Skip to main content
Glama
oathe-ai
by oathe-ai

get_audit_report

Retrieve the full behavioral security audit report for a GitHub repository. Review trust score, verdict, findings, and recommendations before installing a third-party MCP server, plugin, or tool.

Instructions

Get the full behavioral security audit report for a GitHub repository. Use this to review all findings before installing a third-party MCP server, plugin, or tool. Returns the latest completed audit with trust score, verdict, findings, category scores, and recommendation. Use get_skill_summary for a quick safety check instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ownerYesGitHub repository owner (e.g. "anthropics")
repoYesGitHub repository name (e.g. "claude-code")

Implementation Reference

  • The handler function that executes the 'get_audit_report' tool logic. It calls registerTool with the tool name, inputSchema, and an async callback that fetches the report from /api/skill/{slug}/latest, returning the SkillReport JSON or an error message.
    export function registerGetReport(server: McpServer): void {
      server.registerTool(
        'get_audit_report',
        {
          description:
            'Get the full behavioral security audit report for a GitHub repository. ' +
            'Use this to review all findings before installing a third-party MCP server, plugin, or tool. ' +
            'Returns the latest completed audit with trust score, verdict, findings, ' +
            'category scores, and recommendation. ' +
            'Use get_skill_summary for a quick safety check instead.',
          inputSchema: {
            owner: z.string().describe('GitHub repository owner (e.g. "anthropics")'),
            repo: z.string().describe('GitHub repository name (e.g. "claude-code")'),
          },
        },
        async ({ owner, repo }) => {
          const slug = `${owner}/${repo}`;
          try {
            const res = await apiFetch(`/api/skill/${slug}/latest`);
            const data = (await res.json()) as { report: SkillReport };
            return {
              content: [
                { type: 'text' as const, text: JSON.stringify(data.report, null, 2) },
              ],
            };
          } catch (err) {
            if (err instanceof ApiError) {
              if (err.status === 404) {
                return {
                  content: [
                    {
                      type: 'text' as const,
                      text: `No completed audit found for ${owner}/${repo}.`,
                    },
                  ],
                  isError: true,
                };
              }
              return {
                content: [{ type: 'text' as const, text: err.message }],
                isError: true,
              };
            }
            throw err;
          }
        },
      );
    }
  • Input schema for the 'get_audit_report' tool, defining two required parameters: owner (GitHub repo owner) and repo (GitHub repo name), both validated as Zod strings.
    inputSchema: {
      owner: z.string().describe('GitHub repository owner (e.g. "anthropics")'),
      repo: z.string().describe('GitHub repository name (e.g. "claude-code")'),
    },
  • src/index.ts:21-23 (registration)
    Registration of the 'get_audit_report' tool by calling registerGetReport(server) in the main entry point.
    registerGetReport(server);
    registerGetSummary(server);
    registerSearchAudits(server);
  • src/index.ts:6-7 (registration)
    Import of the registerGetReport function from the get-report tool module into the main entry point.
    import { registerGetReport } from './tools/get-report.js';
    import { registerGetSummary } from './tools/get-summary.js';
  • The apiFetch helper used by the handler to make HTTP requests to the Oathe API. Handles timeouts, network errors, and non-OK responses.
    export async function apiFetch(
      path: string,
      init?: RequestInit,
    ): Promise<Response> {
      const url = `${BASE_URL}${path}`;
    
      let res: Response;
      try {
        res = await fetch(url, {
          ...init,
          signal: init?.signal ?? AbortSignal.timeout(30_000),
          headers: {
            'Content-Type': 'application/json',
            ...init?.headers,
          },
        });
      } catch (err: unknown) {
        if (err instanceof DOMException && err.name === 'TimeoutError') {
          throw new ApiError(
            'Request timed out after 30 seconds. The API may be temporarily unavailable.',
            0,
          );
        }
        if (err instanceof TypeError) {
          throw new ApiError(
            `Network error: unable to reach API at ${BASE_URL}. Check your connection or OATHE_API_BASE setting.`,
            0,
          );
        }
        throw err;
      }
    
      if (!res.ok) {
        const body = await res.json().catch(() => ({}));
        const message = body.message ?? body.error ?? 'Unknown error';
        throw new ApiError(message, res.status);
      }
    
      return res;
    }
Behavior3/5

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

No annotations provided. Description describes return content (trust score, verdict, etc.) but does not disclose behavioral traits like authentication requirements, rate limits, or non-destructive nature beyond the implicit 'get'.

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?

Two sentences with purpose first, no redundant words, and a clear alternative suggestion. Every sentence earns its place.

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?

Despite no output schema, the description fully enumerates the return values (trust score, verdict, findings, category scores, recommendation). Covers all needed context for a moderate-complexity tool.

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 coverage is 100% with clear descriptions for both parameters. The description adds no meaning beyond the schema, meeting baseline expectation.

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?

Clearly states verb 'Get', resource 'full behavioral security audit report', and context 'for a GitHub repository'. Distinct from sibling tool 'get_skill_summary'.

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?

Explicitly states when to use: 'review all findings before installing a third-party MCP server, plugin, or tool'. Also suggests alternative 'get_skill_summary' for quick checks. Lacks explicit when-not conditions.

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/oathe-ai/oathe-mcp'

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