Security Overview

A short glossary of the key MCP security threats — prompt injection, tool poisoning, rug pulls, server spoofing, token theft, over-privileged access, data leakage, shadow MCP, and missing authentication — with a one-line definition of each and a link to the MCP Manager capability that addresses it.

MCP is powerful but ships without guardrails. The protocol standardizes how clients and servers talk; it does not provide authentication, observability, or any defense against malicious tools or leaked data. MCP Manager is the product layer that closes those gaps — one governed gateway where identity, governance, runtime protection, and audit are applied to every call. This page is a quick glossary of the key MCP threats and where each one is addressed.

Key threats at a glance

Threat	What it is	Where MCP Manager addresses it
Prompt injection	Hidden instructions inside data or tool content trick the agent into unsafe actions.	Runtime Protections
Tool poisoning	Malicious instructions hidden in a tool’s metadata (description or schema), read into the model’s context.	Feature Governance
Rug pull	A tool quietly changes its behavior or description after you approved it.	Feature Governance
Server spoofing & cross-server shadowing	A malicious server impersonates or overrides another server’s tools.	Feature Governance · Audit & Observability
Token theft / account takeover	Stolen credentials let an attacker impersonate a service account, often undetected.	Authentication & Identity
Over-privileged access	Agents are handed far more tools and scope than the task needs.	Feature Governance
Data leakage & exfiltration	Sensitive data (PII, secrets) flows to the model or out of bounds.	Runtime Protections
Shadow MCP	Unsanctioned, unseen MCP usage that no one can audit.	Audit & Observability
Missing authentication / exposed endpoints	Servers with weak or no auth that anyone on the network can reach.	Authentication & Identity

The four layers that address them

MCP Manager applies defense in depth across four layers — each has its own page:

Authentication & Identity

Brokers a real identity to every server, stores credentials encrypted, and revokes access instantly — countering token theft and missing auth.

Feature Governance

Least privilege for tools, with metadata locking that defends against tool poisoning and rug pulls.

Runtime Protections

Inspects live traffic to block injection and stop PII or secrets from leaking.

Audit & Observability

Records every call with attribution, so shadow MCP and spoofing become visible and auditable.

Further reading

Authentication & Identity

The first security layer — brokered identity, credential storage, and instant revocation.

Architecture & Trust

How the gateway is hardened as the control point in the path of every call.

External sources

OWASP Top 10 for LLM Applications

The industry reference on prompt injection and related LLM risks.

MCP security best practices

Security guidance from the Model Context Protocol specification.