
Storskarvia MCP server
Which MCP servers are Storskarvia'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 2026-10-25
- Registry namecom.storskarvia/writing-studioverified in the MCP registry
The registry name sits under storskarvia.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-25
- Tools10
- Server calls itselfStorskarvia
- Server version1.28.1
- Protocol version2025-06-18
On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 196 ms.
- Its tools do fact-check period details against the year a manuscript states, but not format screenplays in Final Draft, Fountain or Movie Magic.
- Checked on 2 of the 7 days it takes to judge reliability.
Once connected
- Parameters are untyped or undescribed in 5 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 scoreafter a weeka score needs 7 daily checks: 2 so far
- What an agent can do with it1 of 2 use cases
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer505 ms
- Space in an agent's context≈ 1,346 tokensthe definitions of all its tools (10), which an agent carries on every turn
- Tool definitionsA · 92 of 100
- Typed results10 of 10 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 5 of 10
What an agent can do with it
- can do · fact-check period details against the year a manuscript states
- not sure · track character details like eye colour across chapters
- cannot · format screenplays in Final Draft, Fountain or Movie Magic
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 →
get_skarvia_infoWhat Storskarvia is and how it's positioned. A professional writing studio for novelists, screenwriters, and video scriptwriters, staffed by an AI team that fact-checks, researches, and tracks continuity -- but never writes the user's…
list_featuresThe AI staff on Storskarvia and what each member actually does. Source: the "On staff" section of the current landing page.
get_pricingCurrent Storskarvia pricing tiers, features, and monthly fact-check quotas. Built from config.PLANS, the same list /pricing renders from, so this can no longer drift from the page the way it did while it was kept by hand. The founder…
list_guidesTitles, slugs, and URLs of Storskarvia's evergreen craft/how-to guides. Reads the live GUIDES list straight from app.main (imported lazily -- see the comment on the import below) so this can never drift out of sync with what's actually…
get_guideSummary and URL for one guide, looked up by slug. Call list_guides first to get valid slugs.
list_my_projectsThe authenticated user's Storskarvia projects (novels, screenplays, video scripts), each with the id, title and binder folder of its documents in binder order. A document id is what prepare_factcheck and submit_findings take. Requires a…
get_findingsFindings for one of the authenticated user's fact-check or continuity runs. Ownership is enforced -- a check_id belonging to another user raises an error rather than leaking their data.
prepare_factcheckStep 1 of a bring-your-own-agent fact-check. Fetches one of the authenticated user's documents (ownership enforced) plus the exact disclosure and method your agent MUST follow. Requires a personal Storskarvia API key as a Bearer token…
ground_claimStep 2 of a bring-your-own-agent fact-check. Runs Storskarvia's own server-side retrieval (Wikipedia + searxng) for one claim and returns the sources -- no verdict, no judgment. Your agent should judge the claim ONLY against these…
submit_findingsStep 3 of a bring-your-own-agent fact-check. Stores your agent's findings as a real Storskarvia Check, visible on the same findings punch list as a staff-run check. Requires a personal Storskarvia API key as a Bearer token, and ownership…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"writing-studio": {
"type": "http",
"url": "https://storskarvia.com/mcp/"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http storskarvia https://storskarvia.com/mcp/claude.ai, ChatGPT and other clients: add https://storskarvia.com/mcp/ as a custom connector in the settings.
OpenAPI spec
163 paths, read 2026-10-25. Open the spec ↗
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.