safeguard-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
SafeGuard MCP server (@the-safeguard-ai/mcp)
A Model Context Protocol server that exposes SafeGuard AI's DLP engine, Secure AI Gateway, and Shadow AI discovery as tools any MCP client (Claude Desktop, Cursor, Windsurf, Claude Code, …) can call. Speaks MCP over stdio.
The point: give an AI agent a governed way to handle and send data. Before an
agent pastes a chunk of text into some external tool, it can dlp_scan it; to
sanitize it, dlp_redact; to ask a model with policy + audit enforced, secure_chat.
Tools
Tool | Needs token? | What it does |
| no | Detect PII/secrets in text; returns findings, counts by type, and whether it would be blocked. Local — no network, no tokens. |
| no | Return a sanitized copy with |
| no | List the detector types SafeGuard recognizes (international by default). Local. |
| yes | Ask an LLM through the gateway — inbound redaction, org policy, routing (cloud/self-hosted), audit log. Returns the reply + redaction count. |
| yes | Summarize which AI tools the org uses and what data was caught on each. Read-only. |
| yes | List the org's active DLP policies as enforced by the gateway. Read-only. |
The three local DLP tools mirror crates/dlp (the Rust source of truth) and run
entirely in-process — no backend required.
Related MCP server: Blekline MCP Server
Configuration (environment)
Var | Default | Purpose |
| (unset) | Bearer token: a user JWT (sign in to SafeGuard) or an org API key ( |
|
| Secure AI Gateway base URL. |
|
| Control-plane (governance API) base URL. |
|
| Default model id for |
|
| Default action for the local DLP tools. |
Run
# from the repo root
bun run mcp
# or directly
bun run services/mcp/src/index.tsstdout is reserved for the MCP protocol; logs go to stderr.
Add to an MCP client
Claude Desktop / Cursor / Windsurf (mcpServers config):
{
"mcpServers": {
"safeguard": {
"command": "bun",
"args": ["run", "/absolute/path/to/safeguard-ai/services/mcp/src/index.ts"],
"env": {
"SAFEGUARD_TOKEN": "<your JWT or sg_… API key>",
"SAFEGUARD_GATEWAY_URL": "http://localhost:8080",
"SAFEGUARD_CONTROL_PLANE_URL": "http://localhost:8081"
}
}
}
}Claude Code:
claude mcp add safeguard --env SAFEGUARD_TOKEN=<token> \
-- bun run /absolute/path/to/safeguard-ai/services/mcp/src/index.tsWithout SAFEGUARD_TOKEN the local DLP tools still work; the gateway and
governance tools return a clear "set SAFEGUARD_TOKEN" message.
Typecheck
bun run typecheckTool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
Agent-native security, trust, reliability, data and procurement tools for AI workflows.
Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
Governed access to sensitive data, secrets and APIs for AI agents. A signed proof for each decision.
Related MCP Servers
- AlicenseAqualityBmaintenanceProtects AI agents from threats like prompt injection, jailbreaks, and SQL injection through a multi-layer scanning pipeline. It also enables PII redaction and rehydration to ensure data privacy during LLM interactions.12215 npm2Apache 2.0

Blekline MCP Serverofficial
AlicenseAqualityCmaintenanceProvides AI ingress governance by masking prompts, classifying risk, and enforcing tool policies before agent calls reach model providers or sandboxes.61AGPL 3.0- AlicenseNot gradedqualityDmaintenanceEnables secure interaction between LLMs and MCP tools by applying zero-trust security controls, including sensitive data masking, file system protection, and policy enforcement.MIT
- FlicenseAqualityNot gradedmaintenanceA data-loss-prevention (DLP) layer for AI agents that intercepts document reads, scans for sensitive data, and redacts or blocks it before it reaches the model, with audit logging.1-