Skip to main content
Glama
intruder-io

intruder-mcp

Official

list_issues

Identify and retrieve security issues from your Intruder account using filters like target addresses, severity, tag names, and snoozed status.

Instructions

    List issues in the Intruder account with optional filters.

    Args:
        target_addresses: Filter by a list of target addresses
        tag_names: Filter by a list of tag names
        snoozed: Filter by snoozed status (true or false)
        severity: Filter by severity level (one of 'critical', 'high', 'medium', 'low')
    

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
target_addressesNo
tag_namesNo
snoozedNo
severityNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • MCP tool registration for 'list_issues' using @mcp.tool() decorator. Defines the tool as an async function with optional filters: target_addresses, tag_names, snoozed, severity.
    @mcp.tool()
    async def list_issues(target_addresses: Optional[List[str]] = None,
                         tag_names: Optional[List[str]] = None,
                         snoozed: Optional[bool] = None,
                         severity: Optional[str] = None) -> str:
        """
        List issues in the Intruder account with optional filters.
    
        Args:
            target_addresses: Filter by a list of target addresses
            tag_names: Filter by a list of tag names
            snoozed: Filter by snoozed status (true or false)
            severity: Filter by severity level (one of 'critical', 'high', 'medium', 'low')
        """
        issues = api.list_issues_all(
            target_addresses=target_addresses,
            tag_names=tag_names,
            snoozed=snoozed,
            severity=severity
        )
        formatted = [f"{issue.id} - {issue.title} ({issue.severity})" for issue in issues]
        return "\n".join(formatted)
  • list_issues API client method - makes HTTP GET request to /issues/ endpoint with optional query params. Returns PaginatedIssueList (single page).
    def list_issues(self, severity: Optional[str] = None, snoozed: Optional[bool] = None, 
                   issue_ids: Optional[List[int]] = None, tag_names: Optional[List[str]] = None,
                   target_addresses: Optional[List[str]] = None, limit: Optional[int] = None,
                   offset: Optional[int] = None) -> PaginatedIssueList:
        params = {}
        if severity:
            params["severity"] = severity
        if snoozed is not None:
            params["snoozed"] = snoozed
        if issue_ids:
            params["issue_ids"] = issue_ids
        if tag_names:
            params["tag_names"] = tag_names
        if target_addresses:
            params["target_addresses"] = target_addresses
        if limit:
            params["limit"] = limit
        if offset:
            params["offset"] = offset
        return PaginatedIssueList(**self.client.get(f"{self.base_url}/issues/", params=params).json())
  • list_issues_all helper - paginates through all issues by calling list_issues in a loop with offset/limit=100, yielding each issue.
    def list_issues_all(self, severity: Optional[str] = None, snoozed: Optional[bool] = None,
                       issue_ids: Optional[List[int]] = None, tag_names: Optional[List[str]] = None,
                       target_addresses: Optional[List[str]] = None) -> Generator[Issue, None, None]:
        offset = 0
        while True:
            response = self.list_issues(severity=severity, snoozed=snoozed, issue_ids=issue_ids,
                                      tag_names=tag_names, target_addresses=target_addresses,
                                      limit=100, offset=offset)
            for issue in response.results:
                yield issue
            if not response.next:
                break
            offset += len(response.results)
  • PaginatedIssueList schema - Pydantic model for the paginated response containing a list of Issue objects.
    class PaginatedIssueList(PaginatedResponse):
        results: List[Issue]
  • Issue schema - Pydantic model representing an issue with fields: id, severity, title, description, remediation, snoozed, etc.
    class Issue(BaseModel):
        id: int
        severity: str
        title: str
        description: str
        remediation: str
        snoozed: bool
        snooze_reason: Optional[str] = None
        snooze_until: Optional[date] = None
        occurrences: Optional[HttpUrl] = None
        exploit_likelihood: Union[ExploitLikelihoodEnum, None]
        cvss_score: Optional[float] = None
Behavior2/5

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

No annotations are provided, so the description must convey behavioral traits. It states 'List issues', implying a read operation, but does not disclose any side effects, authentication needs, rate limits, or data volume expectations. For a list endpoint, pagination, default ordering, or maximum results are common concerns that remain unaddressed.

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

Conciseness4/5

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

The description is concise: one line for purpose followed by a parameter list. It is front-loaded with the main action. Every sentence provides value; no fluff. While it could be more structured, it is appropriate for a Python docstring format.

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?

The tool has an output schema, so the description need not explain return values. However, it does not mention pagination, sorting, or default behavior when no filters are applied. For a list tool with optional filters and no required parameters, this contextual information would be helpful for an agent to use the tool correctly.

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 lists all four parameters and provides some meaning beyond the schema, especially for severity where it enumerates possible values ('critical', 'high', 'medium', 'low'). However, for target_addresses and tag_names, it only says 'Filter by a list of...' without explaining the format or behavior. With 0% schema description coverage, the description partially compensates but lacks depth.

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 'List issues in the Intruder account', specifying the verb and resource. It distinguishes from sibling tools like create_scan or get_scan by focusing on listing. However, it does not explicitly differentiate from list_occurrences or list_scans, so slightly less than perfect.

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 given on when to use this tool versus alternatives. The description only mentions optional filters, but does not explain scenarios where filtering is needed or when other list tools might be more appropriate. 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.

Install Server

Other Tools

Latest Blog Posts

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/intruder-io/intruder-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server