gmi-security-mcp

Overview Schema Source Related Servers Discussions Admin

draft_private_disclosure

Drafts a private security disclosure in Markdown from a confirmed real finding, refusing low-confidence or unconfirmed cases and writing only when a path and server permission are provided.

Instructions

Draft a private disclosure from a confirmed real finding.

Uses the GitHub Security Lab report template, with the ssh-mcp-server host-key draft as the worked example of the format. Refuses when the verdict is not real, or when confidence is below 0.8 without explicit confirmation. When finding_id is given, the finding must be in the store with status confirmed, or triaged with verdict real and confidence at or above 0.8; otherwise the draft is refused and the result says why. Returns the draft as Markdown and writes it only when write_path is given. It is never sent, never opened as a PR, never forked, never pushed, never emailed. sent is always false. Writing the draft to write_path needs --allow-apply on the server command line; without it the call is refused. When --require-scope is set, the write target must sit inside a repo with scope enabled.

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": {
      "finding": "<finding>",
      "repo": "<repo>"
    },
    "name": "draft_private_disclosure"
  }
}

Input Schema

Name	Required	Description	Default
`repo`	Yes
`db_path`	No
`finding`	Yes
`finding_id`	No
`write_path`	No
`include_fix`	No
`maintainer_contact`	No
`confirm_low_confidence`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.5.11Nov 12, 2026

addedInput schema / properties / db_path

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Db Path"
+}

addedInput schema / properties / finding_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Finding Id"
+}

First observedv0.3.0Nov 10, 2026

TDQS

A4.3/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses that the draft is never sent, opened as a PR, forked, pushed, or emailed, and that sent is always false. It also exposes server-side configuration dependencies (--allow-apply, --require-scope) that determine whether the call succeeds at all, which is exactly the kind of context annotations would normally supply.

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 action and the guardrail, and most sentences carry real information. The negative list (never sent, never opened as a PR, never forked, never pushed, never emailed) partly restates 'sent is always false' and the run-on formatting of the raw text slightly hurts scanability, but there is little true filler.

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

Completeness4/5

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

For an 8-parameter, nested-object tool with no annotations, the description covers the risky paths well and, since an output schema exists, it reasonably stops at noting the draft is Markdown and refusals explain why. The remaining gap is the four undocumented parameters, which an agent must guess at from their names alone.

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 0% across 8 parameters, so the description must compensate and it only partly does. It richly documents finding_id (store membership, status, verdict, confidence threshold) and write_path (write only when given, needs --allow-apply, scope constraint), but include_fix, maintainer_contact, db_path, and repo are left entirely unexplained in both schema and description.

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 first sentence names a specific verb and resource (draft a private disclosure) plus the input constraint (a confirmed real finding), and the second pins the output format to the GitHub Security Lab report template. No sibling tool in the catalog drafts disclosures, so the boundary is unambiguous.

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

Usage Guidelines4/5

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

It states refusal conditions explicitly: verdict not real, confidence below 0.8 without confirmation, finding not in the store with status confirmed, or missing --allow-apply / scope. That is strong when-not guidance. What it does not do is name the prerequisite sibling actions (mark_confirmed, triage_semgrep_finding) that would produce an eligible finding, leaving that inference to the agent.

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

Deploy Server