Softlander Book a call
Agent security and cybersecurity

MCP server security review

Inspect the authority exposed by a particular MCP server integration

An agent is connected to an MCP server with access to business resources. The decision is how to inspect the authority exposed by a particular MCP server integration. The work begins with your actual workflow and looks for the evidence that separates intended behaviour from a consequential exception. It is particularly relevant to integration security reviewers and tool platform owners. A useful outcome is an explicit account of what was examined, what remains uncertain, and which decision the evidence can support.

Book a 30 minute readiness callBrowse this capability group

The agent security relationship

  1. Starting evidenceServer version

    Establish the basis for tool definition.

  2. Decision boundaryCaller identity

    Resolve authentication and permitted operation scope.

  3. Decision artefactMCP server review

    Retain the scoped finding and its unresolved dependencies.

Proposed working model. A bounded challenge cannot establish exhaustive protection.

Decision

Frame the decision around tool definition

Questions and the evidence they need

Criterion / evidenceTool definition
Inspect server version for the relevant constraint or observation.
Criterion / evidenceCaller identity
Inspect exposed tool definitions for the relevant constraint or observation.
Criterion / evidenceResource effect
Inspect authentication settings for the relevant constraint or observation.
Read each criterion against the available evidence before deciding that additional work is needed.

The decision is how to inspect the authority exposed by a particular MCP server integration. This is relevant to integration security reviewers and tool platform owners when an agent is connected to an MCP server with access to business resources. Name the affected workflow, the consequence of a wrong decision, and the owner who can act on the result. The initial discussion should establish which evidence is already available and which uncertainty is material enough to investigate.

The specific failure hypothesis is that a tool description conceals broad side effects or the server executes using unrestricted shared credentials. It remains a hypothesis until examined in the deployment. Existing internal tests or operating records may already resolve it; identify the uncovered question before commissioning additional work.

Mechanism

An MCP server review follows exposed actions to resources

Relationships within agent security

Source or conditionTool definition
Inspect the installed interface and argument meaning.
Crossing or choiceCaller identity
Resolve authentication and permitted operation scope.
Consequence or decisionResource effect
Check actual access behind accepted tool requests.
Observe the control and resulting business effect. Each relationship needs evidence in the actual scope.

What this specialty examines

MCP server review concerns the actual installed server, exposed tools and resource authority. Record implementation version, configuration and trust assumptions. A standardised interface does not establish that the server’s tools are narrow, correctly implemented or appropriate for the workflow.

The review should review the installed server and permitted interactions, then test argument, identity and action boundaries. Identify the normal route, relevant exceptions and the authoritative record of the outcome. Inspect the relevant business-system record, enforcement event or process evidence alongside any reported status. Keep incomplete cases visible, with an explanation of what their absence prevents the owner from concluding.

The tradeoff to make explicit

For this decision, standardised interfaces simplify connection while each server’s actual behaviour still needs assessment. Compare the available design or operating choices against the same intended outcome. If one option removes a required control or changes the task boundary, describe that difference before treating its apparent simplicity, speed or lower effort as an improvement. The decision should expose the tradeoff instead of burying it in an aggregate score.

Preparation

Connect the working inputs to the boundary being examined

Evidence packet for tool definition

Illustrative working format

BasisServer version
Match this description to the deployed or proposed boundary being examined.
ContextExposed tool definitions
Check its relationship to the relevant workflow and expose missing context.
ObservationAuthentication settings
Identify the expected principal, audience, and verifier response to invalid evidence.
DependencyResource permissions
Specify the subject, operation, resource, and context at the enforcing boundary.
Illustrative preparation record. Availability, revision, and handling need confirmation.

Start with server version, exposed tool definitions, authentication settings and resource permissions. Identify the owner, revision and operating context of each source. Sanitised examples may support initial design, but differences from actual conditions should remain explicit. Where direct access is unsuitable, a customer-controlled evidence or execution route may be considered, with agreed handling and retention.

