Softlander Book a call
Agent-to-agent interoperability

MCP architecture and security

Design an MCP integration around explicit resource and authority boundaries

Several MCP servers are being added to a common agent environment. The decision is how to design an MCP integration around explicit resource and authority boundaries. 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 tool platform architects and application security 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 interaction contracts relationship

  1. Starting evidenceClient

    Establish the basis for client authority.

  2. Decision boundaryServer exposure

    Map available tools and their enforcement points.

  3. Decision artefactMCP architecture proposal

    Retain the scoped finding and its unresolved dependencies.

Proposed working model. Untested peers require their own compatibility evidence.

Decision

Frame the decision around client authority

Questions and the evidence they need

Criterion / evidenceClient authority
Inspect client for the relevant constraint or observation.
Criterion / evidenceServer exposure
Inspect server configurations for the relevant constraint or observation.
Criterion / evidenceData movement
Inspect tool inventories 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 design an MCP integration around explicit resource and authority boundaries. This is relevant to tool platform architects and application security owners when several MCP servers are being added to a common agent environment. 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 convenient connection settings give tools more data or action authority than the workflow needs. 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

MCP architecture must expose its trust and data boundaries

Relationships within interaction contracts

Source or conditionClient authority
Identify the task and credentials entering the exchange.
Crossing or choiceServer exposure
Map available tools and their enforcement points.
Consequence or decisionData movement
Trace resource access and result handling.
Compare authority and state at the receiving boundary. Each relationship needs evidence in the actual scope.

What this specialty examines

MCP architecture should identify which clients trust which servers and which resources each tool can affect. Record authentication, tool eligibility, permission enforcement and data movement in the chosen deployment. Interface consistency does not remove the need to assess server behaviour.

The review should map server trust, tool exposure, permission enforcement and data handling in the actual deployment. 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, a consistent interface reduces connection work while server trust and permissions remain deployment choices. 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 client authority

Illustrative working format

BasisClient
Identify provenance and the specific decision this material can inform.
ContextServer configurations
Match this description to the deployed or proposed boundary being examined.
ObservationTool inventories
Name the custodian and the conditions requiring a refreshed version.
DependencyIdentity flows
Use nonsecret metadata to trace issuance, acceptance, and withdrawal responsibility.
Illustrative preparation record. Availability, revision, and handling need confirmation.

Start with client and server configurations, tool inventories, identity flows and data paths. 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 integration owner, agreed expectations for a representative interaction case, and the authority to inspect the relevant boundary. Specify what evidence would distinguish the failure in which convenient connection settings give tools more data or action authority than the workflow needs 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 client authority through to an accountable finding

From the scoped material to a decision record

  1. Establish conditionsClient

    Agree the task meaning at the sending boundary.

  2. Examine the relationshipServer exposure

    Apply the scoped check to data movement.

  3. Retain the findingMCP architecture proposal

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

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

Fix the interaction contract and versions

Assemble client and server configurations, tool inventories, identity flows and data paths with tool platform architects and application security owners. Identify the participating implementations, interface revisions, authority assumptions and intended business result. Prepare messages and task-state examples from both sides, including an interrupted exchange and a disputed or incomplete outcome. The preparation output is a paired contract fixture showing what each participant expects and which differences would prevent the workflow from completing correctly.

Run and compare both sides of the exchange

Separate connection design from action authorisation. Inspect how new tools become available, how configuration changes are reviewed and where denied actions stop. Limit conclusions to the actual implementation and version reviewed rather than generalizing to every MCP deployment.

Choose the contract or integration change

Summarise the comparison in an MCP architecture proposal with trust-boundary and control-placement decisions. Classify each mismatch as interface validation, business meaning, identity, task state or operating behaviour. Decide whether to change a participant, add an explicit adapter rule, narrow supported combinations or defer the connection. Validate the affected pair again and preserve limitations that translation cannot resolve, especially around cancellation, authority and partial completion.

Indicative artefact

Make the MCP architecture proposal usable by its owner

MCP architecture proposal

Illustrative working format

Annotated fieldMCP architecture proposal
Identify the assessed workflow, revision, and decision boundary.
Annotated fieldTrust-boundary
Link supporting and contrary observations to inspectable evidence.
Annotated fieldControl-placement decisions
Name the unresolved condition, next action, and accountable owner.
Illustrative artefact structure, not a completed engagement or an observed result.

