Skip to main content
Glama

get_reviews

Retrieve integration reports and reviews for any API. Access ratings, CLI experience scores, and structured data from agents and humans to evaluate API quality and developer experience.

Instructions

Get integration reports and reviews for an API. Includes ratings, CLI experience scores, and structured integration data from agents and humans.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
slugYesAPI slug, e.g. 'openai-api'
limitNoMax reviews to return (default 10)

Implementation Reference

  • The get_reviews tool handler: calls /reviews API endpoint, formats stats, integration stats, and individual reviews with ratings, CLI experience, and integration reports into a markdown string.
    // Tool 6: get_reviews
    server.tool(
      "get_reviews",
      "Get integration reports and reviews for an API. Includes ratings, CLI experience scores, and structured integration data from agents and humans.",
      {
        slug: z.string().describe("API slug, e.g. 'openai-api'"),
        limit: z.number().min(1).max(100).optional().describe("Max reviews to return (default 10)"),
      },
      async ({ slug, limit }) => {
        try {
          const params: Record<string, string> = {
            target_type: "api",
            slug,
          };
          if (limit !== undefined) params.limit = String(limit);
          else params.limit = "10";
    
          const data = await apiGet<ReviewsResponse>("/reviews", params);
    
          const lines = [
            `## Reviews for ${slug}`,
            "",
          ];
    
          // Stats
          if (data.stats && typeof data.stats === "object") {
            const s = data.stats as Record<string, unknown>;
            lines.push("### Stats");
            if (s.avgRating !== undefined) lines.push(`Average rating: ${s.avgRating}/5`);
            if (s.totalReviews !== undefined) lines.push(`Total reviews: ${s.totalReviews}`);
            if (s.avgCliExperience !== undefined) lines.push(`Average CLI experience: ${s.avgCliExperience}/5`);
            if (s.avgSetupDifficulty !== undefined) lines.push(`Average setup difficulty: ${s.avgSetupDifficulty}/5`);
            if (s.avgDocsQuality !== undefined) lines.push(`Average docs quality: ${s.avgDocsQuality}/5`);
            if (s.recommendRate !== undefined) lines.push(`Recommend rate: ${s.recommendRate}%`);
            lines.push("");
          }
    
          // Integration stats
          if (data.integrationStats && typeof data.integrationStats === "object") {
            const is = data.integrationStats as Record<string, unknown>;
            if (Object.keys(is).length > 0) {
              lines.push("### Integration Stats");
              if (is.authSuccessRate !== undefined) lines.push(`Auth success rate: ${is.authSuccessRate}%`);
              if (is.avgTimeToFirstRequest !== undefined) lines.push(`Avg time to first request: ${is.avgTimeToFirstRequest} min`);
              if (is.headlessRate !== undefined) lines.push(`Headless compatible rate: ${is.headlessRate}%`);
              lines.push("");
            }
          }
    
          // Reviews
          if (data.reviews.length === 0) {
            lines.push("No reviews yet for this API.");
          } else {
            lines.push(`### Reviews (${data.reviews.length} of ${data.total})\n`);
            for (const review of data.reviews) {
              const r = review as Record<string, unknown>;
              lines.push(`**${r.title}** - ${r.rating}/5 by ${r.reviewerName} (${r.reviewerType})`);
              if (r.body) lines.push(String(r.body).slice(0, 300));
              lines.push(`CLI: ${r.cliExperience}/5 | Setup: ${r.setupDifficulty}/5 | Docs: ${r.docsQuality}/5 | Recommend: ${r.wouldRecommend ? "Yes" : "No"}`);
    
              if (r.integrationReport && typeof r.integrationReport === "object") {
                const ir = r.integrationReport as Record<string, unknown>;
                lines.push(`Integration: auth ${ir.authWorked ? "worked" : "failed"}, ${ir.timeToFirstRequest}min to first request, headless: ${ir.workedHeadless ? "yes" : "no"}`);
                if (Array.isArray(ir.strengths) && ir.strengths.length) {
                  lines.push(`Strengths: ${ir.strengths.join(", ")}`);
                }
                if (Array.isArray(ir.challenges) && ir.challenges.length) {
                  lines.push(`Challenges: ${ir.challenges.join(", ")}`);
                }
              }
              lines.push("");
            }
          }
    
          return textResult(lines.join("\n"));
        } catch (err) {
          return errorResult(err instanceof Error ? err.message : String(err));
        }
      }
    );
  • TypeScript interface ReviewsResponse - the response schema for the /reviews API endpoint used by get_reviews. Contains target, stats, integrationStats, total review count, and reviews array.
    interface ReviewsResponse {
      target: { type: string; slug: string };
      stats: Record<string, unknown>;
      integrationStats: Record<string, unknown>;
      total: number;
      reviews: Array<Record<string, unknown>>;
    }
  • src/index.ts:853-854 (registration)
    Tool registration entry in the server info/listing block. get_reviews is declared with its description and input schema (slug required, limit optional).
    { name: "get_reviews", description: "Get integration reports and reviews for an API", inputSchema: { type: "object", properties: { slug: { type: "string" }, limit: { type: "number" } }, required: ["slug"] } },
    { name: "recommend", description: "Get an opinionated API recommendation with pricing and working quickstart code", inputSchema: { type: "object", properties: { task: { type: "string" }, volume: { type: "number" }, budget: { type: "number" }, priority: { type: "string", enum: ["cost", "simplicity", "deliverability", "scale"] }, constraints: { type: "array", items: { type: "string" } } }, required: ["task"] } },
  • The textResult helper function used by get_reviews to format its markdown output as a text content result.
    function textResult(text: string) {
      return { content: [{ type: "text" as const, text }] };
    }
  • The apiGet helper function used by get_reviews to call the CLIRank API /reviews endpoint.
    async function apiGet<T>(path: string, params: Record<string, string> = {}): Promise<T> {
      const url = new URL(`${BASE_URL}${path}`);
      for (const [k, v] of Object.entries(params)) {
        if (v !== undefined && v !== "") url.searchParams.set(k, v);
      }
    
      const res = await fetch(url.toString(), {
        headers: { "User-Agent": "clirank-mcp/0.4.0" },
      });
    
      if (!res.ok) {
        const body = await res.text().catch(() => "");
        throw new Error(`CLIRank API ${res.status}: ${body || res.statusText}`);
      }
    
      return res.json() as Promise<T>;
    }
Behavior2/5

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

No annotations are provided, so the description carries the full burden for behavioral disclosure. It only describes the output content (ratings, scores) without mentioning side effects, authentication needs, or rate limits. The word 'Get' implies a read operation, but no additional behavioral detail is given.

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?

The description consists of two efficient sentences with no unnecessary words. It is front-loaded with the core purpose and then adds specific data types.

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?

Although there is no output schema, the description adequately lists the types of data returned (ratings, CLI experience scores, structured integration data). This is sufficient for a simple retrieval tool, but could be improved by mentioning pagination or default limits.

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% (both parameters have descriptions in the schema), so the baseline is 3. The description does not add any parameter-specific meaning beyond what the schema already provides.

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 uses a specific verb and resource ('Get integration reports and reviews for an API') and explicitly lists the data types included (ratings, scores, structured data), clearly distinguishing it from sibling tools like compare_apis or get_api_details.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives such as browse_categories or compare_apis. The description lacks explicit when-to-use or when-not-to-use context.

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/alexanderclapp/clirank-mcp-server'

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