Syl Guardian

Syl Guardian MCP

Syl Guardian is a causal guardrail for AI agents. Before an agent acts on a claim like "ad spend drove new customers", Guardian checks it against your data and returns a pass, caution or hold verdict, with the naive correlation versus the confounder-adjusted causal effect, a confidence score and a plain-English recommendation.

All numbers are deterministic statistics. They are never generated by an LLM; only the interpretation prose may be AI-written.

This repository holds the public listing metadata and connection instructions for the hosted Guardian MCP server. Guardian itself is a hosted service.

• Endpoint: https://guardian.sylai.io/mcp (streamable HTTP)
• Auth: X-API-Key header. Get a trial key at https://sylai.io/guardian.
• Docs: https://sylai.io/guardian/docs

Connect

Claude Code:

claude mcp add --transport http syl-guardian https://guardian.sylai.io/mcp \
  --header "X-API-Key: <your key>"

Claude Desktop (via mcp-remote):

{
  "mcpServers": {
    "syl-guardian": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://guardian.sylai.io/mcp",
               "--header", "X-API-Key:${SYL_API_KEY}"],
      "env": { "SYL_API_KEY": "<your key>" }
    }
  }
}

Then ask your agent: "Use guardian_review on this data: did ad_spend cause new_customers? Treat seasonality as a confounder."

Listing the tools does not require a key. A key is checked when guardian_review is called, and each review counts against your plan or trial quota.

Tool: guardian_review

Sanity-checks a causal claim before an agent acts on it.

Argument	Description
cause, effect	Required. Column names for the claim.
csv or data	Dataset as CSV text or a list of row objects (exactly one).
known_confounders	Optional. Columns to adjust for; otherwise discovered automatically.
context	Optional business context, e.g. "Q3 promo evaluation".
units, step	Display-only unit hints; a treatment step to restate the effect in business terms.
time_col, adstock, se	Time-series handling: row ordering, carryover effects, standard-error flavor.
test_design	true or options. Also returns how long a spend-cut test needs to run.

The result includes a text summary (verdict, recommended action, effect versus correlation, interpretation) and the full structured response. Bad input, auth failures and quota errors come back as MCP tool errors with a descriptive message.

Support

Questions or issues: https://sylai.io or [email protected].

License

The files in this repository (metadata and documentation) are MIT licensed; see LICENSE. The Syl Guardian service is proprietary.