mitre-cwe-mcp-server

Search CAPEC attack patterns

cwe_search_attack_patterns

Read-onlyIdempotent

Search CAPEC attack patterns by every whitespace-separated text token, recorded CWE or ATT&CK mapping, abstraction, severity, or likelihood. Text tokens match at word starts or camelCase humps; tokens of at least four Unicode letters also match after exactly one un or mis prefix at a word start (config finds misconfiguration), with possible spelling coincidences. An exact closed spelling also matches Unicode letter words joined by single ASCII hyphens (hardcoded finds hard-coded). Parent ATT&CK techniques include recorded subtechniques; CWE mappings are exact without hierarchy expansion. Omit filters to browse. Deprecated and Obsolete patterns are excluded by default. Mappings are incomplete and do not validate current ATT&CK coverage. Results order by all tokens in the name or in one recorded alternate term such as MITM, then all in the description, then any other match, then numeric ID; use cwe_get_attack_pattern for complete sections and follow nextCursor for remaining matches.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "cwe_search_attack_patterns"
  }
}

Input Schema

Name	Required	Description
`cweId`	No	Exact recorded CWE mapping, a CWE ID such as CWE-79 or 79 from cwe_search_weaknesses; blank means unset.
`limit`	No	Maximum page size; capped at 100 items with disclosure.
`cursor`	No	Opaque continuation returned by this tool.
`filter`	No	All-token case-insensitive filter over the name, recorded alternate terms, and description; each token matches at a word start or camelCase hump (path finds XPath). Tokens of at least four Unicode letters also match after exactly one un or mis prefix at a word start; spelling coincidences can match. An exact closed spelling also matches Unicode letter words joined by single ASCII hyphens. Blank means unset.
`severity`	No	Exact source severity; discover with cwe_list_reference topic filter_values.
`likelihood`	No	Exact source likelihood; discover with cwe_list_reference topic filter_values.
`abstraction`	No	Exact CAPEC abstraction; blank means unset.
`includeInactive`	No	Include Deprecated and Obsolete patterns; default false.
`attackTechniqueId`	No	Recorded Tdddd or Tdddd.ddd mapping from cwe_get_attack_pattern mappings, also accepting bare numeric form; blank means unset.

Output Schema

Name	Required	Description
`cap`	No	Effective limit.
`error`	No	Present when the call failed. Absent on success.
`shown`	No	Page item count.
`notice`	No	Empty-result or cap guidance.
`results`	No	Matching pattern page.
`truncated`	No	Whether more matches remain.
`pagination`	No	Local result pagination.
`provenance`	No	Loaded catalog provenance.
`totalCount`	No	Matching count before paging.
`appliedFilters`	No	Applied filters and defaults.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 11, 2026

changedInput schema / properties / filter / description

Previous value: -"All-token case-insensitive filter over the name, recorded alternate terms, and description; each token matches at a word start or camelCase hump (path finds XPath). Tokens of at least four Unicode letters also match after exactly one un or mis prefix at a word start; spelling coincidences can match. Blank means unset."New value: +"All-token case-insensitive filter over the name, recorded alternate terms, and description; each token matches at a word start or camelCase hump (path finds XPath). Tokens of at least four Unicode letters also match after exactly one un or mis prefix at a word start; spelling coincidences can match. An exact closed spelling also matches Unicode letter words joined by single ASCII hyphens. Blank means unset."

changedInput schema / properties / limit / description

Previous value: -"Maximum page size; capped at 100 and a 24,000-byte response budget with disclosure."New value: +"Maximum page size; capped at 100 items with disclosure."

Changed1 schema field changedOct 24, 2026

changedInput schema / properties / filter / description

Previous value: -"All-token case-insensitive filter over the name, recorded alternate terms, and description; each token matches at a word start or camelCase hump (path finds XPath), never inside a word. Blank means unset."New value: +"All-token case-insensitive filter over the name, recorded alternate terms, and description; each token matches at a word start or camelCase hump (path finds XPath). Tokens of at least four Unicode letters also match after exactly one un or mis prefix at a word start; spelling coincidences can match. Blank means unset."

First observedOct 23, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnly/openWorld/idempotent, and the description adds substantial semantics: token matching at word starts or camelCase humps, single un/mis prefix matching, hyphen-joined spellings, parent ATT&CK techniques including subtechniques, exact CWE without hierarchy expansion, and default exclusion of Deprecated/Obsolete. It also honestly warns that mappings are incomplete and do not validate current ATT&CK coverage. Only the absence of any note on result volume/pagination cost relative to openWorldHint keeps it from a 5.

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?

Front-loaded with the search space, then matching rules, then scope caveats, then ordering and the sibling pointer. Every sentence carries information, but the filter-matching clauses restate what the input schema already documents, and the parenthetical approach makes the block dense.

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

Completeness5/5

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

An output schema exists, so return values need not be described, yet the description still explains result ordering and the nextCursor pagination path. Combined with exclusion defaults, mapping-incompleteness caveats, and the sibling handoff, an agent has everything needed for a 9-parameter, zero-required search tool.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3; however the description adds meaning not fully in the schema, notably that a parent ATT&CK technique id pulls in its recorded subtechniques and that CWE mappings are exact with no hierarchy expansion. Those are semantic consequences of parameter values rather than restatements. The filter matching rules largely duplicate the filter parameter's own schema text.

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

Purpose5/5

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

Opens with a specific verb+resource ("Search CAPEC attack patterns") and enumerates the exact dimensions searchable: text tokens, recorded CWE/ATT&CK mappings, abstraction, severity, likelihood. It is immediately distinguishable from the detail-oriented sibling cwe_get_attack_pattern, which is named explicitly.

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

Usage Guidelines5/5

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

Provides clear when-to-use guidance ("Omit filters to browse"), a when-to-use-the-alternative rule ("use cwe_get_attack_pattern for complete sections"), and continuation behavior ("follow nextCursor for remaining matches"). An agent does not need to guess the routing between search and get.

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

All mitre-cwe-mcp-server tools Inspect

Try in Browser

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

Glama MCP Gateway

Add one secure layer between your agents and this server.