Skip to main content
Glama
marcoeg

mcp-nvd

search_cve

Search for Common Vulnerabilities and Exposures (CVEs) by keyword in the NIST National Vulnerability Database to identify security vulnerabilities.

Instructions

Search CVEs by keyword and return formatted results matching the get_cve format.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keywordYes
exact_matchNo
conciseNo
resultsNo

Implementation Reference

  • The core handler function for the 'search_cve' MCP tool. It constructs the NVD API query URL based on parameters, fetches data using make_nvd_request, formats results using format_cve, and returns a concatenated string of formatted CVEs.
    @mcp.tool()
    async def search_cve(keyword: str, exact_match: bool = False, concise: bool = False, results: int = 10) -> str:
        """Search CVEs by keyword and return formatted results matching the get_cve format."""
        params = {
            "keywordSearch": keyword,
            "resultsPerPage": results  # Use the results parameter here
        }
        if exact_match:
            params["keywordExactMatch"] = ""  # Presence of the param enables exact match, no value needed
    
        url = f"{BASE_URL}?{'&'.join(f'{k}={v}' for k, v in params.items())}"
        data = await make_nvd_request(url)
    
        if not data or "vulnerabilities" not in data or not data["vulnerabilities"]:
            return f"No CVEs found for keyword: {keyword} (exact_match: {exact_match})"
    
        logger.info(f"Searching CVEs with keyword: {keyword}, exact_match: {exact_match}, results: {results}")
        results_list = []
        for cve in data["vulnerabilities"]:
            formatted_cve = format_cve(cve["cve"], concise)
            results_list.append(formatted_cve)
    
        total_results = data.get("totalResults", 0)
        result_str = f"Found {len(results_list)} of {total_results} CVEs for keyword '{keyword}' (exact_match: {exact_match}, results requested: {results}):\n\n"
        result_str += "\n\n---\n\n".join(results_list)
        logger.info(f"Completed search for keyword: {keyword}, found {len(results_list)} results")
        return result_str
  • Supporting helper function to format individual CVE data into a readable string, used within search_cve to process each result.
    def format_cve(cve: Dict[str, Any], concise: bool = False) -> str:
        """Helper function to format a single CVE entry, shared by get_cve and search_cve."""
        try:
            cve_id = cve["id"]
            source_identifier = cve["sourceIdentifier"]
            published = cve["published"]
            last_modified = cve["lastModified"]
            vuln_status = cve["vulnStatus"]
            description = next(
                (desc["value"] for desc in cve["descriptions"] if desc["lang"] == "en"),
                "No English description available",
            )
    
            # Extract CVSS v3.1 metrics
            cvss_v31_metric = next(
                (metric for metric in cve.get("metrics", {}).get("cvssMetricV31", []) if metric["type"] == "Primary"),
                None,
            )
            cvss_v31_data = cvss_v31_metric["cvssData"] if cvss_v31_metric else None
            cvss_v31_score = cvss_v31_data.get("baseScore", "N/A") if cvss_v31_data else "N/A"
            cvss_v31_severity = cvss_v31_data.get("baseSeverity", "N/A") if cvss_v31_data else "N/A"
            cvss_v31_vector = cvss_v31_data.get("vectorString", "N/A") if cvss_v31_data else "N/A"
            cvss_v31_exploitability = cvss_v31_metric.get("exploitabilityScore", "N/A") if cvss_v31_metric else "N/A"
            cvss_v31_impact = cvss_v31_metric.get("impactScore", "N/A") if cvss_v31_metric else "N/A"
    
            # Extract CVSS v2.0 metrics
            cvss_v2 = next(
                (metric["cvssData"] for metric in cve.get("metrics", {}).get("cvssMetricV2", []) if metric["type"] == "Primary"),
                None,
            )
            cvss_v2_score = cvss_v2.get("baseScore", "N/A") if cvss_v2 else "N/A"
            cvss_v2_severity = cvss_v2.get("baseSeverity", "N/A") if cvss_v2 else "N/A"
            cvss_v2_vector = cvss_v2.get("vectorString", "N/A") if cvss_v2 else "N/A"
    
            # Extract weaknesses (CWE IDs)
            weaknesses = [
                desc["value"] for weak in cve.get("weaknesses", []) for desc in weak["description"] if desc["lang"] == "en"
            ]
            weaknesses_str = ", ".join(weaknesses) if weaknesses else "None listed"
    
            # Extract references with tags
            references = [f"{ref['url']} ({', '.join(ref.get('tags', []))})" for ref in cve.get("references", [])]
            references_str = "\n  - " + "\n  - ".join(references) if references else "None listed"
    
