Lattice: CVE, MITRE ATT&CK and detection graph for security agents

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

CVE, KEV, MITRE ATT&CK, CWE and detection graph for AI agents; every link names its source.

Measured statistics

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Lattice: CVE, MITRE ATT&CK and detection graph for security agents": {
      "url": "https://lattice.namiq.io/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (7)

• graph_meta read-only

  Describe the graph this server reads, without looking up any fact in it. Returns the snapshot id and creation time, the schema version with notable schema changes, the node labels (types), the relationship verbs, the contributing sources, and the path templates that graph_path accepts. When to call it: once at the start of a session, to learn the valid values for the label argument of graph_lookup, graph_search and graph_neighbors, the verb values for graph_neighbors and the template names for graph_path; and when you report a finding, to cite the snapshot id it came from. What it is not for: it returns no CVEs, techniques, groups or detections. Use graph_lookup to find those. It takes no arguments, only reads, and gives the same answer to every caller of a snapshot.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• graph_lookup read-only

  Find nodes by exact external id, e.g. CVE-2021-44228, T1059.001, CWE-79. Returns each match with its source (a CVE has a kev node if CISA lists it as exploited, and an nvd node) and a uid for graph_node and graph_neighbors. An empty items list means the graph has no such id.

  Parameters:

  • id (required) — string — Exact external id, for example CVE-2021-44228, T1059.001 or CWE-79. Case-insensitive; prefixes and free text do not match (use graph_search for a prefix).
  • label — Optional node label (type) to restrict the answer to, for example CVE, Technique or Detection. The valid labels are listed by graph_meta; an unknown label is refused with the valid ones.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• graph_search read-only

  List nodes whose external id starts with a prefix (e.g. CVE-2024-1, T105). Ids only, not free text. If the answer has truncated: true, pass its next_cursor as cursor to continue; a list without truncated is complete.

  Parameters:

  • id_prefix (required) — string — Start of an external id, at least a few characters, for example CVE-2024-1 or T105. Not free text.
  • label — Optional node label (type) to restrict the answer to, for example CVE, Technique or Detection. The valid labels are listed by graph_meta; an unknown label is refused with the valid ones.
  • limit — integer — Maximum items to return. The server clamps it to its own maximum; the answer reports applied_limit and limit_clamped.
  • cursor — Continuation token: pass the next_cursor from a previous answer that had truncated: true to get the next page. Omit it for the first page.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• graph_node read-only

  One node's properties (long text is clipped). uid comes from graph_lookup or graph_search. On a kev node: date_added, due_date, known_ransomware_use (Known or Unknown; Unknown means not recorded), required_action, vendor_project, product. On an nvd node: description and metadata (cvss_score, affected_products). A cvss_score of 0 means not scored yet.

  Parameters:

  • uid (required) — string — The uid of a node, as returned by graph_lookup, graph_search or graph_neighbors.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• graph_neighbors read-only

  Directly connected nodes with each link's verb, source, confidence and whether it is declared or inferred. Declared and cross-source links come first. If the answer has truncated: true, pass its next_cursor as cursor to continue.

  Parameters:

  • uid (required) — string — The uid of the node whose links to list, from graph_lookup, graph_search or graph_node.
  • verb — Optional upper-case relationship verb to keep, for example EXPLOITS, DETECTS or USES. The valid verbs are listed by graph_meta.
  • label — Optional node label (type) to restrict the answer to, for example CVE, Technique or Detection. The valid labels are listed by graph_meta; an unknown label is refused with the valid ones.
  • limit — integer — Maximum links to return. The server clamps it to its own maximum; the answer reports applied_limit and limit_clamped.
  • cursor — Continuation token: pass the next_cursor from a previous answer that had truncated: true to get the next page. Omit it for the first page.
  • direction — string — Which links to follow: out (from this node), in (to this node) or both.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• graph_path read-only

  Answer a fixed multi-hop question from an external id. Templates: cve-context (start: CVE), cve-to-defense (start: CVE), technique-coverage (start: Technique), weakness-chain (start: Weakness), actor-ttps (start: ThreatActor/Malware/Campaign). cve-to-defense gives the techniques a CVE enables and the detections and procedures for them.

  Parameters:

  • template (required) — string — Name of the path template, one of: cve-context, cve-to-defense, technique-coverage, weakness-chain, actor-ttps.
  • id (required) — string — External id to start from; it must be of a kind the template starts from (see the template list in the tool description).
  • label — Optional node label (type) to restrict the answer to, for example CVE, Technique or Detection. The valid labels are listed by graph_meta; an unknown label is refused with the valid ones.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• graph_notices read-only

  Return the licence and attribution notices for the data sources behind an answer. Other tools list notice ids with their answers. Pass those ids here to get, for each notice, its title, what it applies to, the obligation it places on you (for example attribution wording or a share-alike condition) and the notice text. Long texts are cut and flagged text_truncated, with text_url pointing to the full text. When to call it: before you quote, republish or build on anything the graph returned, and then quote what the obligation requires. Unknown ids are reported in unknown rather than failing. What it is not for: it returns no security facts, and it is source licence information, not legal advice. It only reads and gives the same answer each time for a snapshot.

  Parameters:

  • ids — Notice ids to fetch, as listed in the notice list of other answers, at most 10 per call. Omit to get the notices the server holds (up to 10). Ids it does not know come back in the unknown list.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.