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

submit_audit

Submit a third-party skill URL for a behavioral security audit before installing. Returns an audit ID to track progress and avoids duplicate scans.

Instructions

Submit a third-party skill for a behavioral security audit before installing it. Accepts any GitHub or ClawHub URL. Returns an audit_id to track progress. Rate limited: one submission per 60 seconds per IP. Returns existing audit_id if URL was already scanned (deduplicated: true). Use check_audit_status to poll for results.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
skill_urlYesGitHub or ClawHub URL of the skill/repo to audit
notification_emailNoOptional email to notify when audit completes
force_rescanNoBypass deduplication and force a fresh audit

Implementation Reference

  • The async handler that executes the submit_audit tool logic: sends a POST request to /api/submit with the skill_url (and optional notification_email/force_rescan), returns the response as JSON, and handles rate-limiting (429) and other API errors.
    async ({ skill_url, notification_email, force_rescan }) => {
      try {
        const body: Record<string, unknown> = { skill_url };
        if (notification_email) {
          body.notification_email = notification_email;
        }
        if (force_rescan) {
          body.force_rescan = true;
        }
    
        const res = await apiFetch('/api/submit', {
          method: 'POST',
          body: JSON.stringify(body),
        });
    
        const data = (await res.json()) as SubmitResponse;
        return {
          content: [{ type: 'text' as const, text: JSON.stringify(data, null, 2) }],
        };
      } catch (err) {
        if (err instanceof ApiError) {
          if (err.status === 429) {
            return {
              content: [
                {
                  type: 'text' as const,
                  text: 'Rate limited — wait 60 seconds before resubmitting.',
                },
              ],
              isError: true,
            };
          }
          return {
            content: [{ type: 'text' as const, text: err.message }],
            isError: true,
          };
        }
        throw err;
      }
    },
  • Input schema for submit_audit: skill_url (required string), notification_email (optional email string), and force_rescan (optional boolean).
    inputSchema: {
      skill_url: z
        .string()
        .describe('GitHub or ClawHub URL of the skill/repo to audit'),
      notification_email: z
        .string()
        .email()
        .optional()
        .describe('Optional email to notify when audit completes'),
      force_rescan: z
        .boolean()
        .optional()
        .describe('Bypass deduplication and force a fresh audit'),
    },
  • The registerSubmitAudit function that registers the tool with the MCP server using server.registerTool('submit_audit', ...).
    export function registerSubmitAudit(server: McpServer): void {
      server.registerTool(
        'submit_audit',
        {
          description:
            'Submit a third-party skill for a behavioral security audit before installing it. ' +
            'Accepts any GitHub or ClawHub URL. Returns an audit_id to track progress. ' +
            'Rate limited: one submission per 60 seconds per IP. ' +
            'Returns existing audit_id if URL was already scanned (deduplicated: true). ' +
            'Use check_audit_status to poll for results.',
          inputSchema: {
            skill_url: z
              .string()
              .describe('GitHub or ClawHub URL of the skill/repo to audit'),
            notification_email: z
              .string()
              .email()
              .optional()
              .describe('Optional email to notify when audit completes'),
            force_rescan: z
              .boolean()
              .optional()
              .describe('Bypass deduplication and force a fresh audit'),
          },
        },
        async ({ skill_url, notification_email, force_rescan }) => {
          try {
            const body: Record<string, unknown> = { skill_url };
            if (notification_email) {
              body.notification_email = notification_email;
            }
            if (force_rescan) {
              body.force_rescan = true;
            }
    
            const res = await apiFetch('/api/submit', {
              method: 'POST',
              body: JSON.stringify(body),
            });
    
            const data = (await res.json()) as SubmitResponse;
            return {
              content: [{ type: 'text' as const, text: JSON.stringify(data, null, 2) }],
            };
          } catch (err) {
            if (err instanceof ApiError) {
              if (err.status === 429) {
                return {
                  content: [
                    {
                      type: 'text' as const,
                      text: 'Rate limited — wait 60 seconds before resubmitting.',
                    },
                  ],
                  isError: true,
                };
              }
              return {
                content: [{ type: 'text' as const, text: err.message }],
                isError: true,
              };
            }
            throw err;
          }
        },
      );
    }
  • src/index.ts:19-23 (registration)
    Calls registerSubmitAudit(server) to wire up the tool at server startup.
    registerSubmitAudit(server);
    registerCheckStatus(server);
    registerGetReport(server);
    registerGetSummary(server);
    registerSearchAudits(server);
  • SubmitResponse type used by the handler — defines the shape of the API response (audit_id, queue_position, notification_email, deduplicated).
    export interface SubmitResponse {
      audit_id: string;
      queue_position?: number;
      notification_email?: string;
      deduplicated?: boolean;
    }
Behavior5/5

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

No annotations exist, so description fully covers: URL types, return value, rate limit, deduplication, and force rescan option. All relevant behaviors disclosed.

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?

Five dense sentences, each adding distinct info. No wasted words. Front-loaded with purpose.

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?

Covers return value, dedup, rate limit, and sibling tool. Lacks error handling details but sufficient for effective use.

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. Description adds value by explaining deduplication context for force_rescan and rate limit (not in schema).

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 'submit' and resource 'third-party skill for behavioral security audit'. Distinguishes from siblings like check_audit_status.

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?

Explicitly indicates when to use ('before installing'), mentions rate limiting, deduplication, and directs to sibling tool for polling.

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