            # Extract configurations (CPEs)
            cpe_matches = []
            for node in cve.get("configurations", [{}])[0].get("nodes", []):
                for match in node.get("cpeMatch", []):
                    if match.get("vulnerable", False):
                        cpe_matches.append(match["criteria"])
            configurations_str = "\n  - " + "\n  - ".join(cpe_matches) if cpe_matches else "None listed"
    
            # Format output
            if concise:
                return (
                    f"CVE ID: {cve_id}\n"
                    f"Description: {description}\n"
                    f"CVSS v3.1 Score: {cvss_v31_score} ({cvss_v31_severity})"
                )
            else:
                return (
                    f"CVE ID: {cve_id}\n"
                    f"Source Identifier: {source_identifier}\n"
                    f"Published: {published}\n"
                    f"Last Modified: {last_modified}\n"
                    f"Vulnerability Status: {vuln_status}\n"
                    f"Description: {description}\n"
                    f"CVSS v3.1 Score: {cvss_v31_score} ({cvss_v31_severity})\n"
                    f"CVSS v3.1 Vector: {cvss_v31_vector}\n"
                    f"CVSS v3.1 Exploitability Score: {cvss_v31_exploitability}\n"
                    f"CVSS v3.1 Impact Score: {cvss_v31_impact}\n"
                    f"CVSS v2.0 Score: {cvss_v2_score} ({cvss_v2_severity})\n"
                    f"CVSS v2.0 Vector: {cvss_v2_vector}\n"
                    f"Weaknesses (CWE): {weaknesses_str}\n"
                    f"References:\n{references_str}\n"
                    f"Affected Configurations (CPE):\n{configurations_str}"
                )
        except Exception as e:
            logger.error(f"Error formatting CVE {cve.get('id', 'unknown')}: {str(e)}")
            return f"Error processing CVE: {str(e)}"
  • Utility function to perform asynchronous HTTP GET requests to the NVD API, handling errors and returning JSON data or None; called by search_cve.
    async def make_nvd_request(url: str) -> Dict[str, Any] | None:
        """Make a request to the NVD API with proper error handling."""
        async with httpx.AsyncClient() as client:
            try:
                response = await client.get(url, headers=HEADERS, timeout=30.0)
                response.raise_for_status()
                return response.json()
            except httpx.HTTPStatusError as e:
                logger.error(f"HTTP error: {e.response.status_code} - {e.response.text}")
                return None
            except httpx.RequestError as e:
                logger.error(f"Request error: {e}")
                return None
            except Exception as e:
                logger.error(f"Unexpected error: {e}")
                return None
  • mcp_nvd/main.py:1-1 (registration)
    Imports the FastMCP server instance which has the search_cve tool registered via decorator in server.py.
    from mcp_nvd.server import mcp
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 mentions that results are 'formatted' to match 'get_cve format,' which adds some context about output behavior. However, it doesn't disclose critical behavioral traits such as whether this is a read-only operation, potential rate limits, authentication requirements, error handling, or what happens when no results are found. For a search tool with zero annotation coverage, this is insufficient.

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 extremely concise—a single sentence that efficiently communicates the core functionality. Every word earns its place: it specifies the action ('Search'), target ('CVEs'), method ('by keyword'), and output characteristic ('formatted results matching the get_cve format'). There's no wasted verbiage or redundancy.

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 tool's complexity (4 parameters, no annotations, no output schema), the description is incomplete. It doesn't explain parameter meanings, behavioral constraints, or output details beyond referencing another tool's format. For a search function that likely returns structured data, more context is needed about what 'formatted results' entail and how parameters affect the search.

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

Parameters2/5

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

The schema description coverage is 0%, meaning none of the 4 parameters have descriptions in the schema. The description only mentions 'keyword' generically and doesn't explain what 'exact_match', 'concise', or 'results' parameters do, their effects, or practical usage. It fails to compensate for the complete lack of schema documentation, leaving parameters largely unexplained.

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: 'Search CVEs by keyword and return formatted results matching the get_cve format.' It specifies the verb ('Search'), resource ('CVEs'), and scope ('by keyword'), but doesn't explicitly differentiate from its sibling tool 'get_cve' beyond mentioning the output format. This makes it clear but lacks sibling differentiation.

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 mentions the sibling tool 'get_cve' only in the context of output format, not as an alternative for different use cases. There are no explicit instructions on when to choose search_cve over get_cve or other potential tools, leaving the agent without contextual usage direction.

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/marcoeg/mcp-nvd'

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