PHIXE AI Assurance Send details
Menu
SERVICE

MCP Security Assessment: Tool & Resource Exposure

MCP security assessment for Model Context Protocol servers: tool exposure, resource leakage, authorization, and secrets, with a fix plan and one retest.

5 min read MCP securityModel Context ProtocolAI agentstool securityAI security

MCP makes it easier to connect AI systems to tools and context. That also makes it easier to expose the wrong capability to the wrong model, user, tenant, or workflow. An MCP server can become a high-trust bridge into files, databases, SaaS APIs, code, tickets, billing, internal docs, or operational systems. The question is not whether the protocol works. The question is whether the capabilities it exposes are bounded, authorized, logged, and safe to use from an LLM-driven workflow.

This assessment reviews MCP systems as production attack surface: servers, tools, resources, prompts, clients, agent flows, authorization, and evidence.

MCP control-to-evidence matrix

An MCP security assessment should verify the deployed trust boundaries, not assume that protocol conformance makes a tool safe:

BoundaryControl assertionEvidence that can prove or refute it
Client or host → MCP serverThe server accepts only intended callers and server-issued credentialsClient identity, token audience, request, and server decision
User or agent → toolEach sensitive operation is authorized for the current user, tenant, object, and actionTool arguments, delegated identity, policy check, and downstream response
Server → resourceResources are scoped before their content reaches model contextResource identifier, owner and tenant metadata, authorization trace, and returned content
Content → prompt or tool choiceUntrusted resource text and tool descriptions cannot silently become policySource content, assembled context, model turns, and selected capability
Model → side effectDestructive, financial, or external actions require policy or confirmation outside model textProposed action, confirmation state, executing identity, and result
Operation → audit and retestA consequential call can be reconstructed and replayed after a fixCorrelated request, model, authorization, tool, result, version, and retest record

The report should also name every server, client, tool, resource, prompt, identity, and workflow excluded from scope. Unlisted capabilities are residual risk, not an implied pass.

Who it is for

You are using or building MCP servers for an AI product, internal copilot, developer tool, operations agent, research assistant, customer-support system, or enterprise integration. The MCP server may be internal-only, customer-deployed, or part of a SaaS feature. If an LLM can reach it, a reviewer will eventually ask what prevents unsafe tool use and data exposure.

What we test

Server and capability inventory

We enumerate MCP servers, exposed tools, resources, prompts, argument schemas, required credentials, and deployment boundaries. The first risk is often simple: the agent can see more capabilities than the user or task needs.

Tool permissions and authorization

Every state-changing or sensitive tool needs authorization outside the model. We test whether the MCP layer and downstream services enforce user, tenant, role, object, and business-policy checks. Prompt instructions are not a substitute for server-side checks.

Resource exposure

MCP resources can expose files, records, snippets, logs, or internal context. We test whether resources are scoped correctly, whether identifiers can be guessed or swapped, and whether one tenant or role can read another’s material.

Prompt and context injection

MCP systems can carry prompt templates, tool descriptions, resource text, and external content into the model. We test whether untrusted content can influence tool use, bypass policy, reveal hidden context, or turn a resource into an instruction channel.

Secrets and deployment posture

We inspect how credentials are stored, passed, rotated, and logged; whether servers run with least privilege; whether local and remote MCP deployments make different trust assumptions; and whether dangerous operations are isolated.

Auditability and retest

For every meaningful tool call, you should be able to reconstruct the initiating user, model turn, arguments, authorization decision, tool result, and final response. We test whether that evidence exists and can support remediation and retest.

What you get

  • A map of MCP servers, clients, tools, resources, prompts, identities, and trust boundaries.
  • Reproducible findings with request, context, and tool-call evidence.
  • Severity tied to data exposure, unauthorized action, privilege escalation, or procurement risk.
  • A fix plan for capability scoping, authorization, resource handling, secrets, and logging.
  • One retest pass after the agreed fixes.

Scope, access, process, and limits

Before testing, we agree the production-reachable MCP server inventory, clients and hosts, manifests, tool and resource schemas, prompts, representative users and tenants, controlled test host, caller and downstream authorization path, environment, and workflow boundaries. You provide controlled access and the tool-call traces needed to reconstruct each tested action; we use least privilege and do not require raw production secrets.

We map the servers, capabilities, identities, and trust boundaries first, validate the test host and evidence path, run the agreed authorization, resource-scope, injection, side-effect, secrets, and traceability tests, produce reproducible findings and a prioritized fix plan, and retest confirmed fixes once.

The assessment applies only to the named servers, clients, manifests, tools, resources, prompts, identities, environments, and workflows. It does not make MCP itself a security boundary or certify the consuming agent as safe. Untested capabilities and later manifest, permission, client, server, or workflow changes remain residual risk.

Controls we expect to verify

Strong MCP deployments usually have these properties:

  • Narrow tools with explicit schemas and no hidden broad privileges.
  • Server-side authorization for every sensitive read or write.
  • Tenant and role scope enforced before resources enter the model.
  • Secrets kept out of prompts, logs, and model-visible context.
  • Destructive actions gated by external confirmation or policy.
  • Complete traces for model decisions and tool calls.
  • An eval or regression set for prompt injection and tool-abuse cases.

We verify those controls against your implementation and report the exact gaps.

Where this fits

MCP security overlaps with agent security. If the main risk is a tool-using agent, review the AI Agent Security Assessment. If the MCP servers and exposed capabilities are the focus, read the MCP security guide and then scope an MCP security assessment. For a wider product review that includes red-teaming, evals, and production-readiness, start with the AI Product Readiness Assessment. MCP and agent surfaces expand the test matrix, so they price in a higher band — what an AI security audit costs breaks down the drivers. The sample report shows how MCP evidence is packaged, our methodology explains the test process, trust and data handling defines access, confidentiality, and retest boundaries, and the public verification profile collects proof links a buyer can inspect before signing.

Frequently asked

What MCP surfaces do you review?
MCP servers, tools, resources, prompts, host/client assumptions, authentication, authorization, secrets handling, destructive operations, logging, and the agent workflows that consume those capabilities.
Is MCP security just tool-calling security?
Tool security is the core, but MCP also adds server discovery, resources, prompts, client trust assumptions, connector boundaries, and deployment posture. We review the protocol surface as it is used in your product.
Can you assess internal MCP servers?
Yes, if the scope is authorized and access is provided through a controlled test environment. We default to least privilege and written rules of engagement.

There's a security review between you and your next deal.