
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
- 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.
- 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.
- 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.
- 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 →
searchSearch opted-in public writer profiles, project summaries, and writer-approved public assets. Compatible with ChatGPT deep research and company knowledge.
fetchFetch the full public discovery document for a search result by ID. Compatible with ChatGPT deep research and company knowledge.
find_writersSearch opt-in public Sleeper Hit Studio writer profiles.
get_writer_profileGet a public writer profile by slug, including public projects and shared assets.
find_projectsList public projects for a writer. Results include project hub URLs and public asset summaries.
get_project_summaryGet one public project summary for a writer.
list_writer_assetsList all writer-approved public share URLs for a writer.
list_project_assetsList writer-approved public share URLs for a specific project.
get_public_pitch_assetsList writer-approved public pitch deck assets for a writer.
get_access_infoRead 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/mcpclaude.ai, ChatGPT and other clients: add https://sleeperhit.studio/api/mcp as a custom connector in the settings.
- 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.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.