Skip to main content
Glama
123Ergo

unphurl-mcp

create_profile

Create a custom scoring profile for URL risk assessment by overriding weights on specific signals, such as parked or brand_impersonation, to tailor detection for your use case.

Instructions

Create or update a custom scoring profile. Profiles are sparse overrides: only specify the weights you want to change. Everything else keeps its default value.

If a profile with this name already exists, it is updated with the new weights (full replacement, not merge).

Weights are points, not percentages. Each weight is the number of points that signal adds to the score when it fires. They don't need to total 100. A profile with weights totalling 90 is conservative (max possible score is 90). A profile with weights totalling 130 is aggressive (multiple signals quickly push to the cap of 100). The threshold the agent sets for action matters more than the weight totals.

Use show_defaults to see all 25 signals with their default weights and descriptions before creating a profile. Use check_url or check_urls with the "profile" parameter to score results with this profile.

Maximum 20 profiles per account. Profile name "default" is reserved.

Common profiles:

  • Cold email: weight parked (30), chain_incomplete (25), ssl_invalid (15) higher. Lower brand_impersonation (10).

  • Security bot: keep brand_impersonation high (40), increase domain_age_7 (30), redirects_5 (25).

  • Lead gen: weight parked (35), http_only (20), chain_incomplete (20) for dead business detection.

  • SEO audit: weight redirects_5 (30), chain_incomplete (30), parked (25) for link quality.

See the Unphurl API documentation for all 19 use case weight examples.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesProfile name (lowercase alphanumeric and hyphens only, 1-50 chars, e.g. 'cold-email', 'security-bot')
weightsYesCustom weights for scoring signals. Only include signals you want to override. Available signals: brand_impersonation (default 40), domain_age_3 (35), domain_age_7 (25), domain_age_30 (15), domain_age_90 (5), ssl_invalid (10), http_only (5), redirects_3 (10), redirects_5 (25), chain_incomplete (15), parked (10), compound (10), brand_impersonation_floor (80), url_long (3), path_deep (3), subdomain_deep (3), subdomain_excessive (5), domain_entropy_high (5), url_contains_ip (10), encoded_hostname (5), tld_redirect_change (5), js_fragment_redirect (25), expiring_soon (10), domain_status_bad (15), no_mx_record (5).

Implementation Reference

  • Registration of the 'create_profile' tool on the MCP server via server.registerTool()
      // --- create_profile ---
      server.registerTool(
        "create_profile",
        {
          description: `Create or update a custom scoring profile. Profiles are sparse overrides: only specify the weights you want to change. Everything else keeps its default value.
    
    If a profile with this name already exists, it is updated with the new weights (full replacement, not merge).
    
    Weights are points, not percentages. Each weight is the number of points that signal adds to the score when it fires. They don't need to total 100. A profile with weights totalling 90 is conservative (max possible score is 90). A profile with weights totalling 130 is aggressive (multiple signals quickly push to the cap of 100). The threshold the agent sets for action matters more than the weight totals.
    
    Use show_defaults to see all 25 signals with their default weights and descriptions before creating a profile. Use check_url or check_urls with the "profile" parameter to score results with this profile.
    
    Maximum 20 profiles per account. Profile name "default" is reserved.
    
    Common profiles:
    - Cold email: weight parked (30), chain_incomplete (25), ssl_invalid (15) higher. Lower brand_impersonation (10).
    - Security bot: keep brand_impersonation high (40), increase domain_age_7 (30), redirects_5 (25).
    - Lead gen: weight parked (35), http_only (20), chain_incomplete (20) for dead business detection.
    - SEO audit: weight redirects_5 (30), chain_incomplete (30), parked (25) for link quality.
    
