Search
“guardrails”
Showing 1–20 of 20 for “guardrails”
- 0.578score
Healthclaw Guardrails
aks129
Guardrailed FHIR access for AI agents: PHI redaction, audit trail, step-up auth, tenant isolation
ConnectorAFreshness: ARemote★ 31Claude Code +3 - 0.628score
Cost Guard MCP
mcpsmiths
Pre-flight query cost and result-size guardrails for AI agents on BigQuery, Snowflake, Databricks
ConnectorAFreshness: ALocalRead-only★ 1↓ 216/wkClaude Code +5 - 0.586score
Syl Guardian
sylai.io
Causal guardrail: pass/caution/hold verdict on a causal claim before an agent acts.
ConnectorAFreshness: ARemoteClaude Code +3 - 0.525score
LogCarverGuard
caiderek
Guardrail for AI agents on SQL Server: statement blocking, optional read-only mode and an audit log.
ConnectorAFreshness: ALocal★ 1Claude Code +5 - 0.646score
Telegram MCP Server
tolboy
Local-first TDLib Telegram MCP server with 115 tools, account isolation and production guardrails.
ConnectorAFreshness: ALocal★ 10Claude Code +5 - 0.638score
Midplane
midplane.aiOfficial
Safe-by-default SQL guardrails for AI agents: AST-checked queries, per-table policy, audit log.
ConnectorAFreshness: ARemoteLocal★ 5Claude Code +5 - 0.628score
Superuser
fitzyracing1
Permission-gated superuser (sysadmin) MCP agent with enterprise guardrails and audit.
ConnectorAFreshness: ALocal★ 3↓ 125/wkClaude Code +5 - 0.602score
Tracelane MCP
tracelane
Read-only, tenant-scoped access to Tracelane agent traces and guardrail verdicts
ConnectorAFreshness: ALocal★ 1Claude Code +5 - 0.588score
Overwing
overwing.aiOfficial
Guardrails for LLM output: pass / fail / review verdicts and one recommended action.
ConnectorAFreshness: ARemoteLocalClaude Code +5 - 0.520score
Aidimag
AiDimag
Persistent, verified memory for AI coding agents: recall, capture, guardrails, review queue.
ConnectorAFreshness: ALocal★ 1Claude Code +5 - 0.517score
Nemotron 3.5 Content Safety
NVIDIA
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B.
ModelAFreshness: A$0.2 / $0.2131K ctxOpen weights - 0.480score
Aifordatabase MCP
dann26parr69
Query any database in plain English or SQL through a guardrailed, read-only data layer.
ConnectorCFreshness: CLocalClaude Code +5 - 0.468score
Aegis Policy
Evozim
Governance firewall and safety guardrails oracle for AI swarms.
ConnectorCFreshness: CRemoteClaude Code +3 - 0.370score
BrainstormRouter MCP Server
justinjilg
AI routing, memory, guardrails, and governance.
ConnectorDFreshness: DRemoteLocal↓ 10/wkClaude Code +5 - 0.562score
Last Price
last-price.aiOfficial
Compute and verify prices from an agent, metered per call.
ConnectorAFreshness: ARemoteClaude Code +3 - 0.381score
Spotdb
aliengiraffe.ai
Ephemeral data sandbox for AI workflows with guardrails and security
ConnectorFFreshness: FLocal★ 21Claude Code +5 - 0.361score
Anchord (AnchorID)
nolenation04
Read-only MCP for identity resolution and write guardrails.
ConnectorDFreshness: DRemoteLocal↓ 6/wkClaude Code +5 - 0.522score
Guardr
guardr.ioOfficial
Hosted MCP for website health monitoring.
ConnectorBFreshness: BRemoteClaude Code +3 - 0.524score
Suprawall MCP
wiserautomation
SupraWall security gateway for AI agents.
ConnectorCFreshness: CLocal★ 2Claude Code +5 - 0.411score
Guardrly MCP
fishcoco-code
Non-invasive AI Agent monitoring — audit every API call to Shopify, Meta Ads, and more
ConnectorDFreshness: DLocal↓ 19/wkClaude Code +5