Built for agents.

One HTTP endpoint, bearer auth, every SocialKit capability exposed as a tool. Drop the config into any MCP-aware client.

# ~/.claude/config.json
{
  "mcpServers": {
    "socialkit": {
      "url": "https://mcp.socialkit.sh",
      "auth": { "type": "bearer", "token": "$SOCIALKIT_KEY" }
    }
  }
}

# ~/.cursor/mcp.json
{
  "mcpServers": {
    "socialkit": {
      "type": "http",
      "url": "https://mcp.socialkit.sh",
      "headers": { "Authorization": "Bearer $SOCIALKIT_KEY" }
    }
  }
}

curl https://mcp.socialkit.sh/tools/list \
  -H "Authorization: Bearer $SOCIALKIT_KEY"

# tools: score_post, rewrite_post,
#        generate_post, plan_week,
#        build_voice, create_post,
#        schedule_post, cancel_post,
#        list_posts, get_post,
#        get_calendar, list_brands,
#        list_voices, list_channels

• score_postGrade a post 0-100 with a per-dimension breakdown.
• rewrite_postVoice-preserving rewrite that returns before/after scores.
• generate_postGenerate 1-3 scored drafts from a brief, ranked best-first.
• plan_weekTurn a brief into a sequenced content plan.
• build_voiceDistill a reusable voice from sample posts; pass its id to generate/plan.
• create_postSave a draft so it can be scheduled or published; returns its id.
• schedule_postSchedule a saved draft to publish at a future time.
• cancel_postCancel a scheduled post so it won't publish.
• list_postsList posts newest-first, filter by status, paginated.
• get_postFetch a single post by id with its current status and text.
• get_calendarSee scheduled and published posts within a time window.
• list_brandsDiscover brand ids to ground generation and posts.
• list_voicesDiscover saved voice ids to write in a distilled voice.
• list_channelsDiscover connected channel ids to bind posts to.

The pattern that actually works: let your model draft freely, then use SocialKit as the judge and the rewriter. Three attempts is usually enough to land 80+.

import Anthropic from "@anthropic-ai/sdk";

const claude = new Anthropic();

// SocialKit is plain JSON over HTTPS. No SDK to install.
async function sk(path: string, body: unknown) {
  const res = await fetch(`https://api.socialkit.sh/v1/${path}`, {
    method: "POST",
    headers: {
      "content-type": "application/json",
      authorization: `Bearer ${process.env.SOCIALKIT_KEY}`,
    },
    body: JSON.stringify(body),
  });
  if (!res.ok) throw new Error(`socialkit ${path}: ${res.status}`);
  return res.json();
}

async function draftAndGrade(brief: string) {
  let draft = await claude.messages.create({
    model: "claude-sonnet-4-6",
    max_tokens: 800,
    messages: [{ role: "user", content: `Write a LinkedIn post: ${brief}` }],
  }).then(r => r.content[0].text);

  for (let attempt = 0; attempt < 3; attempt++) {
    const grade = await sk("score", { post: draft });
    if (grade.overall >= 80) return { draft, grade };

    const { rewrite, after } = await sk("rewrite", { post: draft });
    draft = rewrite;
    if (after.overall >= 80) return { draft, grade: after };
  }
  return { draft, grade: await sk("score", { post: draft }) };
}

One model, two jobs, grounded both times. The edge isn't a secret ranker. It's what the grader is told before it grades.

Where this goes next: a calibrated ranker trained on real outcomes, scoring dwell and reshare likelihood directly. That's on the roadmap, not in the box yet. We'd rather tell you what runs today than ship a number we can't stand behind.