A useful decision artefact is an MCP architecture proposal with trust-boundary and control-placement decisions. 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 data movement through a constructed exception

A constructed case and its decision paths

Illustrative scenario

  1. SituationClient authority

    A client discovers a tool whose resource permissions exceed the intended workflow.

  2. Question to examineServer exposure

    Map the discovered tool to its actual resource-side permission check.

  3. Conditional next actionData movement

    Limit exposure where the advertised interface exceeds intended authority.

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

Consider a fictional situation: an agent connects to both internal records and external search through a common tool layer. The scenario is illustrative, with no client engagement, executed test or measured improvement implied.

For internal records and external search, consider whether one agent should expose information from the first tool to the second. Tool availability and permitted information flow are different decisions. The architecture should make both explicit.

Scope and next action

Keep the conclusion within named implementations and revisions

Confirm fit before the next commitment

Included boundaryClient authority
This review is limited to named implementations and revisions.
PrerequisiteClient
The relevant owner must confirm access and the intended operating conditions.
Claim limitMCP architecture proposal
Untested peers require their own compatibility evidence.
Bring the triggering change and existing evidence; resolve the dependency that could alter the decision.

Compatibility is assessed for named implementations, versions, features and workflows. It does not establish universal conformance, vendor endorsement or interoperability with untested peers. 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 several MCP servers are being added to a common agent environment; confirm which missing observation would change the owner’s next action.

Ways to engage

Related engagement scopes

AI Agent Protocol Interoperability Lab

Find where connected agents disagree. Exercise message contracts, identity propagation and failure recovery across your selected integrations.

Read about this offer

Continue exploring

Related insights and resources

Evaluation & assurance6 MIN READ

How to design a joint AI evaluation lab

A joint lab should be a governed way to create decision evidence across organisations, with shared methods but explicit ownership of systems, data and conclusions.

Agent security6 MIN READ

Agent protocols are creating a new control surface

Protocols make tools and agents interoperable, but they also standardise discovery, delegation and context exchange. Those interfaces need explicit trust and policy controls.

Agent security6 MIN READ

A practical security review for an MCP server

Review an MCP server as a privileged protocol adapter: verify tool semantics, OAuth boundaries, token audience, downstream delegation, input handling, isolation, logging and consent.

A little more clarity

Questions to consider.

Start with the questions that shape a better decision.

Should every available MCP tool be exposed to the agent?

No. Expose tools according to workflow need, trust and authorised action scope. Connection availability and tool eligibility are separate decisions, and newly discovered functions should not silently gain authority.

Which configurations define MCP server trust?

Start with client and server configurations, tool inventories, identity flows and data paths. 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 tool exposure and data flow be reviewed?

Map server trust, tool exposure, permission enforcement and data handling in the actual deployment. Compare both participants' accepted inputs, task states and results under a named interface revision. Include interrupted or delayed interactions. Parser acceptance should not be treated as agreement about business meaning, authority or completion.

What belongs in an MCP architecture proposal?

The proposed output is an MCP architecture proposal with trust-boundary and control-placement decisions. 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 a connected tool remain unavailable?

Keep a connected tool unavailable when its authority, data flows or behaviour exceed the intended workflow or remain unverified. Connection configuration and action eligibility should be separately controlled.

What if existing evidence already answers the question?

Review its scope, provenance and configuration before proposing new work. Existing work from tool platform architects and application security 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 client and server configurations, tool inventories, identity flows and data paths 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

Agent2Agent protocol evaluation

Evaluate a chosen Agent2Agent implementation against workflow expectations. The review connects selected specification revision, implementation documentation, task states and authentication settings to a bounded review of agent interaction contracts, giving the integration owner a clearer basis for the next action.

Agent protocol compatibility testing

Verify compatibility between concrete agent protocol implementations. The review connects version matrices, supported features, message examples and failure responses to a bounded review of agent interaction contracts, giving the integration owner a clearer basis for the next action.

Cross-vendor agent integration

Integrate agents from different vendors around one accountable workflow. The review connects vendor interface documentation, task contracts, identity requirements and exit constraints to a bounded review of agent interaction contracts, giving the integration owner a clearer basis for the next action.