearly documented. The description adds no additional semantic context beyond implying the scan must be 'running', which is minimal value. Baseline 3 is appropriate as the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('Check') and resource ('status of a running scan'), making it immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_scan_results' or 'list_scans', which could provide similar status information in different contexts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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 'get_scan_results' or 'list_scans'. It mentions 'running scan' but doesn't clarify prerequisites (e.g., whether the scan must be actively executing) or exclusions (e.g., not for completed scans).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_site_mapB

Get the site structure discovered during scanning and browsing

ParametersJSON Schema
NameRequiredDescriptionDefault
hostNoFilter by host (optional)
limitNoMaximum number of items to return (default: 20)
with_parametersNoOnly show URLs with parameters (optional)

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves 'site structure discovered during scanning and browsing,' implying a read-only operation, but doesn't specify if this is real-time data, cached results, or requires specific permissions. It also lacks details on output format, pagination, or error handling, which are critical for a tool with parameters like 'limit' and filtering options.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence: 'Get the site structure discovered during scanning and browsing.' It is front-loaded with the core purpose, uses clear language, and avoids unnecessary words. Every part of the sentence contributes directly to understanding the tool's function, 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.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 3 parameters with full schema coverage but no annotations or output schema, the description is minimally adequate. It covers the basic purpose but lacks context on behavioral aspects like data freshness, permissions, or output format. For a scanning-related tool that likely interacts with dynamic data, more details on how it integrates with siblings (e.g., after 'start_scan') would improve completeness, but it meets the minimum viable threshold.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

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 for 'host' (filter by host), 'limit' (maximum items), and 'with_parameters' (only show URLs with parameters). The description doesn't add any meaning beyond this, as it doesn't explain how these parameters affect the 'site structure' retrieval or provide usage examples. With high schema coverage, the baseline score of 3 is appropriate, as the schema handles the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Get the site structure discovered during scanning and browsing.' It specifies the verb ('Get') and resource ('site structure'), and distinguishes it from siblings like 'get_proxy_history' or 'get_scan_issues' by focusing on site structure rather than proxy logs or issues. However, it doesn't explicitly differentiate from 'get_scan_status' in terms of what 'site structure' entails versus 'status,' leaving some ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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. It doesn't mention any prerequisites, such as needing a scan to have been performed first, or compare it to siblings like 'get_scan_status' for status updates or 'start_scan' for initiating scans. Without such context, users might struggle to choose the right tool in this scanning-related set.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

start_scanC

Start a new vulnerability scan on a target URL

ParametersJSON Schema
NameRequiredDescriptionDefault
scan_typeNoType of scan to perform
targetYesTarget URL to scan (e.g., https://example.com)

TDQS

C2.9/5.0
Behavior2/5

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 states the action ('Start a new vulnerability scan') but lacks details on execution traits, such as whether it's asynchronous, requires authentication, has rate limits, or what happens upon invocation (e.g., scan initiation vs. immediate results). This is inadequate for a mutation tool with zero annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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 unnecessary words. It is front-loaded with the core action and resource, making it easy to parse and understand quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of starting a vulnerability scan (a mutation operation with potential side effects), no annotations, and no output schema, the description is incomplete. It fails to address key contextual aspects like what the tool returns (e.g., a scan ID), error conditions, or behavioral implications, leaving significant gaps for the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

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 for both parameters (scan_type with enum values and target with examples). The description adds no additional parameter semantics beyond what the schema provides, such as explaining scan_type differences or target format nuances, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Start a new vulnerability scan') and the target ('on a target URL'), providing a specific verb+resource combination. However, it doesn't differentiate from sibling tools like 'get_scan_status' or 'get_scan_issues', which are related but not direct alternatives for initiating scans.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description offers no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, such as needing a target URL, or clarify its role relative to sibling tools like 'get_can_status' for monitoring scans. This leaves the agent without context for tool selection.

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.

  1. 5 tool updatesv1.0.0
    • First observedget_proxy_history
    • First observedget_scan_issues
    • First observedget_scan_status
    • First observedget_site_map
    • First observedstart_scan
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.3/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: get_proxy_history retrieves captured traffic, get_scan_issues fetches vulnerability findings, get_scan_status checks scan progress, get_site_map provides site structure, and start_scan initiates new scans. The descriptions make it unambiguous which tool to use for each specific task.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern with 'get_' or 'start_' prefixes followed by descriptive nouns (proxy_history, scan_issues, scan_status, site_map, scan). This uniform snake_case naming makes the tool set predictable and easy to understand.

Tool Count4/5

Five tools is reasonable for a BurpSuite security testing server, covering core functions like traffic capture, scanning, and results retrieval. While slightly lean, it provides essential operations without being overwhelming. A few additional tools for scan configuration or issue management could enhance completeness but aren't critical.

Completeness3/5

The tools cover basic scanning workflow (start, check status, get results) and proxy history, but lack operations for managing scans (e.g., pause, stop, configure) or interacting with issues (e.g., export, filter, annotate). This creates minor gaps that agents might need to work around, though core functionality is present.

Maintenance

ActivityMaintained
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches