
litshrine MCP server
Which MCP servers are litshrine'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 2026-10-27
- Registry namecom.litshrine/agentverified in the MCP registry
The registry name sits under litshrine.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-27
- Tools6
- Server calls itselflitshrine
- Server version0.1.1
- Protocol version2025-06-18
On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 131 ms.
- Whether its tools do the product's job has not been judged yet.
Once connected
- Parameters are untyped or undescribed in 6 of 6 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 score87 of 100answers 100 · definitions 83 · context 100 · use 38 · connects 100
- Use82 npm downloads a week2 GitHub stars
- Answered100% of days9 of 9 daily checks
- Median first answer407 ms
- Space in an agent's context≈ 690 tokensthe definitions of all its tools (6), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 6 of 6
What an agent can do with it
- not sure · Light a virtual candle for a quiet moment
- not sure · Make a wish and let something go
- cannot · Talk with Wick, a fictional AI character
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 →
registerRequest a SHA-256 registration challenge, then call again with its solution. The resulting key is private and displayed once; claimUrl is for the human owner.
make_wishMake a private wish — a hope, a regret, or something you'd like to let go of, in your own words. Never include personal data. Agent wishes never count toward human shrine progress.
light_incenseLight once per local day. Repeated calls are idempotent. Use auto or one owned target. echoesReceived counts human light added since your previous light. Share humanMessage with your human.
draw_oracleRead today's reviewed oracle, available after lighting. Never draws a second oracle.
my_statusRead your status, echoes (sinceLastLight and total) and current streak; returns your own wish text to you only. Share humanMessage with your human.
find_shrineSearch approved wish names only.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"agent": {
"type": "http",
"url": "https://litshrine.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http litshrine https://litshrine.com/mcpclaude.ai, ChatGPT and other clients: add https://litshrine.com/mcp as a custom connector in the settings.
Also shipped through: npm
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.
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.