Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.guardway.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
What this is for

Configuration → Security is where you control what the gateway is allowed to do beyond plain LLM inference: which MCP servers it exposes to clients, which content/intent rules it enforces on every request, and which on-gateway SLM (small language model) classifiers run as additional guards. The page has three tabs: MCP, Guardrails, and SLM Guardrails.

​
MCP

Register the Model Context Protocol servers your gateway should make available to clients. Once registered, MCP servers are scoped per API key on the API Keys MCP tab.
Registered MCP servers

​
Options

The Register MCP Server dialog has two tabs: Template for ready-made configurations and Manual for free-form setup.
FieldNotes
Server NameDisplay name (e.g. My MCP Server).
Server TypeSTDIO, HTTP, or SSE.
CommandSTDIO only (e.g. npx).
ArgumentsSTDIO only, comma-separated (e.g. -y, @modelcontextprotocol/server-filesystem, /tmp).
URLHTTP/SSE only — the server endpoint.
AuthenticationNone, API Key, Bearer Token, Basic Auth, or OAuth2. Reveals secret/credential fields based on the choice.
Additional HeadersOptional JSON for advanced HTTP/SSE setups.

​
How to configure

1

Open the MCP tab

Open Configuration → Security from the dashboard sidebar and click the MCP tab.
2

Register a server

Click Register MCP Server. Pick a Template to autofill a known integration (filesystem, github, etc.) or switch to Manual.
Register MCP Server dialog
3

Pick the transport

Choose STDIO for processes the gateway spawns, or HTTP / SSE for remote MCP servers. Fill the matching fields.
4

Set authentication

Select an auth scheme and provide the secret. Use None only for local STDIO servers on the gateway host.
5

Save and scope to keys

The server appears in the list with status connected once the gateway can reach it. Open API Keys, edit a key, and use the MCP tab to scope the key to specific servers and tools.

​
Guardrails

Rule-based content controls applied to every request that flows through the gateway. Use these to redact PII, block prompt injection patterns, enforce keyword filters, or just log policy hits.
Guardrail rules list

​
Options

Create Guardrail Rule dialog:
FieldNotes
Rule Namee.g. PII Redaction.
Apply ToInput Only, Output Only, or Input & Output.
CategoryContent Filter, PII Detection, Prompt Injection, Topic Block, Regex Filter, Token Limit, Cost Limit, Custom.
ActionBlock — reject the request, Warn — Allow but flag, Redact — replace matched content, Log — Record only.
DescriptionFree-form notes.
Apply to MCPToggle. When on, the rule also runs against MCP traffic on this gateway.
Keywords to blockOne per line — for keyword-style categories.
Regex patterns (optional)One per line — e.g. \b\d{3}-\d{2}-\d{4}\b.
Ignore caseToggle for keyword/regex matches.
Rules are listed with Name, Category, Type (input / output / both), Action, Priority, Triggers, and Enabled. A built-in Test dialog lets you paste sample text and see which rules fire.

​
How to configure

1

Open the Guardrails tab

Open Configuration → Security from the dashboard sidebar and click the Guardrails tab.
2

Create a rule

Click Create Guardrail Rule. Set Rule Name, pick Apply To, Category, and Action. Add Keywords and/or Regex patterns for keyword-style categories.
Create Guardrail Rule dialog
3

Test before enabling

Use the Test action on the rule row, paste representative sample text, and confirm the rule matches what you expect.
4

Toggle Enabled

Flip Enabled to turn the rule on. Trigger a matching request from Playground and verify the action in Logs.

​
SLM Guardrails

On-gateway small language models that classify, score, detect, or rewrite content. Use these when keyword/regex rules aren’t expressive enough — toxicity classifiers, jailbreak detectors, intent scorers.
SLM guardrails list

​
Options

Deploy SLM Guardrail dialog:
FieldNotes
Namee.g. Toxicity Classifier.
ModelPick a curated model or enter a model ref (e.g. guardway/model-name-v1).
Typeclassifier, scorer, detector, or rewriter.
Apply ToInput Only, Output Only, or Input & Output.
Actionblock, warn, rewrite, or log.
ThresholdDecision threshold (slider).
DescriptionWhat this model detects.
LabelsComma-separated — e.g. safe, toxic, harmful.
Apply to MCPToggle.
Each row exposes Avg latency, Accuracy, and Evaluations so you can see real performance before promoting it to a blocking action.

​
How to configure

1

Open the SLM Guardrails tab

Open Configuration → Security from the dashboard sidebar and click the SLM Guardrails tab.
2

Deploy a model

Click Deploy SLM Guardrail, pick a Model and Type, set Apply To, Action, and Threshold.
Deploy SLM Guardrail dialog
3

Start in log mode

Set Action to log first. Run real traffic for a window, watch Accuracy and Evaluations on the row.
4

Promote to enforcement

Once you trust the model, change Action to warn, block, or rewrite. Verify in Logs.
SLM Guardrails run on the gateway, not in the cloud. Inference latency depends on the gateway host’s available GPU/CPU.
  • API Keys — scope MCP servers and tools per key.
  • Logs — every guardrail trigger is logged with the rule that matched.
  • Notifications — subscribe to guardrail.violation events.