    See the Unphurl API documentation for all 19 use case weight examples.`,
          inputSchema: {
            name: z
              .string()
              .regex(/^[a-z0-9][a-z0-9-]{0,48}[a-z0-9]$|^[a-z0-9]$/)
              .describe(
                "Profile name (lowercase alphanumeric and hyphens only, 1-50 chars, e.g. 'cold-email', 'security-bot')"
              ),
            weights: z
              .record(z.string(), z.number().int().min(0).max(1000))
              .describe(
                "Custom weights for scoring signals. Only include signals you want to override. Available signals: brand_impersonation (default 40), domain_age_3 (35), domain_age_7 (25), domain_age_30 (15), domain_age_90 (5), ssl_invalid (10), http_only (5), redirects_3 (10), redirects_5 (25), chain_incomplete (15), parked (10), compound (10), brand_impersonation_floor (80), url_long (3), path_deep (3), subdomain_deep (3), subdomain_excessive (5), domain_entropy_high (5), url_contains_ip (10), encoded_hostname (5), tld_redirect_change (5), js_fragment_redirect (25), expiring_soon (10), domain_status_bad (15), no_mx_record (5)."
              ),
          },
        },
        async ({ name, weights }) => {
          if (!api.hasApiKey) return authError();
    
          try {
            const result = await api.createProfile(name, weights);
            return successResult(result);
          } catch (err) {
            if (err instanceof ApiRequestError) return apiErrorToResult(err);
            return errorResult(err instanceof Error ? err.message : "Unknown error");
          }
        }
      );
  • Handler function that executes the create_profile tool logic — calls api.createProfile(name, weights)
    async ({ name, weights }) => {
      if (!api.hasApiKey) return authError();
    
      try {
        const result = await api.createProfile(name, weights);
        return successResult(result);
      } catch (err) {
        if (err instanceof ApiRequestError) return apiErrorToResult(err);
        return errorResult(err instanceof Error ? err.message : "Unknown error");
      }
    }
  • Input schema for create_profile: 'name' (regex-validated string) and 'weights' (record of string to int 0-1000)
    inputSchema: {
      name: z
        .string()
        .regex(/^[a-z0-9][a-z0-9-]{0,48}[a-z0-9]$|^[a-z0-9]$/)
        .describe(
          "Profile name (lowercase alphanumeric and hyphens only, 1-50 chars, e.g. 'cold-email', 'security-bot')"
        ),
      weights: z
        .record(z.string(), z.number().int().min(0).max(1000))
        .describe(
          "Custom weights for scoring signals. Only include signals you want to override. Available signals: brand_impersonation (default 40), domain_age_3 (35), domain_age_7 (25), domain_age_30 (15), domain_age_90 (5), ssl_invalid (10), http_only (5), redirects_3 (10), redirects_5 (25), chain_incomplete (15), parked (10), compound (10), brand_impersonation_floor (80), url_long (3), path_deep (3), subdomain_deep (3), subdomain_excessive (5), domain_entropy_high (5), url_contains_ip (10), encoded_hostname (5), tld_redirect_change (5), js_fragment_redirect (25), expiring_soon (10), domain_status_bad (15), no_mx_record (5)."
        ),
    },
  • API client method that sends POST /v1/profiles with name and weights to create/update a profile
    async createProfile(
      name: string,
      weights: Record<string, number>
    ): Promise<Profile> {
      return this.doRequest<Profile>("POST", "/v1/profiles", { name, weights });
    }
  • src/index.ts:37-37 (registration)
    Top-level registration call that wires registerProfileTools (which includes create_profile) into the MCP server
    registerProfileTools(server, api); // list_profiles, create_profile, delete_profile, show_defaults
Behavior5/5

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

With no annotations, the description fully discloses behavioral traits: full replacement on update, max 20 profiles, reserved name 'default', weights are points not percentages, and scoring implications.

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?

Well-structured with clear sections and front-loaded purpose. Slightly long but every sentence adds value; could be slightly more concise but still effective.

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?

Given complexity (nested weights, no output schema), the description covers all necessary context: behavior, constraints, usage with other tools, and examples. Complete for agent decision-making.

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%, but the description adds significant value by explaining weights as points, their effect on scoring, and giving concrete profile examples. Enhances understanding beyond 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?

The description clearly states the tool creates or updates a custom scoring profile, defines what a profile is (weights for signals), and distinguishes from sibling tools like delete_profile and list_profiles.

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?

Provides explicit guidance: use show_defaults to preview signals, use check_urls with profile to score, clarifies sparse overrides and update behavior. Also includes common profile examples and refers to API docs.

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/123Ergo/unphurl-mcp'

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