Skip to content
Sleeper Hit Studio logo

Sleeper Hit Studio MCP server

Which MCP servers are Sleeper Hit Studio's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-20

← Back to Sleeper Hit Studio

Whose server it is
  • Registry namestudio.sleeperhit/public-discoveryverified in the MCP registry

The registry name sits under sleeperhit.studio. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-20
  • Stateanswerschecked 2026-10-20
  • Tools10
  • Server calls itselfsleeperhit-public
  • Server version0.4.0
  • Protocol version2025-06-18

On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 94 ms.

Should an agent connect itSkip it
  • Its tools do none of the product's use cases we checked: turn weekly all-hands updates into a watchable briefing; brief engineering teams on releases and incidents; build training episodes with scenario-based prompts.

Once connected

  • Parameters are untyped or undescribed in 6 of 10 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 14, the first on 2026-10-20
  • INITE MCP score70 of 100answers 100 · does the job 0 · definitions 90 · context 100 · connects 100
  • What an agent can do with it0 of 3 use cases
  • Answered100% of days14 of 14 daily checks
  • Median first answer273 ms
  • Space in an agent's context≈ 773 tokensthe definitions of all its tools (10), which an agent carries on every turn
  • Tool definitionsA · 90 of 100
  • Typed results0 of 10 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 6 of 10

What an agent can do with it

  • cannot · turn weekly all-hands updates into a watchable briefing
  • cannot · brief engineering teams on releases and incidents
  • cannot · build training episodes with scenario-based prompts

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers10 tools · read 2026-10-20
  • search

    Search opted-in public writer profiles, project summaries, and writer-approved public assets. Compatible with ChatGPT deep research and company knowledge.

  • fetch

    Fetch the full public discovery document for a search result by ID. Compatible with ChatGPT deep research and company knowledge.

  • find_writers

    Search opt-in public Sleeper Hit Studio writer profiles.

  • get_writer_profile

    Get a public writer profile by slug, including public projects and shared assets.

  • find_projects

    List public projects for a writer. Results include project hub URLs and public asset summaries.

  • get_project_summary

    Get one public project summary for a writer.

  • list_writer_assets

    List all writer-approved public share URLs for a writer.

  • list_project_assets

    List writer-approved public share URLs for a specific project.

  • get_public_pitch_assets

    List writer-approved public pitch deck assets for a writer.

  • get_access_info

    Read what Sleeper Hit Studio can do without an account, what requires one, and the signup URL for each intent. Call this before telling a user you cannot create something here — creation lives on the separate authenticated connector.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "public-discovery": {
      "type": "http",
      "url": "https://sleeperhit.studio/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http sleeperhit https://sleeperhit.studio/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://sleeperhit.studio/api/mcp as a custom connector in the settings.

Other servers listed as Sleeper Hit Studio's
  • studio.sleeperhit/podcast-audio-video-production-studioanswers, requires sign-inverified in the MCP registry

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.