The scope also needs the security decision owner, agreed expectations for a representative threat scenario, and the authority to inspect the relevant boundary. Specify what evidence would distinguish the failure in which a tool description conceals broad side effects or the server executes using unrestricted shared credentials from acceptable behaviour. If stakeholders disagree about intended behaviour, resolve the interpretation before classifying the observed difference as a defect.

How the work proceeds

Carry tool definition through to an accountable finding

From the scoped material to a decision record

  1. Establish conditionsServer version

    Define the hypothetical attacker’s starting influence.

  2. Examine the relationshipCaller identity

    Apply the scoped check to resource effect.

  3. Retain the findingMCP server review

    Record the evidence, open dependencies, and the owner’s next decision.

Proposed sequence; resolve interpretation or access gaps before relying on the next step.

Define the controlled threat scenario

Review server version, exposed tool definitions, authentication settings and resource permissions with integration security reviewers and tool platform owners. State what the hypothetical attacker controls, the protected action and the systems included in the authorised exercise. Prepare synthetic records and harmless markers where appropriate, with stopping conditions for unexpected effects. The preparation output is a scenario brief that distinguishes an influence attempt from a prohibited action actually reaching a business resource.

Challenge the path and review effects

Inspect authentication, permissions, argument validation, side effects and data movement. Test only authorised interactions with synthetic resources. Keep server-specific findings distinct from claims about the protocol as a whole.

Select a control response and retest

Build an MCP server review with interface, authority and configuration findings from the reviewed observations. Separate agent behaviour, application enforcement and the resulting resource state so the recommended change reaches the responsible layer. Choose a bounded retest that reproduces the original condition and checks legitimate behaviour after remediation. If the required investigation exceeds the agreed technique or expertise, retain the unresolved path and identify the qualified review needed.

Indicative artefact

Make the MCP server review usable by its owner

MCP server review

Illustrative working format

Annotated fieldMCP server review
Identify the assessed workflow, revision, and decision boundary.
Annotated fieldInterface
Record accepted inputs, task meaning, and incomplete or failed outcome semantics.
Annotated fieldAuthority
Specify the acting role, allowed resource effect, and enforcement boundary.
Illustrative artefact structure, not a completed engagement or an observed result.

A useful decision artefact is an MCP server review with interface, authority and configuration findings. Supporting material may include selected cases, configuration or process records, evidence references, a disagreement log and prioritised actions. Retain the case selection rationale and material disagreements alongside the result; otherwise the result may be mistaken for complete coverage.

Illustrative scenario

Examine resource effect through a constructed exception

A constructed case and its decision paths

Illustrative scenario

  1. SituationTool definition

    A valid tool request reaches a resource beyond the caller's approved scope.

  2. Question to examineCaller identity

    Compare the caller mandate with the resource actually reached by the tool.

  3. Conditional next actionResource effect

    Restrict the server-side action boundary where caller scope is lost.

Fictional example. No executed test, customer engagement, or measured outcome is implied.

Consider a fictional situation: a fictional document server exposes a convenience tool that can also modify sharing permissions. The scenario is illustrative, with no client engagement, executed test or measured improvement implied.

For document sharing, compare the tool’s description with its effective operations and privileges. If a convenience action changes permissions, make that consequence visible and enforceable. The agent should not receive sharing authority merely because it needs to retrieve a document.

Scope and next action

Keep the conclusion within the agreed threat scenario

Confirm fit before the next commitment

Included boundaryTool definition
This review is limited to the agreed threat scenario.
PrerequisiteServer version
The relevant owner must confirm access and the intended operating conditions.
Claim limitMCP server review
A bounded challenge cannot establish exhaustive protection.
Bring the triggering change and existing evidence; resolve the dependency that could alter the decision.

Authorised scenario testing is not a claim of exhaustive penetration testing or guaranteed protection. Intrusive security work requires qualified specialists and a separately agreed scope. Any engagement depends on an agreed scope, qualified team, authorised access and confirmed availability. Bring the affected workflow, its current configuration or process, the triggering change and the evidence already available. The immediate scope question is prompted by the situation in which an agent is connected to an MCP server with access to business resources; confirm which missing observation would change the owner’s next action.

