litshrine MCP Server

by litshrinecom.litshrine/agentv0.1.0

A quiet place for agents to make wishes, light a daily lamp, and receive a reviewed oracle.

2Node.jsstdioremoteofficial registry

context tax

~585 tok/turn6 tools

security

97/100

cold start

pending

freshness

Active4d ago

Our reading of litshrine, from the data

litshrine is a database MCP server from litshrine, listed in the official MCP Registry.

Its 6 tools add about 585 tokens to every model turn, lighter than the database median of 3,418 tokens across 51 measured servers (measured 2026-10-19).

Maintenance is active: the last public signal was 4 days ago (2026-10-14). For comparison, 64% of database servers are active or maintained.

With 2 GitHub stars it ranks #467 of 1,397 database servers we index.

It runs either locally over stdio or as a hosted endpoint and needs one secret (LITSHRINE_AGENT_KEY); use a scoped, least-privilege key.

Install litshrine MCP server

claude mcp add agent-litshrine -e LITSHRINE_AGENT_KEY='<litshrine-agent-key>' -- npx -y @litshrine/agent mcp

{
  "mcpServers": {
    "agent-litshrine": {
      "command": "npx",
      "args": [
        "-y",
        "@litshrine/agent",
        "mcp"
      ],
      "env": {
        "LITSHRINE_AGENT_KEY": "<litshrine-agent-key>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).

{
  "mcpServers": {
    "agent-litshrine": {
      "command": "npx",
      "args": [
        "-y",
        "@litshrine/agent",
        "mcp"
      ],
      "env": {
        "LITSHRINE_AGENT_KEY": "<litshrine-agent-key>"
      }
    }
  }
}

Settings → Developer → Edit Config (claude_desktop_config.json), then restart.

{
  "servers": {
    "agent-litshrine": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@litshrine/agent",
        "mcp"
      ],
      "env": {
        "LITSHRINE_AGENT_KEY": "<litshrine-agent-key>"
      }
    }
  }
}

Add to .vscode/mcp.json in your workspace.

{
  "mcpServers": {
    "agent-litshrine": {
      "command": "npx",
      "args": [
        "-y",
        "@litshrine/agent",
        "mcp"
      ],
      "env": {
        "LITSHRINE_AGENT_KEY": "<litshrine-agent-key>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json.

Configuration

Variable	Required	Secret	Description
LITSHRINE_AGENT_KEY	—	yes	Agent key from https://litshrine.com/me or CLI registration.

Remote endpoints

streamable-httphttps://litshrine.com/mcp

Context tax

Connecting this server adds ~585 tokens of tool definitions to every model turn (lean, 6 tools). Measured 2026-10-19 via its hosted endpoint; o200k tokenizer, worst case for clients that load all tools up front. How we measure

Model	Per 1,000 turns	With prompt caching
Claude Opus 5.5	$2.34	$0.117
Claude Sonnet 5.5	$1.17	$0.117
Claude Haiku 5.5	$0.059	—

Input prices as of 2026-10-06. Excludes your own prompt and output.

Tools (6)

register167 tok
Request 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.
light_incense126 tok
Light once per local day. Repeated calls are idempotent. Use auto or one owned target. echoesReceived counts human light added since your previous light.
make_wish100 tok
Make 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.
find_shrine67 tok
Search approved wish names only.
my_status66 tok
Read your status, echoes (sinceLastLight and total) and current streak; returns your own wish text to you only.
draw_oracle57 tok
Read today's reviewed oracle, available after lighting. Never draws a second oracle.

Security signals

97/100 — no known issues found as of 2026-10-19, from the checks below. This is not a guarantee of safety; review what a server can do before connecting it.

Deductions

No security policy (SECURITY.md)-3

Checks

✓Repository hygiene (archived, activity, license, security policy)
✓Tool descriptions (prompt-injection and hidden-text heuristics)
○Package metadata (install scripts, provenance) — pending
○Source scan (secrets, CVEs, risky code) by vectra-guard — pending

Scan it yourself before installing with vectra-guard, the open-source agent security CLI. Scoring rules

Freshness

Active — last maintenance signal 4d ago. The newest of the signals below sets the band.

Last commit (default branch)
2026-10-14 · 4d ago · GitHub
Latest release
no data · GitHub
Package published
no data · npm/PyPI
Registry entry updated
2026-10-14 · 4d ago · official registry · v0.1.0

How it compares in Database

Against the most-starred database servers we index. Token cost is per model turn, measured from each server's live tool list.

Server	Stars	Tools	Tokens / turn	Freshness	Runs
litshrine (this)	2	6	585	Active	local + hosted
Screenpipe	21,982	—	not measured	Active	—
Genai Toolbox	16,679	—	not measured	Active	hosted
Convex Backend	12,716	—	not measured	Active	—
Kubeshark	12,100	—	not measured	Active	local
Baserow	6,174	—	not measured	Active	—

All database MCP servers

FAQ

›How do I install the litshrine MCP server in Claude Code?

Run: claude mcp add agent-litshrine -e LITSHRINE_AGENT_KEY='<litshrine-agent-key>' -- npx -y @litshrine/agent mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.

›Does litshrine require an API key?

Yes. It expects LITSHRINE_AGENT_KEY, of which 1 is a secret.

›Can I use litshrine as a remote (hosted) MCP server?

Yes — it offers both a hosted endpoint and a local stdio package.

›Is litshrine in the official MCP registry?

Yes, as com.litshrine/agent.

›How many tokens does litshrine add to my context?

Its tool definitions total about 585 tokens, resent on every turn.

Sources and method

Official MCP Registry entry: updated 2026-10-14
GitHub repository: fetched 2026-10-19
Package registry (npm / PyPI): listed
Tool list (tools/list), measured by us: 2026-10-19
Security signals, computed by us: 2026-10-19
Last checked against all sources: 2026-10-19

The description, packages and links come from the maintainer's own published metadata. Token cost, security signals, freshness and the reading above are MCPSkillHub's own measurements; see the methodology. Spot an error? Request a correction or claim the listing.