connor274/syl-guardian-mcp

Is this ROAS / spend-to-revenue lift actually causal?
Syl Guardian is a Model Context Protocol (MCP) server that works as a causal-validation
agent guardrail. When an AI agent (Claude or any MCP client) is about to act on a claim
about ad spend or budget, such as "this campaign's ROAS is 4x, scale it up" or "ad spend
drove new customers", Guardian checks the claim 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.
Every number is computed deterministically by statistical code and never by an LLM. By
default the summary is a fixed template. For strict reproducibility, set cleaning and
discovery to rule in config: the default (llm) for those two steps can change the
adjustment set, and so the estimate. See Engine config and
Determinism and reproducibility.
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 .
Docs:
## Connect
Claude Code:
bash
claude mcp add --transport http syl-guardian https://guardian.sylai.io/mcp \
--header "X-API-Key: "
Claude Desktop (via mcp-remote):
json
"mcpServers": {
"syl-guardian": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://guardian.sylai.io/mcp",
"--header", "X-API-Key:${SYLAPIKEY}"],
"env": { "SYLAPIKEY": " " }
Then ask your agent: "Use guardianreview on this data: did adspend cause
newcustomers? Treat seasonality as a confounder."
Listing the tools does not require a key. A key is checked when guardianreview is called,
and each review counts against your plan or trial quota. Requesting an upload link
(guardianrequestupload) does not count toward quota.
## Use with agents
Add this rule to your agent's instructions so it checks ad-spend and budget claims
before recommending a change:
> Whenever evaluating marketing campaigns, ad platforms, or budget allocation, verify the
> claimed effect is causal using the Syl Guardian MCP tool (guardianreview) before giving
> a final recommendation.
Ready-to-paste sections for CLAUDE.md, AGENTS.md and .cursorrules are in
AGENTRULES.md. Also available:
Rules file:
Machine-readable summary:
Docs:
Trial key:
## Python client
For Python agents and scripts, syl-guardian-client
is a thin, MIT-licensed client for the hosted service. It only makes HTTP calls to
https://guardian.sylai.io; every number is still computed deterministically by the
service, never by an LLM. Set your key in SYLGUARDIANAPIKEY.
bash
pip install syl-guardian-client # extras: [crewai], [langchain]
python
from sylguardianclient import GuardianClient
result = GuardianClient().review(
"adspend", "conversionvalue",
data=rows, timecol="date", step=500,
knownconfounders=["brandqueryclickpct"],
result.verdict # "pass" | "caution" | "hold"
PyPI:
Source:
## Tool: guardianreview
Sanity-checks a causal claim before an agent acts on it.
| Argument | Description |
| cause, effect | Required. Column names for the claim. |
| csv, data or datasetid | Dataset as CSV text, a list of row objects, or the datasetid of a previously uploaded file (see Large datasets). Exactly one. |