Skip to main content
Glama
CISO Assistant MCP Server

CISO Assistant MCP Server

Ciso Ingest

ciso_ingest

Lists CISO Assistant GRC records by kind and ingests them into the medulla knowledge graph as typed OWL nodes, including evidence documents and attachment blobs.

Instructions

List a CISO Assistant GRC record kind and natively ingest it into medulla.

Maps records to typed OWL nodes (:RiskScenario / :Control / :Audit / :Incident / :Asset / :Vulnerability) or, for evidences, :Document nodes plus attachment blobs. Best-effort — returns {"ingested": null} when no engine is reachable. CONCEPT:AU-KG.ingest.enterprise-source-extractor.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "kind": "<kind>"
    },
    "name": "ciso_ingest"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesGRC record kind to list and ingest into the knowledge graph. One of: 'risk_assessments', 'risk_scenarios', 'applied_controls', 'compliance_assessments', 'incidents', 'assets', 'vulnerabilities', 'evidences'.
params_jsonNoJSON string of list filters (e.g. folder, limit) for the client.{}
ingest_attachmentsNoFor kind='evidences', also store attachment file bytes as :Blob/:MediaAsset.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.3.6

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and mostly succeeds: it discloses the write side effect (creating typed OWL nodes and :Blob/:MediaAsset blobs for attachments), that the operation is best-effort, and the exact degenerate return value {"ingested": null} when no engine is reachable. It stops short of stating idempotency, what happens to previously ingested nodes, or which CISO Assistant connection/auth is used.

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 action and scope are front-loaded, followed by the node mapping and then the failure semantics, and no sentence is purely filler. The trailing 'CONCEPT:AU-KG.ingest.enterprise-source-extractor' token is internal jargon that costs a line without helping an agent decide or call.

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?

For a 3-parameter, annotation-free tool that mutates an external knowledge graph and has no output schema, the description covers destination types and failure behavior but omits re-run/idempotency semantics, source connection/auth expectations, and any sense of return contents on success. Adequate for a first call, not complete for reliable repeated 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?

Schema description coverage is 100%, so the schema already documents kind, params_json, and ingest_attachments with examples. The description adds the kind-to-node-type mapping context, but that largely restates the evidences attachment semantics already in the schema and adds nothing about params_json filters or format.

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?

The description pairs a specific verb with a specific resource: it lists a CISO Assistant GRC record kind and ingests it into the medulla knowledge graph, then names the exact node types produced. That is enough for an agent to distinguish it from the many ciso_assistant_api_*_list/_destroy siblings that only touch the CISO Assistant API and never write to the graph.

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

Usage Guidelines3/5

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

The use case (pull GRC records into the knowledge graph rather than just read them) is implied by 'natively ingest it into medulla', and the evidences/attachment behavior is called out. But there is no explicit guidance on when to choose this over the plain ciso_assistant_api_* list tools, and no prerequisites or exclusions are stated.

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

Deploy Server

Other Tools