Ways to engage

Related engagement scopes

Agent Release Readiness Review

The Agent Release Readiness Review is a fixed-scope, three-week independent test of one AI agent workflow that shows a release board what the agent does, what it is allowed to do and what happens when it is wrong, and ends in a signed recommendation.

3 weeksRead about this offer

AI Agent Runtime Security Review

Make every delegation explicit. Examine who the agent acts for, where it can execute and which tools it can reach when instructions alone are not enough.

Read about this offer

AI Agent Red Team

Challenge the boundaries that matter to your workflow. Test agreed attack scenarios against agent instructions, tools and data access.

Read about this offer

Continue exploring

Related insights and resources

Agent security6 MIN READ

The permission boundary behind every agent action

An agent can only be evaluated in the context of what its tools allow. Examine identity, delegated authority and action boundaries before you put a workflow in motion.

Whitepaper5 MIN READ

Before your agent can act, define its authority

A working paper for the moment an AI system moves from advice to action. Map identity, permissions, approvals and recovery into an authority model your team can review and test.

Agent security6 MIN READ

Running an AI-agent incident tabletop exercise

A useful tabletop follows one plausible agent failure through detection, containment, evidence, business recovery and accountable return to service.

A little more clarity

Questions to consider.

Start with the questions that shape a better decision.

Does using MCP make a server safe to connect?

No. Assess the actual server implementation, configuration, tools and resource authority. Protocol use does not establish appropriate permissions, trustworthy behaviour or safe deployment for a particular workflow.

Which server records reveal MCP tool authority?

Start with server version, exposed tool definitions, authentication settings and resource permissions. Record their revision, owner and relationship to the intended workflow. Missing context should be identified before interpreting outcomes; a sanitised fixture is useful only when its relevant differences from the operating case are understood.

How should actual server side effects be checked?

Review the installed server and permitted interactions, then test argument, identity and action boundaries. State the hypothetical attacker's control and inspect attempted actions, tool enforcement and actual effects separately. A refusal, a blocked call and a successful prohibited action are different results. Preserve unsuccessful challenges as well as adverse findings.

What belongs in an MCP server findings report?

The proposed output is an MCP server review with interface, authority and configuration findings. Include the selected conditions, supporting observations, unresolved differences and next decision. A reviewer should be able to follow each important conclusion back to its evidence and understand the limits without depending on an undocumented explanation from the author.

When should an exposed tool be withheld?

Withhold a tool when its behaviour, authority or data handling exceeds the intended task or lacks sufficient evidence. Connection success and a plausible description do not establish that it belongs in the agent's available action set.

What if existing evidence already answers the question?

Review its scope, provenance and configuration before proposing new work. Existing work from integration security reviewers and tool platform owners may already be sufficient. In that case, capture the decision, unresolved limitations and the change that would require another review. Additional assessment should address a real gap.

What would make the findings inconclusive?

Missing server version, exposed tool definitions, authentication settings and resource permissions can prevent a reliable interpretation, depending on the case. Record the specific missing observation and its implication. The owner can supply evidence, narrow the claim or defer the dependent decision; an incomplete case should not silently be counted as a pass.

Start with the decision you need to make.

Tell us about the agent workflow you want reviewed, and where you need greater clarity. Scope and availability are confirmed together.

Book a 30 minute readiness call Get the agent release checklist

Connected disciplines

Adversarial agent testing

Challenge a defined agent workflow using authorised adversarial scenarios. The review connects rules of engagement, threat hypotheses, synthetic data and stop conditions to a bounded review of agent security, giving the security decision owner a clearer basis for the next action.

AI incident-response planning

Prepare an operational response to agent-related incidents. The review connects system ownership, tool privileges, incident classes and evidence-retention controls to a bounded review of agent security, giving the security decision owner a clearer basis for the next action.

Agent kill-switch and containment design

Design a reliable way to stop agent action and contain remaining authority. The review connects worker queues, credential paths, scheduler controls and cancellation semantics to a bounded review of agent security, giving the security decision owner a clearer basis for the next action.